Dense neural network with Keras

3.1. Dense neural network with Keras#

Authors: Javier Duarte, Raghav Kansal

Run this cell to download the data if you did not already download it in from Tutorial #1:

!mkdir -p data
!wget -O data/ntuple_4mu_bkg.root "https://zenodo.org/record/3901869/files/ntuple_4mu_bkg.root?download=1"
!wget -O data/ntuple_4mu_VV.root "https://zenodo.org/record/3901869/files/ntuple_4mu_VV.root?download=1"

3.1.1. Loading `pandas` DataFrames#

Now we load two different NumPy arrays. One corresponding to the VV signal and one corresponding to the background.

import uproot
import numpy as np
import pandas as pd
import h5py

# fix random seed for reproducibility
seed = 7
np.random.seed(seed)

treename = "HZZ4LeptonsAnalysisReduced"
filename = {}
upfile = {}
df = {}

filename["VV"] = "data/ntuple_4mu_VV.root"
filename["bkg"] = "data/ntuple_4mu_bkg.root"

VARS = ["f_mass4l", "f_massjj"]  # choose which vars to use (2d)

upfile["VV"] = uproot.open(filename["VV"])
upfile["bkg"] = uproot.open(filename["bkg"])

df["bkg"] = upfile["bkg"][treename].arrays(VARS, library="pd")
df["VV"] = upfile["VV"][treename].arrays(VARS, library="pd")

# cut out undefined variables VARS[0] and VARS[1] > -999
df["VV"] = df["VV"][(df["VV"][VARS[0]] > -999) & (df["VV"][VARS[1]] > -999)]
df["bkg"] = df["bkg"][(df["bkg"][VARS[0]] > -999) & (df["bkg"][VARS[1]] > -999)]

# add isSignal variable
df["VV"]["isSignal"] = np.ones(len(df["VV"]))
df["bkg"]["isSignal"] = np.zeros(len(df["bkg"]))

3.1.2. Define the model#

We’ll start with a dense (fully-connected) NN layer. Our model will have a single fully-connected hidden layer with the same number of neurons as input variables. The weights are initialized using a small Gaussian random number. We will switch between linear and tanh activation functions for the hidden layer. The output layer contains a single neuron in order to make predictions. It uses the sigmoid activation function in order to produce a probability output in the range of 0 to 1.

We are using the binary_crossentropy loss function during training, a standard loss function for binary classification problems. We will optimize the model with the Adam algorithm for stochastic gradient descent and we will collect accuracy metrics while the model is trained.

# baseline keras model
from tensorflow.keras.models import Sequential, Model
from tensorflow.keras.optimizers import SGD
from tensorflow.keras.layers import (
    Input,
    Activation,
    Dense,
    Convolution2D,
    MaxPooling2D,
    Dropout,
    Flatten,
)

NDIM = len(VARS)
inputs = Input(shape=(NDIM,), name="input")
outputs = Dense(1, name="output", kernel_initializer="normal", activation="sigmoid")(inputs)

# creae the model
model = Model(inputs=inputs, outputs=outputs)
# compile the model
model.compile(optimizer="adam", loss="binary_crossentropy", metrics=["accuracy"])
# print the model summary
model.summary()

Model: "model_1"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 input (InputLayer)          [(None, 2)]               0         
                                                                 
 output (Dense)              (None, 1)                 3         
                                                                 
=================================================================
Total params: 3 (12.00 Byte)
Trainable params: 3 (12.00 Byte)
Non-trainable params: 0 (0.00 Byte)
_________________________________________________________________

3.1.3. Dividing the data into testing and training dataset#

We will split the data into two parts (one for training+validation and one for testing). We will also apply “standard scaling” preprocessing: http://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.StandardScaler.html i.e. making the mean = 0 and the RMS = 1 for all input variables (based only on the training/validation dataset). We will also define our early stopping criteria to prevent over-fitting and we will save the model based on the best val_loss.

df_all = pd.concat([df["VV"], df["bkg"]])
dataset = df_all.values
X = dataset[:, 0:NDIM]
Y = dataset[:, NDIM]

from sklearn.model_selection import train_test_split

X_train_val, X_test, Y_train_val, Y_test = train_test_split(X, Y, test_size=0.2, random_state=7)

# preprocessing: standard scalar
from sklearn.preprocessing import StandardScaler

scaler = StandardScaler().fit(X_train_val)
X_train_val = scaler.transform(X_train_val)
X_test = scaler.transform(X_test)

# early stopping callback
from tensorflow.keras.callbacks import EarlyStopping

early_stopping = EarlyStopping(monitor="val_loss", patience=10)

# model checkpoint callback
# this saves our model architecture + parameters into dense_model.h5
from tensorflow.keras.callbacks import ModelCheckpoint

model_checkpoint = ModelCheckpoint(
    "dense_model.h5",
    monitor="val_loss",
    verbose=0,
    save_best_only=True,
    save_weights_only=False,
    mode="auto",
    save_freq="epoch",
)

3.1.4. Run training#

Here, we run the training.

# Train classifier
history = model.fit(
    X_train_val,
    Y_train_val,
    epochs=1000,
    batch_size=1024,
    verbose=1,
    callbacks=[early_stopping, model_checkpoint],
    validation_split=0.25,
)

Epoch 1/1000
13/13 [==============================] - 0s 9ms/step - loss: 0.6877 - accuracy: 0.6873 - val_loss: 0.6827 - val_accuracy: 0.8218
Epoch 2/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.6789 - accuracy: 0.8704 - val_loss: 0.6741 - val_accuracy: 0.9024
Epoch 3/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.6703 - accuracy: 0.9211 - val_loss: 0.6656 - val_accuracy: 0.9388
Epoch 4/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.6620 - accuracy: 0.9416 - val_loss: 0.6574 - val_accuracy: 0.9417
Epoch 5/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.6538 - accuracy: 0.9404 - val_loss: 0.6493 - val_accuracy: 0.9400
Epoch 6/1000
 1/13 [=>............................] - ETA: 0s - loss: 0.6493 - accuracy: 0.9492

/Users/raghav/mambaforge/envs/machine-learning-hats-2023/lib/python3.10/site-packages/keras/src/engine/training.py:3000: UserWarning: You are saving your model as an HDF5 file via `model.save()`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')`.
  saving_api.save_model(

13/13 [==============================] - 0s 3ms/step - loss: 0.6458 - accuracy: 0.9385 - val_loss: 0.6415 - val_accuracy: 0.9371
Epoch 7/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.6380 - accuracy: 0.9365 - val_loss: 0.6338 - val_accuracy: 0.9361
Epoch 8/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.6304 - accuracy: 0.9355 - val_loss: 0.6263 - val_accuracy: 0.9359
Epoch 9/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.6230 - accuracy: 0.9350 - val_loss: 0.6191 - val_accuracy: 0.9344
Epoch 10/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.6158 - accuracy: 0.9343 - val_loss: 0.6119 - val_accuracy: 0.9339
Epoch 11/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.6087 - accuracy: 0.9335 - val_loss: 0.6050 - val_accuracy: 0.9337
Epoch 12/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.6018 - accuracy: 0.9326 - val_loss: 0.5982 - val_accuracy: 0.9335
Epoch 13/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.5951 - accuracy: 0.9326 - val_loss: 0.5916 - val_accuracy: 0.9337
Epoch 14/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.5886 - accuracy: 0.9322 - val_loss: 0.5851 - val_accuracy: 0.9332
Epoch 15/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.5822 - accuracy: 0.9322 - val_loss: 0.5789 - val_accuracy: 0.9327
Epoch 16/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.5760 - accuracy: 0.9321 - val_loss: 0.5727 - val_accuracy: 0.9318
Epoch 17/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.5699 - accuracy: 0.9318 - val_loss: 0.5667 - val_accuracy: 0.9318
Epoch 18/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.5640 - accuracy: 0.9317 - val_loss: 0.5609 - val_accuracy: 0.9315
Epoch 19/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.5582 - accuracy: 0.9314 - val_loss: 0.5551 - val_accuracy: 0.9313
Epoch 20/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.5526 - accuracy: 0.9314 - val_loss: 0.5495 - val_accuracy: 0.9311
Epoch 21/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.5470 - accuracy: 0.9313 - val_loss: 0.5441 - val_accuracy: 0.9308
Epoch 22/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.5417 - accuracy: 0.9312 - val_loss: 0.5388 - val_accuracy: 0.9308
Epoch 23/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.5364 - accuracy: 0.9310 - val_loss: 0.5336 - val_accuracy: 0.9308
Epoch 24/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.5312 - accuracy: 0.9308 - val_loss: 0.5285 - val_accuracy: 0.9306
Epoch 25/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.5262 - accuracy: 0.9306 - val_loss: 0.5234 - val_accuracy: 0.9303
Epoch 26/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.5212 - accuracy: 0.9303 - val_loss: 0.5186 - val_accuracy: 0.9303
Epoch 27/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.5164 - accuracy: 0.9302 - val_loss: 0.5138 - val_accuracy: 0.9303
Epoch 28/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.5117 - accuracy: 0.9301 - val_loss: 0.5091 - val_accuracy: 0.9298
Epoch 29/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.5071 - accuracy: 0.9298 - val_loss: 0.5046 - val_accuracy: 0.9298
Epoch 30/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.5026 - accuracy: 0.9300 - val_loss: 0.5001 - val_accuracy: 0.9298
Epoch 31/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4982 - accuracy: 0.9300 - val_loss: 0.4957 - val_accuracy: 0.9291
Epoch 32/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4938 - accuracy: 0.9299 - val_loss: 0.4914 - val_accuracy: 0.9286
Epoch 33/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4896 - accuracy: 0.9298 - val_loss: 0.4872 - val_accuracy: 0.9286
Epoch 34/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4854 - accuracy: 0.9297 - val_loss: 0.4831 - val_accuracy: 0.9286
Epoch 35/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4813 - accuracy: 0.9297 - val_loss: 0.4790 - val_accuracy: 0.9286
Epoch 36/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4774 - accuracy: 0.9294 - val_loss: 0.4751 - val_accuracy: 0.9284
Epoch 37/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4735 - accuracy: 0.9294 - val_loss: 0.4712 - val_accuracy: 0.9279
Epoch 38/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4697 - accuracy: 0.9294 - val_loss: 0.4674 - val_accuracy: 0.9279
Epoch 39/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4659 - accuracy: 0.9292 - val_loss: 0.4637 - val_accuracy: 0.9279
Epoch 40/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4622 - accuracy: 0.9290 - val_loss: 0.4600 - val_accuracy: 0.9279
Epoch 41/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4586 - accuracy: 0.9288 - val_loss: 0.4565 - val_accuracy: 0.9279
Epoch 42/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4551 - accuracy: 0.9286 - val_loss: 0.4529 - val_accuracy: 0.9279
Epoch 43/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4516 - accuracy: 0.9285 - val_loss: 0.4495 - val_accuracy: 0.9279
Epoch 44/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4482 - accuracy: 0.9285 - val_loss: 0.4461 - val_accuracy: 0.9277
Epoch 45/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4449 - accuracy: 0.9285 - val_loss: 0.4428 - val_accuracy: 0.9274
Epoch 46/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4417 - accuracy: 0.9285 - val_loss: 0.4396 - val_accuracy: 0.9274
Epoch 47/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4385 - accuracy: 0.9285 - val_loss: 0.4364 - val_accuracy: 0.9272
Epoch 48/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4353 - accuracy: 0.9282 - val_loss: 0.4333 - val_accuracy: 0.9272
Epoch 49/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4322 - accuracy: 0.9282 - val_loss: 0.4302 - val_accuracy: 0.9272
Epoch 50/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4292 - accuracy: 0.9282 - val_loss: 0.4272 - val_accuracy: 0.9272
Epoch 51/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4262 - accuracy: 0.9282 - val_loss: 0.4242 - val_accuracy: 0.9270
Epoch 52/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4233 - accuracy: 0.9281 - val_loss: 0.4213 - val_accuracy: 0.9270
Epoch 53/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4205 - accuracy: 0.9281 - val_loss: 0.4185 - val_accuracy: 0.9265
Epoch 54/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4177 - accuracy: 0.9279 - val_loss: 0.4157 - val_accuracy: 0.9265
Epoch 55/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4149 - accuracy: 0.9278 - val_loss: 0.4129 - val_accuracy: 0.9265
Epoch 56/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4122 - accuracy: 0.9278 - val_loss: 0.4102 - val_accuracy: 0.9262
Epoch 57/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4095 - accuracy: 0.9277 - val_loss: 0.4075 - val_accuracy: 0.9262
Epoch 58/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4069 - accuracy: 0.9277 - val_loss: 0.4049 - val_accuracy: 0.9262
Epoch 59/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4043 - accuracy: 0.9277 - val_loss: 0.4023 - val_accuracy: 0.9262
Epoch 60/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.4018 - accuracy: 0.9277 - val_loss: 0.3998 - val_accuracy: 0.9260
Epoch 61/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3993 - accuracy: 0.9275 - val_loss: 0.3973 - val_accuracy: 0.9257
Epoch 62/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3969 - accuracy: 0.9273 - val_loss: 0.3949 - val_accuracy: 0.9257
Epoch 63/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3945 - accuracy: 0.9273 - val_loss: 0.3925 - val_accuracy: 0.9257
Epoch 64/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3921 - accuracy: 0.9273 - val_loss: 0.3901 - val_accuracy: 0.9257
Epoch 65/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3898 - accuracy: 0.9273 - val_loss: 0.3878 - val_accuracy: 0.9257
Epoch 66/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3875 - accuracy: 0.9273 - val_loss: 0.3855 - val_accuracy: 0.9257
Epoch 67/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3852 - accuracy: 0.9273 - val_loss: 0.3833 - val_accuracy: 0.9257
Epoch 68/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3830 - accuracy: 0.9273 - val_loss: 0.3811 - val_accuracy: 0.9257
Epoch 69/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3809 - accuracy: 0.9273 - val_loss: 0.3789 - val_accuracy: 0.9260
Epoch 70/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3787 - accuracy: 0.9273 - val_loss: 0.3768 - val_accuracy: 0.9260
Epoch 71/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3766 - accuracy: 0.9274 - val_loss: 0.3747 - val_accuracy: 0.9260
Epoch 72/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3746 - accuracy: 0.9274 - val_loss: 0.3726 - val_accuracy: 0.9260
Epoch 73/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3725 - accuracy: 0.9274 - val_loss: 0.3705 - val_accuracy: 0.9260
Epoch 74/1000
13/13 [==============================] - 0s 5ms/step - loss: 0.3705 - accuracy: 0.9273 - val_loss: 0.3685 - val_accuracy: 0.9260
Epoch 75/1000
13/13 [==============================] - 0s 5ms/step - loss: 0.3686 - accuracy: 0.9273 - val_loss: 0.3666 - val_accuracy: 0.9260
Epoch 76/1000
13/13 [==============================] - 0s 5ms/step - loss: 0.3666 - accuracy: 0.9273 - val_loss: 0.3646 - val_accuracy: 0.9260
Epoch 77/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.3647 - accuracy: 0.9274 - val_loss: 0.3627 - val_accuracy: 0.9260
Epoch 78/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.3629 - accuracy: 0.9274 - val_loss: 0.3608 - val_accuracy: 0.9260
Epoch 79/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.3610 - accuracy: 0.9274 - val_loss: 0.3590 - val_accuracy: 0.9257
Epoch 80/1000
13/13 [==============================] - 0s 6ms/step - loss: 0.3592 - accuracy: 0.9273 - val_loss: 0.3571 - val_accuracy: 0.9257
Epoch 81/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.3574 - accuracy: 0.9274 - val_loss: 0.3553 - val_accuracy: 0.9257
Epoch 82/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3556 - accuracy: 0.9274 - val_loss: 0.3536 - val_accuracy: 0.9257
Epoch 83/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3539 - accuracy: 0.9274 - val_loss: 0.3518 - val_accuracy: 0.9257
Epoch 84/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3522 - accuracy: 0.9275 - val_loss: 0.3501 - val_accuracy: 0.9257
Epoch 85/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3505 - accuracy: 0.9275 - val_loss: 0.3484 - val_accuracy: 0.9257
Epoch 86/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3488 - accuracy: 0.9275 - val_loss: 0.3467 - val_accuracy: 0.9257
Epoch 87/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3472 - accuracy: 0.9275 - val_loss: 0.3451 - val_accuracy: 0.9257
Epoch 88/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3456 - accuracy: 0.9275 - val_loss: 0.3435 - val_accuracy: 0.9257
Epoch 89/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3440 - accuracy: 0.9275 - val_loss: 0.3419 - val_accuracy: 0.9260
Epoch 90/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3424 - accuracy: 0.9276 - val_loss: 0.3403 - val_accuracy: 0.9262
Epoch 91/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3409 - accuracy: 0.9276 - val_loss: 0.3387 - val_accuracy: 0.9262
Epoch 92/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3393 - accuracy: 0.9277 - val_loss: 0.3372 - val_accuracy: 0.9262
Epoch 93/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3379 - accuracy: 0.9277 - val_loss: 0.3357 - val_accuracy: 0.9262
Epoch 94/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3364 - accuracy: 0.9278 - val_loss: 0.3342 - val_accuracy: 0.9262
Epoch 95/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3349 - accuracy: 0.9278 - val_loss: 0.3327 - val_accuracy: 0.9262
Epoch 96/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3335 - accuracy: 0.9279 - val_loss: 0.3313 - val_accuracy: 0.9265
Epoch 97/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3321 - accuracy: 0.9280 - val_loss: 0.3299 - val_accuracy: 0.9267
Epoch 98/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3307 - accuracy: 0.9281 - val_loss: 0.3285 - val_accuracy: 0.9267
Epoch 99/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3293 - accuracy: 0.9281 - val_loss: 0.3271 - val_accuracy: 0.9267
Epoch 100/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3279 - accuracy: 0.9282 - val_loss: 0.3257 - val_accuracy: 0.9267
Epoch 101/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3266 - accuracy: 0.9282 - val_loss: 0.3244 - val_accuracy: 0.9267
Epoch 102/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3253 - accuracy: 0.9282 - val_loss: 0.3230 - val_accuracy: 0.9270
Epoch 103/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3240 - accuracy: 0.9282 - val_loss: 0.3217 - val_accuracy: 0.9270
Epoch 104/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3227 - accuracy: 0.9282 - val_loss: 0.3204 - val_accuracy: 0.9270
Epoch 105/1000
13/13 [==============================] - 0s 5ms/step - loss: 0.3214 - accuracy: 0.9283 - val_loss: 0.3191 - val_accuracy: 0.9270
Epoch 106/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.3202 - accuracy: 0.9283 - val_loss: 0.3179 - val_accuracy: 0.9270
Epoch 107/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.3189 - accuracy: 0.9283 - val_loss: 0.3166 - val_accuracy: 0.9270
Epoch 108/1000
13/13 [==============================] - 0s 5ms/step - loss: 0.3177 - accuracy: 0.9284 - val_loss: 0.3154 - val_accuracy: 0.9272
Epoch 109/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3165 - accuracy: 0.9285 - val_loss: 0.3142 - val_accuracy: 0.9272
Epoch 110/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3153 - accuracy: 0.9287 - val_loss: 0.3130 - val_accuracy: 0.9272
Epoch 111/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3141 - accuracy: 0.9287 - val_loss: 0.3118 - val_accuracy: 0.9272
Epoch 112/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3130 - accuracy: 0.9287 - val_loss: 0.3106 - val_accuracy: 0.9277
Epoch 113/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3118 - accuracy: 0.9289 - val_loss: 0.3094 - val_accuracy: 0.9284
Epoch 114/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3107 - accuracy: 0.9289 - val_loss: 0.3083 - val_accuracy: 0.9284
Epoch 115/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3096 - accuracy: 0.9289 - val_loss: 0.3072 - val_accuracy: 0.9284
Epoch 116/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3085 - accuracy: 0.9290 - val_loss: 0.3061 - val_accuracy: 0.9284
Epoch 117/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3074 - accuracy: 0.9290 - val_loss: 0.3050 - val_accuracy: 0.9284
Epoch 118/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3064 - accuracy: 0.9290 - val_loss: 0.3039 - val_accuracy: 0.9284
Epoch 119/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3053 - accuracy: 0.9291 - val_loss: 0.3028 - val_accuracy: 0.9284
Epoch 120/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3043 - accuracy: 0.9292 - val_loss: 0.3018 - val_accuracy: 0.9284
Epoch 121/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3032 - accuracy: 0.9292 - val_loss: 0.3007 - val_accuracy: 0.9284
Epoch 122/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3022 - accuracy: 0.9292 - val_loss: 0.2997 - val_accuracy: 0.9284
Epoch 123/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3012 - accuracy: 0.9292 - val_loss: 0.2987 - val_accuracy: 0.9286
Epoch 124/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.3002 - accuracy: 0.9292 - val_loss: 0.2976 - val_accuracy: 0.9289
Epoch 125/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2992 - accuracy: 0.9292 - val_loss: 0.2966 - val_accuracy: 0.9289
Epoch 126/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2982 - accuracy: 0.9292 - val_loss: 0.2956 - val_accuracy: 0.9289
Epoch 127/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2973 - accuracy: 0.9293 - val_loss: 0.2947 - val_accuracy: 0.9289
Epoch 128/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2963 - accuracy: 0.9293 - val_loss: 0.2937 - val_accuracy: 0.9291
Epoch 129/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2954 - accuracy: 0.9295 - val_loss: 0.2928 - val_accuracy: 0.9294
Epoch 130/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2945 - accuracy: 0.9296 - val_loss: 0.2918 - val_accuracy: 0.9294
Epoch 131/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2935 - accuracy: 0.9296 - val_loss: 0.2909 - val_accuracy: 0.9294
Epoch 132/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2926 - accuracy: 0.9296 - val_loss: 0.2900 - val_accuracy: 0.9296
Epoch 133/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2918 - accuracy: 0.9297 - val_loss: 0.2891 - val_accuracy: 0.9296
Epoch 134/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2909 - accuracy: 0.9297 - val_loss: 0.2882 - val_accuracy: 0.9296
Epoch 135/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2900 - accuracy: 0.9297 - val_loss: 0.2873 - val_accuracy: 0.9296
Epoch 136/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2892 - accuracy: 0.9298 - val_loss: 0.2864 - val_accuracy: 0.9296
Epoch 137/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2883 - accuracy: 0.9299 - val_loss: 0.2856 - val_accuracy: 0.9296
Epoch 138/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2875 - accuracy: 0.9299 - val_loss: 0.2847 - val_accuracy: 0.9296
Epoch 139/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2866 - accuracy: 0.9299 - val_loss: 0.2839 - val_accuracy: 0.9296
Epoch 140/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2858 - accuracy: 0.9302 - val_loss: 0.2830 - val_accuracy: 0.9296
Epoch 141/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2850 - accuracy: 0.9302 - val_loss: 0.2822 - val_accuracy: 0.9306
Epoch 142/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2842 - accuracy: 0.9302 - val_loss: 0.2814 - val_accuracy: 0.9306
Epoch 143/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2834 - accuracy: 0.9302 - val_loss: 0.2806 - val_accuracy: 0.9306
Epoch 144/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2826 - accuracy: 0.9302 - val_loss: 0.2798 - val_accuracy: 0.9306
Epoch 145/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2818 - accuracy: 0.9305 - val_loss: 0.2790 - val_accuracy: 0.9311
Epoch 146/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2811 - accuracy: 0.9306 - val_loss: 0.2782 - val_accuracy: 0.9313
Epoch 147/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2803 - accuracy: 0.9308 - val_loss: 0.2774 - val_accuracy: 0.9313
Epoch 148/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2796 - accuracy: 0.9309 - val_loss: 0.2766 - val_accuracy: 0.9313
Epoch 149/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.2788 - accuracy: 0.9309 - val_loss: 0.2759 - val_accuracy: 0.9313
Epoch 150/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2781 - accuracy: 0.9310 - val_loss: 0.2751 - val_accuracy: 0.9313
Epoch 151/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2773 - accuracy: 0.9310 - val_loss: 0.2744 - val_accuracy: 0.9315
Epoch 152/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2766 - accuracy: 0.9311 - val_loss: 0.2736 - val_accuracy: 0.9315
Epoch 153/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2759 - accuracy: 0.9313 - val_loss: 0.2729 - val_accuracy: 0.9315
Epoch 154/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2752 - accuracy: 0.9313 - val_loss: 0.2722 - val_accuracy: 0.9315
Epoch 155/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2745 - accuracy: 0.9314 - val_loss: 0.2715 - val_accuracy: 0.9318
Epoch 156/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2738 - accuracy: 0.9314 - val_loss: 0.2707 - val_accuracy: 0.9318
Epoch 157/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2731 - accuracy: 0.9314 - val_loss: 0.2700 - val_accuracy: 0.9318
Epoch 158/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2724 - accuracy: 0.9314 - val_loss: 0.2693 - val_accuracy: 0.9320
Epoch 159/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2717 - accuracy: 0.9316 - val_loss: 0.2687 - val_accuracy: 0.9320
Epoch 160/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2711 - accuracy: 0.9318 - val_loss: 0.2680 - val_accuracy: 0.9320
Epoch 161/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2704 - accuracy: 0.9318 - val_loss: 0.2673 - val_accuracy: 0.9320
Epoch 162/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2698 - accuracy: 0.9318 - val_loss: 0.2666 - val_accuracy: 0.9320
Epoch 163/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2691 - accuracy: 0.9318 - val_loss: 0.2660 - val_accuracy: 0.9320
Epoch 164/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2685 - accuracy: 0.9319 - val_loss: 0.2653 - val_accuracy: 0.9320
Epoch 165/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2679 - accuracy: 0.9319 - val_loss: 0.2647 - val_accuracy: 0.9323
Epoch 166/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2672 - accuracy: 0.9318 - val_loss: 0.2640 - val_accuracy: 0.9327
Epoch 167/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2666 - accuracy: 0.9318 - val_loss: 0.2634 - val_accuracy: 0.9327
Epoch 168/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2660 - accuracy: 0.9318 - val_loss: 0.2628 - val_accuracy: 0.9330
Epoch 169/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2654 - accuracy: 0.9319 - val_loss: 0.2622 - val_accuracy: 0.9330
Epoch 170/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2648 - accuracy: 0.9319 - val_loss: 0.2615 - val_accuracy: 0.9332
Epoch 171/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2642 - accuracy: 0.9321 - val_loss: 0.2609 - val_accuracy: 0.9332
Epoch 172/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2636 - accuracy: 0.9322 - val_loss: 0.2603 - val_accuracy: 0.9332
Epoch 173/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2630 - accuracy: 0.9322 - val_loss: 0.2597 - val_accuracy: 0.9332
Epoch 174/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2625 - accuracy: 0.9323 - val_loss: 0.2591 - val_accuracy: 0.9330
Epoch 175/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2619 - accuracy: 0.9323 - val_loss: 0.2586 - val_accuracy: 0.9332
Epoch 176/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.2613 - accuracy: 0.9323 - val_loss: 0.2580 - val_accuracy: 0.9335
Epoch 177/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.2608 - accuracy: 0.9324 - val_loss: 0.2574 - val_accuracy: 0.9335
Epoch 178/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2602 - accuracy: 0.9324 - val_loss: 0.2568 - val_accuracy: 0.9337
Epoch 179/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2597 - accuracy: 0.9325 - val_loss: 0.2563 - val_accuracy: 0.9339
Epoch 180/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2591 - accuracy: 0.9325 - val_loss: 0.2557 - val_accuracy: 0.9339
Epoch 181/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2586 - accuracy: 0.9325 - val_loss: 0.2551 - val_accuracy: 0.9339
Epoch 182/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2580 - accuracy: 0.9325 - val_loss: 0.2546 - val_accuracy: 0.9339
Epoch 183/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2575 - accuracy: 0.9326 - val_loss: 0.2540 - val_accuracy: 0.9339
Epoch 184/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2570 - accuracy: 0.9326 - val_loss: 0.2535 - val_accuracy: 0.9342
Epoch 185/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2565 - accuracy: 0.9326 - val_loss: 0.2530 - val_accuracy: 0.9344
Epoch 186/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2559 - accuracy: 0.9328 - val_loss: 0.2524 - val_accuracy: 0.9344
Epoch 187/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2554 - accuracy: 0.9329 - val_loss: 0.2519 - val_accuracy: 0.9351
Epoch 188/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2549 - accuracy: 0.9329 - val_loss: 0.2514 - val_accuracy: 0.9351
Epoch 189/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2544 - accuracy: 0.9329 - val_loss: 0.2508 - val_accuracy: 0.9351
Epoch 190/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2539 - accuracy: 0.9330 - val_loss: 0.2503 - val_accuracy: 0.9351
Epoch 191/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2534 - accuracy: 0.9332 - val_loss: 0.2498 - val_accuracy: 0.9351
Epoch 192/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2529 - accuracy: 0.9332 - val_loss: 0.2493 - val_accuracy: 0.9351
Epoch 193/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2525 - accuracy: 0.9334 - val_loss: 0.2488 - val_accuracy: 0.9351
Epoch 194/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2520 - accuracy: 0.9335 - val_loss: 0.2483 - val_accuracy: 0.9351
Epoch 195/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2515 - accuracy: 0.9335 - val_loss: 0.2478 - val_accuracy: 0.9354
Epoch 196/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2510 - accuracy: 0.9335 - val_loss: 0.2473 - val_accuracy: 0.9356
Epoch 197/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2506 - accuracy: 0.9335 - val_loss: 0.2469 - val_accuracy: 0.9356
Epoch 198/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2501 - accuracy: 0.9335 - val_loss: 0.2464 - val_accuracy: 0.9356
Epoch 199/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2496 - accuracy: 0.9335 - val_loss: 0.2459 - val_accuracy: 0.9356
Epoch 200/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2492 - accuracy: 0.9336 - val_loss: 0.2454 - val_accuracy: 0.9356
Epoch 201/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2487 - accuracy: 0.9337 - val_loss: 0.2450 - val_accuracy: 0.9356
Epoch 202/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2483 - accuracy: 0.9337 - val_loss: 0.2445 - val_accuracy: 0.9356
Epoch 203/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2478 - accuracy: 0.9337 - val_loss: 0.2441 - val_accuracy: 0.9356
Epoch 204/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2474 - accuracy: 0.9337 - val_loss: 0.2436 - val_accuracy: 0.9359
Epoch 205/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2470 - accuracy: 0.9339 - val_loss: 0.2431 - val_accuracy: 0.9361
Epoch 206/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.2465 - accuracy: 0.9341 - val_loss: 0.2427 - val_accuracy: 0.9361
Epoch 207/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.2461 - accuracy: 0.9341 - val_loss: 0.2423 - val_accuracy: 0.9361
Epoch 208/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2457 - accuracy: 0.9343 - val_loss: 0.2418 - val_accuracy: 0.9361
Epoch 209/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2453 - accuracy: 0.9345 - val_loss: 0.2414 - val_accuracy: 0.9361
Epoch 210/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2449 - accuracy: 0.9347 - val_loss: 0.2409 - val_accuracy: 0.9361
Epoch 211/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2444 - accuracy: 0.9348 - val_loss: 0.2405 - val_accuracy: 0.9361
Epoch 212/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2440 - accuracy: 0.9350 - val_loss: 0.2401 - val_accuracy: 0.9364
Epoch 213/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2436 - accuracy: 0.9350 - val_loss: 0.2397 - val_accuracy: 0.9364
Epoch 214/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2432 - accuracy: 0.9351 - val_loss: 0.2393 - val_accuracy: 0.9364
Epoch 215/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2428 - accuracy: 0.9351 - val_loss: 0.2388 - val_accuracy: 0.9366
Epoch 216/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2424 - accuracy: 0.9353 - val_loss: 0.2384 - val_accuracy: 0.9371
Epoch 217/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.2420 - accuracy: 0.9354 - val_loss: 0.2380 - val_accuracy: 0.9373
Epoch 218/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2417 - accuracy: 0.9355 - val_loss: 0.2376 - val_accuracy: 0.9373
Epoch 219/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2413 - accuracy: 0.9355 - val_loss: 0.2372 - val_accuracy: 0.9373
Epoch 220/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2409 - accuracy: 0.9355 - val_loss: 0.2368 - val_accuracy: 0.9376
Epoch 221/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2405 - accuracy: 0.9356 - val_loss: 0.2364 - val_accuracy: 0.9376
Epoch 222/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2401 - accuracy: 0.9356 - val_loss: 0.2360 - val_accuracy: 0.9380
Epoch 223/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2397 - accuracy: 0.9358 - val_loss: 0.2356 - val_accuracy: 0.9380
Epoch 224/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2394 - accuracy: 0.9359 - val_loss: 0.2352 - val_accuracy: 0.9380
Epoch 225/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2390 - accuracy: 0.9359 - val_loss: 0.2349 - val_accuracy: 0.9380
Epoch 226/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2386 - accuracy: 0.9359 - val_loss: 0.2345 - val_accuracy: 0.9380
Epoch 227/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2383 - accuracy: 0.9359 - val_loss: 0.2341 - val_accuracy: 0.9385
Epoch 228/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2379 - accuracy: 0.9360 - val_loss: 0.2337 - val_accuracy: 0.9388
Epoch 229/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2376 - accuracy: 0.9360 - val_loss: 0.2333 - val_accuracy: 0.9388
Epoch 230/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2372 - accuracy: 0.9363 - val_loss: 0.2330 - val_accuracy: 0.9388
Epoch 231/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2369 - accuracy: 0.9363 - val_loss: 0.2326 - val_accuracy: 0.9388
Epoch 232/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2365 - accuracy: 0.9363 - val_loss: 0.2322 - val_accuracy: 0.9388
Epoch 233/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2362 - accuracy: 0.9363 - val_loss: 0.2319 - val_accuracy: 0.9388
Epoch 234/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2358 - accuracy: 0.9363 - val_loss: 0.2315 - val_accuracy: 0.9388
Epoch 235/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2355 - accuracy: 0.9364 - val_loss: 0.2312 - val_accuracy: 0.9390
Epoch 236/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2351 - accuracy: 0.9367 - val_loss: 0.2308 - val_accuracy: 0.9392
Epoch 237/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2348 - accuracy: 0.9367 - val_loss: 0.2305 - val_accuracy: 0.9392
Epoch 238/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2345 - accuracy: 0.9367 - val_loss: 0.2301 - val_accuracy: 0.9392
Epoch 239/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2342 - accuracy: 0.9367 - val_loss: 0.2298 - val_accuracy: 0.9395
Epoch 240/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2338 - accuracy: 0.9368 - val_loss: 0.2294 - val_accuracy: 0.9395
Epoch 241/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2335 - accuracy: 0.9370 - val_loss: 0.2291 - val_accuracy: 0.9397
Epoch 242/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2332 - accuracy: 0.9371 - val_loss: 0.2288 - val_accuracy: 0.9397
Epoch 243/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2329 - accuracy: 0.9371 - val_loss: 0.2284 - val_accuracy: 0.9397
Epoch 244/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2326 - accuracy: 0.9371 - val_loss: 0.2281 - val_accuracy: 0.9397
Epoch 245/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2322 - accuracy: 0.9371 - val_loss: 0.2278 - val_accuracy: 0.9397
Epoch 246/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2319 - accuracy: 0.9373 - val_loss: 0.2274 - val_accuracy: 0.9397
Epoch 247/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2316 - accuracy: 0.9374 - val_loss: 0.2271 - val_accuracy: 0.9397
Epoch 248/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2313 - accuracy: 0.9375 - val_loss: 0.2268 - val_accuracy: 0.9397
Epoch 249/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2310 - accuracy: 0.9376 - val_loss: 0.2265 - val_accuracy: 0.9397
Epoch 250/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2307 - accuracy: 0.9376 - val_loss: 0.2262 - val_accuracy: 0.9397
Epoch 251/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2304 - accuracy: 0.9377 - val_loss: 0.2258 - val_accuracy: 0.9397
Epoch 252/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2301 - accuracy: 0.9378 - val_loss: 0.2255 - val_accuracy: 0.9397
Epoch 253/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2298 - accuracy: 0.9381 - val_loss: 0.2252 - val_accuracy: 0.9397
Epoch 254/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2295 - accuracy: 0.9382 - val_loss: 0.2249 - val_accuracy: 0.9397
Epoch 255/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2293 - accuracy: 0.9384 - val_loss: 0.2246 - val_accuracy: 0.9397
Epoch 256/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2290 - accuracy: 0.9384 - val_loss: 0.2243 - val_accuracy: 0.9397
Epoch 257/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2287 - accuracy: 0.9384 - val_loss: 0.2240 - val_accuracy: 0.9397
Epoch 258/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2284 - accuracy: 0.9384 - val_loss: 0.2237 - val_accuracy: 0.9397
Epoch 259/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2281 - accuracy: 0.9384 - val_loss: 0.2234 - val_accuracy: 0.9397
Epoch 260/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2278 - accuracy: 0.9384 - val_loss: 0.2231 - val_accuracy: 0.9397
Epoch 261/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2276 - accuracy: 0.9384 - val_loss: 0.2228 - val_accuracy: 0.9397
Epoch 262/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2273 - accuracy: 0.9385 - val_loss: 0.2225 - val_accuracy: 0.9397
Epoch 263/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2270 - accuracy: 0.9386 - val_loss: 0.2223 - val_accuracy: 0.9397
Epoch 264/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2268 - accuracy: 0.9386 - val_loss: 0.2220 - val_accuracy: 0.9397
Epoch 265/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2265 - accuracy: 0.9386 - val_loss: 0.2217 - val_accuracy: 0.9400
Epoch 266/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2262 - accuracy: 0.9388 - val_loss: 0.2214 - val_accuracy: 0.9400
Epoch 267/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2260 - accuracy: 0.9389 - val_loss: 0.2211 - val_accuracy: 0.9400
Epoch 268/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2257 - accuracy: 0.9389 - val_loss: 0.2209 - val_accuracy: 0.9400
Epoch 269/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2254 - accuracy: 0.9389 - val_loss: 0.2206 - val_accuracy: 0.9400
Epoch 270/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2252 - accuracy: 0.9389 - val_loss: 0.2203 - val_accuracy: 0.9400
Epoch 271/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2249 - accuracy: 0.9389 - val_loss: 0.2200 - val_accuracy: 0.9400
Epoch 272/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2247 - accuracy: 0.9389 - val_loss: 0.2198 - val_accuracy: 0.9400
Epoch 273/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2244 - accuracy: 0.9390 - val_loss: 0.2195 - val_accuracy: 0.9400
Epoch 274/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2242 - accuracy: 0.9391 - val_loss: 0.2192 - val_accuracy: 0.9400
Epoch 275/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2239 - accuracy: 0.9391 - val_loss: 0.2189 - val_accuracy: 0.9400
Epoch 276/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.2237 - accuracy: 0.9393 - val_loss: 0.2187 - val_accuracy: 0.9400
Epoch 277/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.2234 - accuracy: 0.9394 - val_loss: 0.2184 - val_accuracy: 0.9405
Epoch 278/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2232 - accuracy: 0.9394 - val_loss: 0.2182 - val_accuracy: 0.9407
Epoch 279/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2230 - accuracy: 0.9396 - val_loss: 0.2179 - val_accuracy: 0.9409
Epoch 280/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2227 - accuracy: 0.9396 - val_loss: 0.2177 - val_accuracy: 0.9412
Epoch 281/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2225 - accuracy: 0.9396 - val_loss: 0.2174 - val_accuracy: 0.9412
Epoch 282/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2222 - accuracy: 0.9396 - val_loss: 0.2171 - val_accuracy: 0.9412
Epoch 283/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2220 - accuracy: 0.9396 - val_loss: 0.2169 - val_accuracy: 0.9412
Epoch 284/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2218 - accuracy: 0.9396 - val_loss: 0.2166 - val_accuracy: 0.9414
Epoch 285/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2215 - accuracy: 0.9397 - val_loss: 0.2164 - val_accuracy: 0.9414
Epoch 286/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2213 - accuracy: 0.9400 - val_loss: 0.2162 - val_accuracy: 0.9417
Epoch 287/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2211 - accuracy: 0.9402 - val_loss: 0.2159 - val_accuracy: 0.9419
Epoch 288/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2209 - accuracy: 0.9402 - val_loss: 0.2157 - val_accuracy: 0.9419
Epoch 289/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2207 - accuracy: 0.9403 - val_loss: 0.2154 - val_accuracy: 0.9419
Epoch 290/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2204 - accuracy: 0.9403 - val_loss: 0.2152 - val_accuracy: 0.9419
Epoch 291/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2202 - accuracy: 0.9404 - val_loss: 0.2150 - val_accuracy: 0.9419
Epoch 292/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2200 - accuracy: 0.9404 - val_loss: 0.2147 - val_accuracy: 0.9419
Epoch 293/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2198 - accuracy: 0.9405 - val_loss: 0.2145 - val_accuracy: 0.9419
Epoch 294/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2195 - accuracy: 0.9406 - val_loss: 0.2143 - val_accuracy: 0.9419
Epoch 295/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2193 - accuracy: 0.9408 - val_loss: 0.2140 - val_accuracy: 0.9419
Epoch 296/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2191 - accuracy: 0.9408 - val_loss: 0.2138 - val_accuracy: 0.9424
Epoch 297/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2189 - accuracy: 0.9408 - val_loss: 0.2136 - val_accuracy: 0.9424
Epoch 298/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2187 - accuracy: 0.9408 - val_loss: 0.2134 - val_accuracy: 0.9424
Epoch 299/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2185 - accuracy: 0.9409 - val_loss: 0.2131 - val_accuracy: 0.9424
Epoch 300/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2183 - accuracy: 0.9410 - val_loss: 0.2129 - val_accuracy: 0.9424
Epoch 301/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2181 - accuracy: 0.9410 - val_loss: 0.2127 - val_accuracy: 0.9426
Epoch 302/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2179 - accuracy: 0.9411 - val_loss: 0.2125 - val_accuracy: 0.9429
Epoch 303/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2177 - accuracy: 0.9411 - val_loss: 0.2123 - val_accuracy: 0.9429
Epoch 304/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2175 - accuracy: 0.9411 - val_loss: 0.2120 - val_accuracy: 0.9429
Epoch 305/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2173 - accuracy: 0.9412 - val_loss: 0.2118 - val_accuracy: 0.9429
Epoch 306/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2171 - accuracy: 0.9412 - val_loss: 0.2116 - val_accuracy: 0.9429
Epoch 307/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2169 - accuracy: 0.9412 - val_loss: 0.2114 - val_accuracy: 0.9429
Epoch 308/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2167 - accuracy: 0.9412 - val_loss: 0.2112 - val_accuracy: 0.9429
Epoch 309/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2165 - accuracy: 0.9416 - val_loss: 0.2110 - val_accuracy: 0.9429
Epoch 310/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2163 - accuracy: 0.9416 - val_loss: 0.2108 - val_accuracy: 0.9429
Epoch 311/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2161 - accuracy: 0.9416 - val_loss: 0.2105 - val_accuracy: 0.9429
Epoch 312/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2159 - accuracy: 0.9416 - val_loss: 0.2103 - val_accuracy: 0.9431
Epoch 313/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2157 - accuracy: 0.9416 - val_loss: 0.2101 - val_accuracy: 0.9431
Epoch 314/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2156 - accuracy: 0.9416 - val_loss: 0.2099 - val_accuracy: 0.9431
Epoch 315/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2154 - accuracy: 0.9416 - val_loss: 0.2098 - val_accuracy: 0.9431
Epoch 316/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2152 - accuracy: 0.9420 - val_loss: 0.2096 - val_accuracy: 0.9433
Epoch 317/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2150 - accuracy: 0.9420 - val_loss: 0.2094 - val_accuracy: 0.9436
Epoch 318/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2149 - accuracy: 0.9420 - val_loss: 0.2092 - val_accuracy: 0.9436
Epoch 319/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2147 - accuracy: 0.9420 - val_loss: 0.2090 - val_accuracy: 0.9436
Epoch 320/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2145 - accuracy: 0.9420 - val_loss: 0.2088 - val_accuracy: 0.9436
Epoch 321/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2143 - accuracy: 0.9421 - val_loss: 0.2086 - val_accuracy: 0.9436
Epoch 322/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2141 - accuracy: 0.9421 - val_loss: 0.2084 - val_accuracy: 0.9436
Epoch 323/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2140 - accuracy: 0.9421 - val_loss: 0.2082 - val_accuracy: 0.9436
Epoch 324/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2138 - accuracy: 0.9422 - val_loss: 0.2080 - val_accuracy: 0.9436
Epoch 325/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2136 - accuracy: 0.9422 - val_loss: 0.2078 - val_accuracy: 0.9436
Epoch 326/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2135 - accuracy: 0.9423 - val_loss: 0.2076 - val_accuracy: 0.9436
Epoch 327/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2133 - accuracy: 0.9423 - val_loss: 0.2075 - val_accuracy: 0.9438
Epoch 328/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2131 - accuracy: 0.9424 - val_loss: 0.2073 - val_accuracy: 0.9438
Epoch 329/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2130 - accuracy: 0.9425 - val_loss: 0.2071 - val_accuracy: 0.9438
Epoch 330/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2128 - accuracy: 0.9425 - val_loss: 0.2069 - val_accuracy: 0.9438
Epoch 331/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2126 - accuracy: 0.9425 - val_loss: 0.2067 - val_accuracy: 0.9438
Epoch 332/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2125 - accuracy: 0.9425 - val_loss: 0.2066 - val_accuracy: 0.9438
Epoch 333/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2123 - accuracy: 0.9425 - val_loss: 0.2064 - val_accuracy: 0.9438
Epoch 334/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2122 - accuracy: 0.9425 - val_loss: 0.2062 - val_accuracy: 0.9438
Epoch 335/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2120 - accuracy: 0.9426 - val_loss: 0.2060 - val_accuracy: 0.9441
Epoch 336/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2118 - accuracy: 0.9428 - val_loss: 0.2059 - val_accuracy: 0.9443
Epoch 337/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2117 - accuracy: 0.9429 - val_loss: 0.2057 - val_accuracy: 0.9446
Epoch 338/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2115 - accuracy: 0.9429 - val_loss: 0.2055 - val_accuracy: 0.9446
Epoch 339/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2114 - accuracy: 0.9429 - val_loss: 0.2053 - val_accuracy: 0.9446
Epoch 340/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2112 - accuracy: 0.9430 - val_loss: 0.2052 - val_accuracy: 0.9446
Epoch 341/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.2111 - accuracy: 0.9430 - val_loss: 0.2050 - val_accuracy: 0.9446
Epoch 342/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2109 - accuracy: 0.9432 - val_loss: 0.2048 - val_accuracy: 0.9446
Epoch 343/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2108 - accuracy: 0.9433 - val_loss: 0.2047 - val_accuracy: 0.9446
Epoch 344/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2106 - accuracy: 0.9433 - val_loss: 0.2045 - val_accuracy: 0.9446
Epoch 345/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2105 - accuracy: 0.9433 - val_loss: 0.2043 - val_accuracy: 0.9446
Epoch 346/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2103 - accuracy: 0.9435 - val_loss: 0.2042 - val_accuracy: 0.9448
Epoch 347/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2102 - accuracy: 0.9435 - val_loss: 0.2040 - val_accuracy: 0.9448
Epoch 348/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2100 - accuracy: 0.9437 - val_loss: 0.2039 - val_accuracy: 0.9448
Epoch 349/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2099 - accuracy: 0.9437 - val_loss: 0.2037 - val_accuracy: 0.9448
Epoch 350/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2098 - accuracy: 0.9437 - val_loss: 0.2035 - val_accuracy: 0.9450
Epoch 351/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2096 - accuracy: 0.9436 - val_loss: 0.2034 - val_accuracy: 0.9450
Epoch 352/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2095 - accuracy: 0.9436 - val_loss: 0.2032 - val_accuracy: 0.9450
Epoch 353/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2093 - accuracy: 0.9437 - val_loss: 0.2031 - val_accuracy: 0.9450
Epoch 354/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2092 - accuracy: 0.9437 - val_loss: 0.2029 - val_accuracy: 0.9450
Epoch 355/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2091 - accuracy: 0.9437 - val_loss: 0.2028 - val_accuracy: 0.9455
Epoch 356/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2089 - accuracy: 0.9439 - val_loss: 0.2026 - val_accuracy: 0.9455
Epoch 357/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2088 - accuracy: 0.9440 - val_loss: 0.2025 - val_accuracy: 0.9455
Epoch 358/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2087 - accuracy: 0.9440 - val_loss: 0.2023 - val_accuracy: 0.9455
Epoch 359/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2085 - accuracy: 0.9440 - val_loss: 0.2022 - val_accuracy: 0.9455
Epoch 360/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2084 - accuracy: 0.9440 - val_loss: 0.2020 - val_accuracy: 0.9455
Epoch 361/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2083 - accuracy: 0.9441 - val_loss: 0.2019 - val_accuracy: 0.9455
Epoch 362/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2081 - accuracy: 0.9442 - val_loss: 0.2017 - val_accuracy: 0.9455
Epoch 363/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2080 - accuracy: 0.9442 - val_loss: 0.2016 - val_accuracy: 0.9455
Epoch 364/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2079 - accuracy: 0.9442 - val_loss: 0.2015 - val_accuracy: 0.9455
Epoch 365/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2078 - accuracy: 0.9444 - val_loss: 0.2013 - val_accuracy: 0.9455
Epoch 366/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2076 - accuracy: 0.9444 - val_loss: 0.2012 - val_accuracy: 0.9455
Epoch 367/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2075 - accuracy: 0.9444 - val_loss: 0.2010 - val_accuracy: 0.9455
Epoch 368/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2074 - accuracy: 0.9445 - val_loss: 0.2009 - val_accuracy: 0.9455
Epoch 369/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2073 - accuracy: 0.9445 - val_loss: 0.2007 - val_accuracy: 0.9455
Epoch 370/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2071 - accuracy: 0.9445 - val_loss: 0.2006 - val_accuracy: 0.9460
Epoch 371/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2070 - accuracy: 0.9445 - val_loss: 0.2005 - val_accuracy: 0.9460
Epoch 372/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2069 - accuracy: 0.9445 - val_loss: 0.2003 - val_accuracy: 0.9460
Epoch 373/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2068 - accuracy: 0.9445 - val_loss: 0.2002 - val_accuracy: 0.9460
Epoch 374/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2067 - accuracy: 0.9445 - val_loss: 0.2001 - val_accuracy: 0.9460
Epoch 375/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2065 - accuracy: 0.9445 - val_loss: 0.1999 - val_accuracy: 0.9460
Epoch 376/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.2064 - accuracy: 0.9445 - val_loss: 0.1998 - val_accuracy: 0.9460
Epoch 377/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2063 - accuracy: 0.9447 - val_loss: 0.1997 - val_accuracy: 0.9462
Epoch 378/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2062 - accuracy: 0.9448 - val_loss: 0.1996 - val_accuracy: 0.9465
Epoch 379/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2061 - accuracy: 0.9448 - val_loss: 0.1994 - val_accuracy: 0.9465
Epoch 380/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2060 - accuracy: 0.9448 - val_loss: 0.1993 - val_accuracy: 0.9465
Epoch 381/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2059 - accuracy: 0.9449 - val_loss: 0.1992 - val_accuracy: 0.9465
Epoch 382/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2058 - accuracy: 0.9449 - val_loss: 0.1990 - val_accuracy: 0.9465
Epoch 383/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2056 - accuracy: 0.9449 - val_loss: 0.1989 - val_accuracy: 0.9465
Epoch 384/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2055 - accuracy: 0.9449 - val_loss: 0.1988 - val_accuracy: 0.9465
Epoch 385/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.2054 - accuracy: 0.9449 - val_loss: 0.1987 - val_accuracy: 0.9465
Epoch 386/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2053 - accuracy: 0.9449 - val_loss: 0.1986 - val_accuracy: 0.9465
Epoch 387/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2052 - accuracy: 0.9449 - val_loss: 0.1984 - val_accuracy: 0.9465
Epoch 388/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2051 - accuracy: 0.9449 - val_loss: 0.1983 - val_accuracy: 0.9465
Epoch 389/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2050 - accuracy: 0.9449 - val_loss: 0.1982 - val_accuracy: 0.9465
Epoch 390/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2049 - accuracy: 0.9449 - val_loss: 0.1981 - val_accuracy: 0.9465
Epoch 391/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2048 - accuracy: 0.9449 - val_loss: 0.1979 - val_accuracy: 0.9467
Epoch 392/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2047 - accuracy: 0.9449 - val_loss: 0.1978 - val_accuracy: 0.9470
Epoch 393/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2046 - accuracy: 0.9449 - val_loss: 0.1977 - val_accuracy: 0.9470
Epoch 394/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2045 - accuracy: 0.9449 - val_loss: 0.1976 - val_accuracy: 0.9470
Epoch 395/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2044 - accuracy: 0.9450 - val_loss: 0.1975 - val_accuracy: 0.9470
Epoch 396/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2043 - accuracy: 0.9450 - val_loss: 0.1974 - val_accuracy: 0.9470
Epoch 397/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2042 - accuracy: 0.9450 - val_loss: 0.1972 - val_accuracy: 0.9470
Epoch 398/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2041 - accuracy: 0.9450 - val_loss: 0.1971 - val_accuracy: 0.9470
Epoch 399/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2040 - accuracy: 0.9450 - val_loss: 0.1970 - val_accuracy: 0.9470
Epoch 400/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2039 - accuracy: 0.9450 - val_loss: 0.1969 - val_accuracy: 0.9472
Epoch 401/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2038 - accuracy: 0.9450 - val_loss: 0.1968 - val_accuracy: 0.9474
Epoch 402/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2037 - accuracy: 0.9450 - val_loss: 0.1967 - val_accuracy: 0.9474
Epoch 403/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2036 - accuracy: 0.9450 - val_loss: 0.1966 - val_accuracy: 0.9474
Epoch 404/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2035 - accuracy: 0.9450 - val_loss: 0.1965 - val_accuracy: 0.9474
Epoch 405/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2034 - accuracy: 0.9450 - val_loss: 0.1964 - val_accuracy: 0.9479
Epoch 406/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2034 - accuracy: 0.9450 - val_loss: 0.1963 - val_accuracy: 0.9479
Epoch 407/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2033 - accuracy: 0.9450 - val_loss: 0.1962 - val_accuracy: 0.9482
Epoch 408/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2032 - accuracy: 0.9450 - val_loss: 0.1961 - val_accuracy: 0.9482
Epoch 409/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2031 - accuracy: 0.9451 - val_loss: 0.1960 - val_accuracy: 0.9482
Epoch 410/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2030 - accuracy: 0.9451 - val_loss: 0.1959 - val_accuracy: 0.9482
Epoch 411/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2029 - accuracy: 0.9451 - val_loss: 0.1958 - val_accuracy: 0.9482
Epoch 412/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2028 - accuracy: 0.9451 - val_loss: 0.1957 - val_accuracy: 0.9482
Epoch 413/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2027 - accuracy: 0.9451 - val_loss: 0.1956 - val_accuracy: 0.9482
Epoch 414/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2027 - accuracy: 0.9452 - val_loss: 0.1955 - val_accuracy: 0.9482
Epoch 415/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2026 - accuracy: 0.9453 - val_loss: 0.1954 - val_accuracy: 0.9482
Epoch 416/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2025 - accuracy: 0.9453 - val_loss: 0.1953 - val_accuracy: 0.9482
Epoch 417/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2024 - accuracy: 0.9454 - val_loss: 0.1952 - val_accuracy: 0.9482
Epoch 418/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2023 - accuracy: 0.9454 - val_loss: 0.1951 - val_accuracy: 0.9482
Epoch 419/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2022 - accuracy: 0.9454 - val_loss: 0.1950 - val_accuracy: 0.9482
Epoch 420/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2022 - accuracy: 0.9454 - val_loss: 0.1949 - val_accuracy: 0.9482
Epoch 421/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2021 - accuracy: 0.9456 - val_loss: 0.1948 - val_accuracy: 0.9482
Epoch 422/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2020 - accuracy: 0.9456 - val_loss: 0.1947 - val_accuracy: 0.9482
Epoch 423/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2019 - accuracy: 0.9456 - val_loss: 0.1946 - val_accuracy: 0.9482
Epoch 424/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2018 - accuracy: 0.9457 - val_loss: 0.1945 - val_accuracy: 0.9484
Epoch 425/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2018 - accuracy: 0.9457 - val_loss: 0.1944 - val_accuracy: 0.9484
Epoch 426/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2017 - accuracy: 0.9457 - val_loss: 0.1943 - val_accuracy: 0.9484
Epoch 427/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2016 - accuracy: 0.9457 - val_loss: 0.1942 - val_accuracy: 0.9484
Epoch 428/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2015 - accuracy: 0.9457 - val_loss: 0.1941 - val_accuracy: 0.9489
Epoch 429/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2015 - accuracy: 0.9458 - val_loss: 0.1940 - val_accuracy: 0.9489
Epoch 430/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2014 - accuracy: 0.9459 - val_loss: 0.1940 - val_accuracy: 0.9491
Epoch 431/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2013 - accuracy: 0.9459 - val_loss: 0.1939 - val_accuracy: 0.9491
Epoch 432/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2012 - accuracy: 0.9459 - val_loss: 0.1938 - val_accuracy: 0.9491
Epoch 433/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2012 - accuracy: 0.9460 - val_loss: 0.1937 - val_accuracy: 0.9491
Epoch 434/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2011 - accuracy: 0.9460 - val_loss: 0.1936 - val_accuracy: 0.9491
Epoch 435/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2010 - accuracy: 0.9460 - val_loss: 0.1935 - val_accuracy: 0.9491
Epoch 436/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2010 - accuracy: 0.9461 - val_loss: 0.1935 - val_accuracy: 0.9491
Epoch 437/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2009 - accuracy: 0.9462 - val_loss: 0.1934 - val_accuracy: 0.9491
Epoch 438/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2008 - accuracy: 0.9462 - val_loss: 0.1933 - val_accuracy: 0.9491
Epoch 439/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2008 - accuracy: 0.9462 - val_loss: 0.1932 - val_accuracy: 0.9491
Epoch 440/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2007 - accuracy: 0.9462 - val_loss: 0.1931 - val_accuracy: 0.9491
Epoch 441/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2006 - accuracy: 0.9462 - val_loss: 0.1930 - val_accuracy: 0.9491
Epoch 442/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2005 - accuracy: 0.9462 - val_loss: 0.1929 - val_accuracy: 0.9491
Epoch 443/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2005 - accuracy: 0.9462 - val_loss: 0.1929 - val_accuracy: 0.9491
Epoch 444/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2004 - accuracy: 0.9462 - val_loss: 0.1928 - val_accuracy: 0.9491
Epoch 445/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2003 - accuracy: 0.9462 - val_loss: 0.1927 - val_accuracy: 0.9491
Epoch 446/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2003 - accuracy: 0.9462 - val_loss: 0.1926 - val_accuracy: 0.9491
Epoch 447/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2002 - accuracy: 0.9462 - val_loss: 0.1925 - val_accuracy: 0.9491
Epoch 448/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2001 - accuracy: 0.9462 - val_loss: 0.1924 - val_accuracy: 0.9491
Epoch 449/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2001 - accuracy: 0.9463 - val_loss: 0.1924 - val_accuracy: 0.9491
Epoch 450/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.2000 - accuracy: 0.9463 - val_loss: 0.1923 - val_accuracy: 0.9491
Epoch 451/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1999 - accuracy: 0.9463 - val_loss: 0.1922 - val_accuracy: 0.9491
Epoch 452/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1999 - accuracy: 0.9463 - val_loss: 0.1921 - val_accuracy: 0.9491
Epoch 453/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1998 - accuracy: 0.9466 - val_loss: 0.1921 - val_accuracy: 0.9494
Epoch 454/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1998 - accuracy: 0.9466 - val_loss: 0.1920 - val_accuracy: 0.9494
Epoch 455/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1997 - accuracy: 0.9466 - val_loss: 0.1919 - val_accuracy: 0.9494
Epoch 456/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1996 - accuracy: 0.9466 - val_loss: 0.1918 - val_accuracy: 0.9494
Epoch 457/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1996 - accuracy: 0.9466 - val_loss: 0.1918 - val_accuracy: 0.9494
Epoch 458/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1995 - accuracy: 0.9466 - val_loss: 0.1917 - val_accuracy: 0.9494
Epoch 459/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1995 - accuracy: 0.9466 - val_loss: 0.1916 - val_accuracy: 0.9494
Epoch 460/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1994 - accuracy: 0.9466 - val_loss: 0.1915 - val_accuracy: 0.9494
Epoch 461/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1993 - accuracy: 0.9466 - val_loss: 0.1915 - val_accuracy: 0.9494
Epoch 462/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1993 - accuracy: 0.9466 - val_loss: 0.1914 - val_accuracy: 0.9494
Epoch 463/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1992 - accuracy: 0.9467 - val_loss: 0.1913 - val_accuracy: 0.9494
Epoch 464/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1992 - accuracy: 0.9468 - val_loss: 0.1913 - val_accuracy: 0.9494
Epoch 465/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1991 - accuracy: 0.9468 - val_loss: 0.1912 - val_accuracy: 0.9494
Epoch 466/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1991 - accuracy: 0.9468 - val_loss: 0.1911 - val_accuracy: 0.9494
Epoch 467/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1990 - accuracy: 0.9468 - val_loss: 0.1910 - val_accuracy: 0.9494
Epoch 468/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1989 - accuracy: 0.9468 - val_loss: 0.1910 - val_accuracy: 0.9494
Epoch 469/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1989 - accuracy: 0.9468 - val_loss: 0.1909 - val_accuracy: 0.9494
Epoch 470/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1988 - accuracy: 0.9469 - val_loss: 0.1908 - val_accuracy: 0.9496
Epoch 471/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1988 - accuracy: 0.9469 - val_loss: 0.1908 - val_accuracy: 0.9496
Epoch 472/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1987 - accuracy: 0.9470 - val_loss: 0.1907 - val_accuracy: 0.9496
Epoch 473/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1987 - accuracy: 0.9470 - val_loss: 0.1906 - val_accuracy: 0.9496
Epoch 474/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1986 - accuracy: 0.9471 - val_loss: 0.1906 - val_accuracy: 0.9496
Epoch 475/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1986 - accuracy: 0.9471 - val_loss: 0.1905 - val_accuracy: 0.9496
Epoch 476/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1985 - accuracy: 0.9471 - val_loss: 0.1904 - val_accuracy: 0.9496
Epoch 477/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1985 - accuracy: 0.9471 - val_loss: 0.1904 - val_accuracy: 0.9496
Epoch 478/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1984 - accuracy: 0.9471 - val_loss: 0.1903 - val_accuracy: 0.9496
Epoch 479/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1984 - accuracy: 0.9471 - val_loss: 0.1902 - val_accuracy: 0.9496
Epoch 480/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1983 - accuracy: 0.9471 - val_loss: 0.1902 - val_accuracy: 0.9496
Epoch 481/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1983 - accuracy: 0.9472 - val_loss: 0.1901 - val_accuracy: 0.9496
Epoch 482/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1982 - accuracy: 0.9472 - val_loss: 0.1901 - val_accuracy: 0.9496
Epoch 483/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1982 - accuracy: 0.9472 - val_loss: 0.1900 - val_accuracy: 0.9496
Epoch 484/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1981 - accuracy: 0.9472 - val_loss: 0.1899 - val_accuracy: 0.9496
Epoch 485/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1981 - accuracy: 0.9472 - val_loss: 0.1899 - val_accuracy: 0.9496
Epoch 486/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1980 - accuracy: 0.9472 - val_loss: 0.1898 - val_accuracy: 0.9496
Epoch 487/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1980 - accuracy: 0.9472 - val_loss: 0.1898 - val_accuracy: 0.9496
Epoch 488/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1979 - accuracy: 0.9472 - val_loss: 0.1897 - val_accuracy: 0.9496
Epoch 489/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1979 - accuracy: 0.9472 - val_loss: 0.1896 - val_accuracy: 0.9496
Epoch 490/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1979 - accuracy: 0.9473 - val_loss: 0.1896 - val_accuracy: 0.9496
Epoch 491/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1978 - accuracy: 0.9473 - val_loss: 0.1895 - val_accuracy: 0.9496
Epoch 492/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1978 - accuracy: 0.9473 - val_loss: 0.1895 - val_accuracy: 0.9496
Epoch 493/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1977 - accuracy: 0.9473 - val_loss: 0.1894 - val_accuracy: 0.9496
Epoch 494/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1977 - accuracy: 0.9473 - val_loss: 0.1893 - val_accuracy: 0.9496
Epoch 495/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1976 - accuracy: 0.9473 - val_loss: 0.1893 - val_accuracy: 0.9496
Epoch 496/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1976 - accuracy: 0.9473 - val_loss: 0.1892 - val_accuracy: 0.9496
Epoch 497/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1976 - accuracy: 0.9473 - val_loss: 0.1892 - val_accuracy: 0.9496
Epoch 498/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1975 - accuracy: 0.9473 - val_loss: 0.1891 - val_accuracy: 0.9496
Epoch 499/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1975 - accuracy: 0.9473 - val_loss: 0.1891 - val_accuracy: 0.9496
Epoch 500/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1974 - accuracy: 0.9474 - val_loss: 0.1890 - val_accuracy: 0.9496
Epoch 501/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1974 - accuracy: 0.9474 - val_loss: 0.1890 - val_accuracy: 0.9496
Epoch 502/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1973 - accuracy: 0.9474 - val_loss: 0.1889 - val_accuracy: 0.9496
Epoch 503/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1973 - accuracy: 0.9474 - val_loss: 0.1889 - val_accuracy: 0.9496
Epoch 504/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1973 - accuracy: 0.9474 - val_loss: 0.1888 - val_accuracy: 0.9496
Epoch 505/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1972 - accuracy: 0.9474 - val_loss: 0.1888 - val_accuracy: 0.9496
Epoch 506/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1972 - accuracy: 0.9475 - val_loss: 0.1887 - val_accuracy: 0.9496
Epoch 507/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1972 - accuracy: 0.9475 - val_loss: 0.1887 - val_accuracy: 0.9496
Epoch 508/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1971 - accuracy: 0.9475 - val_loss: 0.1886 - val_accuracy: 0.9496
Epoch 509/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1971 - accuracy: 0.9475 - val_loss: 0.1886 - val_accuracy: 0.9496
Epoch 510/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1971 - accuracy: 0.9475 - val_loss: 0.1885 - val_accuracy: 0.9496
Epoch 511/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1970 - accuracy: 0.9475 - val_loss: 0.1885 - val_accuracy: 0.9496
Epoch 512/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1970 - accuracy: 0.9475 - val_loss: 0.1884 - val_accuracy: 0.9496
Epoch 513/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1969 - accuracy: 0.9475 - val_loss: 0.1884 - val_accuracy: 0.9496
Epoch 514/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1969 - accuracy: 0.9475 - val_loss: 0.1883 - val_accuracy: 0.9496
Epoch 515/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1969 - accuracy: 0.9475 - val_loss: 0.1883 - val_accuracy: 0.9496
Epoch 516/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1968 - accuracy: 0.9476 - val_loss: 0.1882 - val_accuracy: 0.9496
Epoch 517/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1968 - accuracy: 0.9476 - val_loss: 0.1882 - val_accuracy: 0.9496
Epoch 518/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1968 - accuracy: 0.9476 - val_loss: 0.1881 - val_accuracy: 0.9496
Epoch 519/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1967 - accuracy: 0.9477 - val_loss: 0.1881 - val_accuracy: 0.9496
Epoch 520/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1967 - accuracy: 0.9477 - val_loss: 0.1880 - val_accuracy: 0.9496
Epoch 521/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1967 - accuracy: 0.9477 - val_loss: 0.1880 - val_accuracy: 0.9496
Epoch 522/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1966 - accuracy: 0.9478 - val_loss: 0.1879 - val_accuracy: 0.9496
Epoch 523/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1966 - accuracy: 0.9478 - val_loss: 0.1879 - val_accuracy: 0.9496
Epoch 524/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1966 - accuracy: 0.9478 - val_loss: 0.1879 - val_accuracy: 0.9496
Epoch 525/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1965 - accuracy: 0.9478 - val_loss: 0.1878 - val_accuracy: 0.9496
Epoch 526/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1965 - accuracy: 0.9478 - val_loss: 0.1878 - val_accuracy: 0.9496
Epoch 527/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1965 - accuracy: 0.9478 - val_loss: 0.1877 - val_accuracy: 0.9496
Epoch 528/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1964 - accuracy: 0.9478 - val_loss: 0.1877 - val_accuracy: 0.9496
Epoch 529/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1964 - accuracy: 0.9478 - val_loss: 0.1876 - val_accuracy: 0.9496
Epoch 530/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1964 - accuracy: 0.9478 - val_loss: 0.1876 - val_accuracy: 0.9496
Epoch 531/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1963 - accuracy: 0.9478 - val_loss: 0.1875 - val_accuracy: 0.9496
Epoch 532/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1963 - accuracy: 0.9478 - val_loss: 0.1875 - val_accuracy: 0.9496
Epoch 533/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1963 - accuracy: 0.9478 - val_loss: 0.1875 - val_accuracy: 0.9496
Epoch 534/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1963 - accuracy: 0.9478 - val_loss: 0.1874 - val_accuracy: 0.9496
Epoch 535/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1962 - accuracy: 0.9478 - val_loss: 0.1874 - val_accuracy: 0.9496
Epoch 536/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1962 - accuracy: 0.9478 - val_loss: 0.1873 - val_accuracy: 0.9496
Epoch 537/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1962 - accuracy: 0.9478 - val_loss: 0.1873 - val_accuracy: 0.9496
Epoch 538/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1961 - accuracy: 0.9478 - val_loss: 0.1873 - val_accuracy: 0.9496
Epoch 539/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1961 - accuracy: 0.9478 - val_loss: 0.1872 - val_accuracy: 0.9496
Epoch 540/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1961 - accuracy: 0.9478 - val_loss: 0.1872 - val_accuracy: 0.9496
Epoch 541/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1961 - accuracy: 0.9478 - val_loss: 0.1871 - val_accuracy: 0.9496
Epoch 542/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1960 - accuracy: 0.9478 - val_loss: 0.1871 - val_accuracy: 0.9496
Epoch 543/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1960 - accuracy: 0.9478 - val_loss: 0.1871 - val_accuracy: 0.9496
Epoch 544/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1960 - accuracy: 0.9478 - val_loss: 0.1870 - val_accuracy: 0.9496
Epoch 545/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1960 - accuracy: 0.9478 - val_loss: 0.1870 - val_accuracy: 0.9496
Epoch 546/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1959 - accuracy: 0.9478 - val_loss: 0.1870 - val_accuracy: 0.9496
Epoch 547/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1959 - accuracy: 0.9478 - val_loss: 0.1869 - val_accuracy: 0.9496
Epoch 548/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1959 - accuracy: 0.9478 - val_loss: 0.1869 - val_accuracy: 0.9496
Epoch 549/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1959 - accuracy: 0.9478 - val_loss: 0.1869 - val_accuracy: 0.9496
Epoch 550/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1958 - accuracy: 0.9478 - val_loss: 0.1868 - val_accuracy: 0.9496
Epoch 551/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1958 - accuracy: 0.9478 - val_loss: 0.1868 - val_accuracy: 0.9496
Epoch 552/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1958 - accuracy: 0.9478 - val_loss: 0.1868 - val_accuracy: 0.9496
Epoch 553/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1958 - accuracy: 0.9478 - val_loss: 0.1867 - val_accuracy: 0.9496
Epoch 554/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1957 - accuracy: 0.9478 - val_loss: 0.1867 - val_accuracy: 0.9496
Epoch 555/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1957 - accuracy: 0.9478 - val_loss: 0.1866 - val_accuracy: 0.9496
Epoch 556/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1957 - accuracy: 0.9478 - val_loss: 0.1866 - val_accuracy: 0.9496
Epoch 557/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1957 - accuracy: 0.9478 - val_loss: 0.1866 - val_accuracy: 0.9496
Epoch 558/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1957 - accuracy: 0.9478 - val_loss: 0.1865 - val_accuracy: 0.9496
Epoch 559/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1956 - accuracy: 0.9478 - val_loss: 0.1865 - val_accuracy: 0.9496
Epoch 560/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1956 - accuracy: 0.9478 - val_loss: 0.1865 - val_accuracy: 0.9496
Epoch 561/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1956 - accuracy: 0.9478 - val_loss: 0.1864 - val_accuracy: 0.9496
Epoch 562/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1956 - accuracy: 0.9478 - val_loss: 0.1864 - val_accuracy: 0.9496
Epoch 563/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1955 - accuracy: 0.9478 - val_loss: 0.1864 - val_accuracy: 0.9496
Epoch 564/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1955 - accuracy: 0.9478 - val_loss: 0.1864 - val_accuracy: 0.9496
Epoch 565/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1955 - accuracy: 0.9478 - val_loss: 0.1863 - val_accuracy: 0.9496
Epoch 566/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1955 - accuracy: 0.9478 - val_loss: 0.1863 - val_accuracy: 0.9496
Epoch 567/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1955 - accuracy: 0.9478 - val_loss: 0.1863 - val_accuracy: 0.9496
Epoch 568/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1954 - accuracy: 0.9478 - val_loss: 0.1862 - val_accuracy: 0.9496
Epoch 569/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1954 - accuracy: 0.9478 - val_loss: 0.1862 - val_accuracy: 0.9496
Epoch 570/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1954 - accuracy: 0.9478 - val_loss: 0.1862 - val_accuracy: 0.9496
Epoch 571/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1954 - accuracy: 0.9479 - val_loss: 0.1861 - val_accuracy: 0.9496
Epoch 572/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1954 - accuracy: 0.9479 - val_loss: 0.1861 - val_accuracy: 0.9496
Epoch 573/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1954 - accuracy: 0.9479 - val_loss: 0.1861 - val_accuracy: 0.9496
Epoch 574/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1953 - accuracy: 0.9479 - val_loss: 0.1860 - val_accuracy: 0.9496
Epoch 575/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1953 - accuracy: 0.9479 - val_loss: 0.1860 - val_accuracy: 0.9496
Epoch 576/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1953 - accuracy: 0.9479 - val_loss: 0.1860 - val_accuracy: 0.9496
Epoch 577/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1953 - accuracy: 0.9480 - val_loss: 0.1860 - val_accuracy: 0.9496
Epoch 578/1000
13/13 [==============================] - 0s 5ms/step - loss: 0.1953 - accuracy: 0.9481 - val_loss: 0.1859 - val_accuracy: 0.9496
Epoch 579/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1952 - accuracy: 0.9482 - val_loss: 0.1859 - val_accuracy: 0.9496
Epoch 580/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1952 - accuracy: 0.9482 - val_loss: 0.1859 - val_accuracy: 0.9496
Epoch 581/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1952 - accuracy: 0.9482 - val_loss: 0.1859 - val_accuracy: 0.9499
Epoch 582/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1952 - accuracy: 0.9482 - val_loss: 0.1858 - val_accuracy: 0.9499
Epoch 583/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1952 - accuracy: 0.9483 - val_loss: 0.1858 - val_accuracy: 0.9499
Epoch 584/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1952 - accuracy: 0.9484 - val_loss: 0.1858 - val_accuracy: 0.9501
Epoch 585/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1951 - accuracy: 0.9484 - val_loss: 0.1858 - val_accuracy: 0.9501
Epoch 586/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1951 - accuracy: 0.9484 - val_loss: 0.1857 - val_accuracy: 0.9499
Epoch 587/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1951 - accuracy: 0.9483 - val_loss: 0.1857 - val_accuracy: 0.9499
Epoch 588/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1951 - accuracy: 0.9483 - val_loss: 0.1857 - val_accuracy: 0.9501
Epoch 589/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1951 - accuracy: 0.9483 - val_loss: 0.1857 - val_accuracy: 0.9501
Epoch 590/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1951 - accuracy: 0.9484 - val_loss: 0.1856 - val_accuracy: 0.9506
Epoch 591/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1951 - accuracy: 0.9484 - val_loss: 0.1856 - val_accuracy: 0.9506
Epoch 592/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1950 - accuracy: 0.9485 - val_loss: 0.1856 - val_accuracy: 0.9506
Epoch 593/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1950 - accuracy: 0.9485 - val_loss: 0.1856 - val_accuracy: 0.9506
Epoch 594/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1950 - accuracy: 0.9485 - val_loss: 0.1856 - val_accuracy: 0.9506
Epoch 595/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1950 - accuracy: 0.9485 - val_loss: 0.1855 - val_accuracy: 0.9506
Epoch 596/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1950 - accuracy: 0.9485 - val_loss: 0.1855 - val_accuracy: 0.9506
Epoch 597/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1950 - accuracy: 0.9485 - val_loss: 0.1855 - val_accuracy: 0.9506
Epoch 598/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1950 - accuracy: 0.9485 - val_loss: 0.1855 - val_accuracy: 0.9506
Epoch 599/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1950 - accuracy: 0.9486 - val_loss: 0.1855 - val_accuracy: 0.9506
Epoch 600/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1949 - accuracy: 0.9486 - val_loss: 0.1854 - val_accuracy: 0.9506
Epoch 601/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1949 - accuracy: 0.9486 - val_loss: 0.1854 - val_accuracy: 0.9506
Epoch 602/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1949 - accuracy: 0.9486 - val_loss: 0.1854 - val_accuracy: 0.9506
Epoch 603/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1949 - accuracy: 0.9486 - val_loss: 0.1854 - val_accuracy: 0.9506
Epoch 604/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1949 - accuracy: 0.9486 - val_loss: 0.1854 - val_accuracy: 0.9506
Epoch 605/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1949 - accuracy: 0.9486 - val_loss: 0.1853 - val_accuracy: 0.9506
Epoch 606/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1949 - accuracy: 0.9486 - val_loss: 0.1853 - val_accuracy: 0.9506
Epoch 607/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1949 - accuracy: 0.9486 - val_loss: 0.1853 - val_accuracy: 0.9506
Epoch 608/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1948 - accuracy: 0.9486 - val_loss: 0.1853 - val_accuracy: 0.9506
Epoch 609/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1948 - accuracy: 0.9486 - val_loss: 0.1852 - val_accuracy: 0.9506
Epoch 610/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1948 - accuracy: 0.9486 - val_loss: 0.1852 - val_accuracy: 0.9506
Epoch 611/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1948 - accuracy: 0.9486 - val_loss: 0.1852 - val_accuracy: 0.9506
Epoch 612/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1948 - accuracy: 0.9486 - val_loss: 0.1852 - val_accuracy: 0.9506
Epoch 613/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1948 - accuracy: 0.9486 - val_loss: 0.1852 - val_accuracy: 0.9506
Epoch 614/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1948 - accuracy: 0.9486 - val_loss: 0.1851 - val_accuracy: 0.9506
Epoch 615/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1948 - accuracy: 0.9486 - val_loss: 0.1851 - val_accuracy: 0.9506
Epoch 616/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1947 - accuracy: 0.9486 - val_loss: 0.1851 - val_accuracy: 0.9506
Epoch 617/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1947 - accuracy: 0.9486 - val_loss: 0.1851 - val_accuracy: 0.9506
Epoch 618/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1947 - accuracy: 0.9486 - val_loss: 0.1850 - val_accuracy: 0.9506
Epoch 619/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1947 - accuracy: 0.9486 - val_loss: 0.1850 - val_accuracy: 0.9506
Epoch 620/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1947 - accuracy: 0.9486 - val_loss: 0.1850 - val_accuracy: 0.9506
Epoch 621/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1947 - accuracy: 0.9486 - val_loss: 0.1850 - val_accuracy: 0.9506
Epoch 622/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1947 - accuracy: 0.9486 - val_loss: 0.1850 - val_accuracy: 0.9506
Epoch 623/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1947 - accuracy: 0.9486 - val_loss: 0.1850 - val_accuracy: 0.9506
Epoch 624/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1947 - accuracy: 0.9486 - val_loss: 0.1849 - val_accuracy: 0.9506
Epoch 625/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1947 - accuracy: 0.9486 - val_loss: 0.1849 - val_accuracy: 0.9506
Epoch 626/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1946 - accuracy: 0.9486 - val_loss: 0.1849 - val_accuracy: 0.9506
Epoch 627/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1946 - accuracy: 0.9486 - val_loss: 0.1849 - val_accuracy: 0.9506
Epoch 628/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1946 - accuracy: 0.9486 - val_loss: 0.1848 - val_accuracy: 0.9506
Epoch 629/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1946 - accuracy: 0.9486 - val_loss: 0.1848 - val_accuracy: 0.9506
Epoch 630/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1946 - accuracy: 0.9486 - val_loss: 0.1848 - val_accuracy: 0.9506
Epoch 631/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1946 - accuracy: 0.9486 - val_loss: 0.1848 - val_accuracy: 0.9506
Epoch 632/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1946 - accuracy: 0.9487 - val_loss: 0.1848 - val_accuracy: 0.9506
Epoch 633/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1946 - accuracy: 0.9487 - val_loss: 0.1848 - val_accuracy: 0.9503
Epoch 634/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1946 - accuracy: 0.9488 - val_loss: 0.1848 - val_accuracy: 0.9506
Epoch 635/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1946 - accuracy: 0.9488 - val_loss: 0.1848 - val_accuracy: 0.9506
Epoch 636/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1946 - accuracy: 0.9487 - val_loss: 0.1847 - val_accuracy: 0.9506
Epoch 637/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1945 - accuracy: 0.9487 - val_loss: 0.1847 - val_accuracy: 0.9506
Epoch 638/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1945 - accuracy: 0.9487 - val_loss: 0.1847 - val_accuracy: 0.9506
Epoch 639/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1945 - accuracy: 0.9487 - val_loss: 0.1847 - val_accuracy: 0.9506
Epoch 640/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1945 - accuracy: 0.9488 - val_loss: 0.1847 - val_accuracy: 0.9503
Epoch 641/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1945 - accuracy: 0.9488 - val_loss: 0.1847 - val_accuracy: 0.9503
Epoch 642/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1945 - accuracy: 0.9488 - val_loss: 0.1846 - val_accuracy: 0.9503
Epoch 643/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1945 - accuracy: 0.9488 - val_loss: 0.1846 - val_accuracy: 0.9503
Epoch 644/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1945 - accuracy: 0.9488 - val_loss: 0.1846 - val_accuracy: 0.9503
Epoch 645/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1945 - accuracy: 0.9488 - val_loss: 0.1846 - val_accuracy: 0.9503
Epoch 646/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1945 - accuracy: 0.9488 - val_loss: 0.1846 - val_accuracy: 0.9503
Epoch 647/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1945 - accuracy: 0.9488 - val_loss: 0.1846 - val_accuracy: 0.9503
Epoch 648/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1945 - accuracy: 0.9489 - val_loss: 0.1846 - val_accuracy: 0.9503
Epoch 649/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1945 - accuracy: 0.9489 - val_loss: 0.1845 - val_accuracy: 0.9503
Epoch 650/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1945 - accuracy: 0.9488 - val_loss: 0.1845 - val_accuracy: 0.9503
Epoch 651/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1945 - accuracy: 0.9488 - val_loss: 0.1845 - val_accuracy: 0.9503
Epoch 652/1000
13/13 [==============================] - 0s 5ms/step - loss: 0.1944 - accuracy: 0.9488 - val_loss: 0.1845 - val_accuracy: 0.9503
Epoch 653/1000
13/13 [==============================] - 0s 5ms/step - loss: 0.1944 - accuracy: 0.9488 - val_loss: 0.1845 - val_accuracy: 0.9503
Epoch 654/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1944 - accuracy: 0.9488 - val_loss: 0.1845 - val_accuracy: 0.9503
Epoch 655/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1944 - accuracy: 0.9488 - val_loss: 0.1844 - val_accuracy: 0.9503
Epoch 656/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1944 - accuracy: 0.9488 - val_loss: 0.1844 - val_accuracy: 0.9503
Epoch 657/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1944 - accuracy: 0.9488 - val_loss: 0.1844 - val_accuracy: 0.9503
Epoch 658/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1944 - accuracy: 0.9488 - val_loss: 0.1844 - val_accuracy: 0.9506
Epoch 659/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1944 - accuracy: 0.9488 - val_loss: 0.1844 - val_accuracy: 0.9506
Epoch 660/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1944 - accuracy: 0.9488 - val_loss: 0.1844 - val_accuracy: 0.9503
Epoch 661/1000
13/13 [==============================] - 0s 5ms/step - loss: 0.1944 - accuracy: 0.9488 - val_loss: 0.1844 - val_accuracy: 0.9503
Epoch 662/1000
13/13 [==============================] - 0s 5ms/step - loss: 0.1944 - accuracy: 0.9488 - val_loss: 0.1844 - val_accuracy: 0.9503
Epoch 663/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1944 - accuracy: 0.9488 - val_loss: 0.1844 - val_accuracy: 0.9503
Epoch 664/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1944 - accuracy: 0.9489 - val_loss: 0.1843 - val_accuracy: 0.9503
Epoch 665/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1944 - accuracy: 0.9489 - val_loss: 0.1843 - val_accuracy: 0.9506
Epoch 666/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1944 - accuracy: 0.9490 - val_loss: 0.1843 - val_accuracy: 0.9506
Epoch 667/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1944 - accuracy: 0.9490 - val_loss: 0.1843 - val_accuracy: 0.9506
Epoch 668/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1944 - accuracy: 0.9490 - val_loss: 0.1843 - val_accuracy: 0.9506
Epoch 669/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1944 - accuracy: 0.9490 - val_loss: 0.1843 - val_accuracy: 0.9508
Epoch 670/1000
13/13 [==============================] - 0s 5ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1843 - val_accuracy: 0.9508
Epoch 671/1000
13/13 [==============================] - 0s 5ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1843 - val_accuracy: 0.9508
Epoch 672/1000
13/13 [==============================] - 0s 6ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1843 - val_accuracy: 0.9511
Epoch 673/1000
13/13 [==============================] - 0s 6ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1843 - val_accuracy: 0.9511
Epoch 674/1000
13/13 [==============================] - 0s 6ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1843 - val_accuracy: 0.9511
Epoch 675/1000
13/13 [==============================] - 0s 6ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1843 - val_accuracy: 0.9511
Epoch 676/1000
13/13 [==============================] - 0s 5ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1842 - val_accuracy: 0.9511
Epoch 677/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1842 - val_accuracy: 0.9508
Epoch 678/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1842 - val_accuracy: 0.9508
Epoch 679/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1842 - val_accuracy: 0.9508
Epoch 680/1000
13/13 [==============================] - 0s 6ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1842 - val_accuracy: 0.9508
Epoch 681/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1842 - val_accuracy: 0.9508
Epoch 682/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1842 - val_accuracy: 0.9508
Epoch 683/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1842 - val_accuracy: 0.9508
Epoch 684/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1841 - val_accuracy: 0.9508
Epoch 685/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1841 - val_accuracy: 0.9508
Epoch 686/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1841 - val_accuracy: 0.9508
Epoch 687/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1841 - val_accuracy: 0.9511
Epoch 688/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1841 - val_accuracy: 0.9511
Epoch 689/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1841 - val_accuracy: 0.9511
Epoch 690/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1841 - val_accuracy: 0.9508
Epoch 691/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1841 - val_accuracy: 0.9508
Epoch 692/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1841 - val_accuracy: 0.9508
Epoch 693/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1841 - val_accuracy: 0.9508
Epoch 694/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1943 - accuracy: 0.9490 - val_loss: 0.1840 - val_accuracy: 0.9508
Epoch 695/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9490 - val_loss: 0.1840 - val_accuracy: 0.9508
Epoch 696/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9490 - val_loss: 0.1840 - val_accuracy: 0.9511
Epoch 697/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1942 - accuracy: 0.9490 - val_loss: 0.1840 - val_accuracy: 0.9511
Epoch 698/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1942 - accuracy: 0.9491 - val_loss: 0.1840 - val_accuracy: 0.9511
Epoch 699/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1942 - accuracy: 0.9491 - val_loss: 0.1840 - val_accuracy: 0.9511
Epoch 700/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1942 - accuracy: 0.9492 - val_loss: 0.1840 - val_accuracy: 0.9513
Epoch 701/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9492 - val_loss: 0.1840 - val_accuracy: 0.9513
Epoch 702/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9492 - val_loss: 0.1840 - val_accuracy: 0.9513
Epoch 703/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9492 - val_loss: 0.1840 - val_accuracy: 0.9513
Epoch 704/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9493 - val_loss: 0.1840 - val_accuracy: 0.9513
Epoch 705/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9493 - val_loss: 0.1840 - val_accuracy: 0.9513
Epoch 706/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9492 - val_loss: 0.1840 - val_accuracy: 0.9513
Epoch 707/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9492 - val_loss: 0.1840 - val_accuracy: 0.9513
Epoch 708/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9491 - val_loss: 0.1840 - val_accuracy: 0.9511
Epoch 709/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9491 - val_loss: 0.1840 - val_accuracy: 0.9511
Epoch 710/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9491 - val_loss: 0.1839 - val_accuracy: 0.9511
Epoch 711/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1942 - accuracy: 0.9492 - val_loss: 0.1839 - val_accuracy: 0.9513
Epoch 712/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1942 - accuracy: 0.9493 - val_loss: 0.1839 - val_accuracy: 0.9513
Epoch 713/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9493 - val_loss: 0.1839 - val_accuracy: 0.9513
Epoch 714/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9492 - val_loss: 0.1839 - val_accuracy: 0.9511
Epoch 715/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9491 - val_loss: 0.1839 - val_accuracy: 0.9511
Epoch 716/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9491 - val_loss: 0.1839 - val_accuracy: 0.9511
Epoch 717/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1942 - accuracy: 0.9492 - val_loss: 0.1839 - val_accuracy: 0.9513
Epoch 718/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9493 - val_loss: 0.1839 - val_accuracy: 0.9513
Epoch 719/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9494 - val_loss: 0.1839 - val_accuracy: 0.9513
Epoch 720/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9493 - val_loss: 0.1839 - val_accuracy: 0.9513
Epoch 721/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9493 - val_loss: 0.1839 - val_accuracy: 0.9513
Epoch 722/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9492 - val_loss: 0.1839 - val_accuracy: 0.9511
Epoch 723/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9491 - val_loss: 0.1838 - val_accuracy: 0.9511
Epoch 724/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9491 - val_loss: 0.1838 - val_accuracy: 0.9511
Epoch 725/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9491 - val_loss: 0.1838 - val_accuracy: 0.9511
Epoch 726/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9491 - val_loss: 0.1838 - val_accuracy: 0.9511
Epoch 727/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1942 - accuracy: 0.9491 - val_loss: 0.1838 - val_accuracy: 0.9513
Epoch 728/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9491 - val_loss: 0.1838 - val_accuracy: 0.9511
Epoch 729/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9492 - val_loss: 0.1838 - val_accuracy: 0.9511
Epoch 730/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9491 - val_loss: 0.1838 - val_accuracy: 0.9511
Epoch 731/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1942 - accuracy: 0.9492 - val_loss: 0.1838 - val_accuracy: 0.9511
Epoch 732/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9492 - val_loss: 0.1838 - val_accuracy: 0.9511
Epoch 733/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9492 - val_loss: 0.1838 - val_accuracy: 0.9511
Epoch 734/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9492 - val_loss: 0.1838 - val_accuracy: 0.9511
Epoch 735/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9492 - val_loss: 0.1838 - val_accuracy: 0.9511
Epoch 736/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9491 - val_loss: 0.1838 - val_accuracy: 0.9511
Epoch 737/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1942 - accuracy: 0.9492 - val_loss: 0.1838 - val_accuracy: 0.9513
Epoch 738/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1942 - accuracy: 0.9493 - val_loss: 0.1838 - val_accuracy: 0.9513
Epoch 739/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1942 - accuracy: 0.9494 - val_loss: 0.1838 - val_accuracy: 0.9513
Epoch 740/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9494 - val_loss: 0.1838 - val_accuracy: 0.9513
Epoch 741/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1942 - accuracy: 0.9494 - val_loss: 0.1838 - val_accuracy: 0.9513
Epoch 742/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1942 - accuracy: 0.9495 - val_loss: 0.1838 - val_accuracy: 0.9513
Epoch 743/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9495 - val_loss: 0.1838 - val_accuracy: 0.9513
Epoch 744/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1838 - val_accuracy: 0.9513
Epoch 745/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1942 - accuracy: 0.9495 - val_loss: 0.1838 - val_accuracy: 0.9513
Epoch 746/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1838 - val_accuracy: 0.9513
Epoch 747/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1838 - val_accuracy: 0.9513
Epoch 748/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1837 - val_accuracy: 0.9513
Epoch 749/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1837 - val_accuracy: 0.9513
Epoch 750/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1838 - val_accuracy: 0.9513
Epoch 751/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1838 - val_accuracy: 0.9513
Epoch 752/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1838 - val_accuracy: 0.9513
Epoch 753/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1837 - val_accuracy: 0.9513
Epoch 754/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9496 - val_loss: 0.1838 - val_accuracy: 0.9513
Epoch 755/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9496 - val_loss: 0.1838 - val_accuracy: 0.9513
Epoch 756/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9496 - val_loss: 0.1837 - val_accuracy: 0.9513
Epoch 757/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1837 - val_accuracy: 0.9513
Epoch 758/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1837 - val_accuracy: 0.9513
Epoch 759/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1837 - val_accuracy: 0.9513
Epoch 760/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9496 - val_loss: 0.1837 - val_accuracy: 0.9513
Epoch 761/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9496 - val_loss: 0.1837 - val_accuracy: 0.9513
Epoch 762/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9496 - val_loss: 0.1837 - val_accuracy: 0.9513
Epoch 763/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9496 - val_loss: 0.1837 - val_accuracy: 0.9513
Epoch 764/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9496 - val_loss: 0.1837 - val_accuracy: 0.9513
Epoch 765/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1837 - val_accuracy: 0.9513
Epoch 766/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1837 - val_accuracy: 0.9513
Epoch 767/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1837 - val_accuracy: 0.9513
Epoch 768/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1837 - val_accuracy: 0.9513
Epoch 769/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1837 - val_accuracy: 0.9513
Epoch 770/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1837 - val_accuracy: 0.9513
Epoch 771/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1837 - val_accuracy: 0.9513
Epoch 772/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1837 - val_accuracy: 0.9513
Epoch 773/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 774/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1837 - val_accuracy: 0.9513
Epoch 775/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 776/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 777/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 778/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1941 - accuracy: 0.9494 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 779/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1941 - accuracy: 0.9494 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 780/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1941 - accuracy: 0.9494 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 781/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1941 - accuracy: 0.9494 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 782/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1941 - accuracy: 0.9494 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 783/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9494 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 784/1000
13/13 [==============================] - 0s 6ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 785/1000
13/13 [==============================] - 0s 5ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 786/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 787/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 788/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 789/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 790/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 791/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 792/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 793/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 794/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 795/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 796/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 797/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9496 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 798/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9496 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 799/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 800/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 801/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 802/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 803/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 804/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 805/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1836 - val_accuracy: 0.9513
Epoch 806/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1836 - val_accuracy: 0.9515
Epoch 807/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1836 - val_accuracy: 0.9515
Epoch 808/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1836 - val_accuracy: 0.9515
Epoch 809/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9498 - val_loss: 0.1836 - val_accuracy: 0.9515
Epoch 810/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9498 - val_loss: 0.1835 - val_accuracy: 0.9513
Epoch 811/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1835 - val_accuracy: 0.9515
Epoch 812/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1836 - val_accuracy: 0.9515
Epoch 813/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1835 - val_accuracy: 0.9515
Epoch 814/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1836 - val_accuracy: 0.9515
Epoch 815/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1836 - val_accuracy: 0.9515
Epoch 816/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1835 - val_accuracy: 0.9515
Epoch 817/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1835 - val_accuracy: 0.9515
Epoch 818/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1835 - val_accuracy: 0.9515
Epoch 819/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9498 - val_loss: 0.1835 - val_accuracy: 0.9515
Epoch 820/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9498 - val_loss: 0.1835 - val_accuracy: 0.9515
Epoch 821/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9498 - val_loss: 0.1835 - val_accuracy: 0.9513
Epoch 822/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9498 - val_loss: 0.1835 - val_accuracy: 0.9513
Epoch 823/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9496 - val_loss: 0.1835 - val_accuracy: 0.9513
Epoch 824/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9496 - val_loss: 0.1835 - val_accuracy: 0.9513
Epoch 825/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9496 - val_loss: 0.1835 - val_accuracy: 0.9513
Epoch 826/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1835 - val_accuracy: 0.9513
Epoch 827/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1835 - val_accuracy: 0.9513
Epoch 828/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1835 - val_accuracy: 0.9513
Epoch 829/1000
13/13 [==============================] - 0s 4ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1835 - val_accuracy: 0.9513
Epoch 830/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1835 - val_accuracy: 0.9513
Epoch 831/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1835 - val_accuracy: 0.9513
Epoch 832/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1835 - val_accuracy: 0.9513
Epoch 833/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1835 - val_accuracy: 0.9513
Epoch 834/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1835 - val_accuracy: 0.9513
Epoch 835/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1835 - val_accuracy: 0.9513
Epoch 836/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1835 - val_accuracy: 0.9513
Epoch 837/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1835 - val_accuracy: 0.9513
Epoch 838/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9498 - val_loss: 0.1835 - val_accuracy: 0.9515
Epoch 839/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1835 - val_accuracy: 0.9515
Epoch 840/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1835 - val_accuracy: 0.9515
Epoch 841/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1835 - val_accuracy: 0.9515
Epoch 842/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1835 - val_accuracy: 0.9515
Epoch 843/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9498 - val_loss: 0.1835 - val_accuracy: 0.9515
Epoch 844/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9498 - val_loss: 0.1835 - val_accuracy: 0.9515
Epoch 845/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9495 - val_loss: 0.1835 - val_accuracy: 0.9513
Epoch 846/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9498 - val_loss: 0.1835 - val_accuracy: 0.9515
Epoch 847/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1835 - val_accuracy: 0.9515
Epoch 848/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1835 - val_accuracy: 0.9515
Epoch 849/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1835 - val_accuracy: 0.9515
Epoch 850/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1835 - val_accuracy: 0.9515
Epoch 851/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1835 - val_accuracy: 0.9515
Epoch 852/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1835 - val_accuracy: 0.9515
Epoch 853/1000
13/13 [==============================] - 0s 2ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1835 - val_accuracy: 0.9515
Epoch 854/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1835 - val_accuracy: 0.9515
Epoch 855/1000
13/13 [==============================] - 0s 3ms/step - loss: 0.1941 - accuracy: 0.9497 - val_loss: 0.1835 - val_accuracy: 0.9515

3.1.5. Plot performance#

Here, we plot the history of the training and the performance in a ROC curve

import matplotlib.pyplot as plt

%matplotlib inline
# plot loss vs epoch
plt.figure(figsize=(15, 10))
ax = plt.subplot(2, 2, 1)
ax.plot(history.history["loss"], label="loss")
ax.plot(history.history["val_loss"], label="val_loss")
ax.legend(loc="upper right")
ax.set_xlabel("epoch")
ax.set_ylabel("loss")

# plot accuracy vs epoch
ax = plt.subplot(2, 2, 2)
ax.plot(history.history["accuracy"], label="acc")
ax.plot(history.history["val_accuracy"], label="val_acc")
ax.legend(loc="upper left")
ax.set_xlabel("epoch")
ax.set_ylabel("acc")

# Plot ROC
Y_predict = model.predict(X_test)
from sklearn.metrics import roc_curve, auc

fpr, tpr, thresholds = roc_curve(Y_test, Y_predict)
roc_auc = auc(fpr, tpr)
ax = plt.subplot(2, 2, 3)
ax.plot(fpr, tpr, lw=2, color="cyan", label="auc = %.3f" % (roc_auc))
ax.plot([0, 1], [0, 1], linestyle="--", lw=2, color="k", label="random chance")
ax.set_xlim([0, 1.0])
ax.set_ylim([0, 1.0])
ax.set_xlabel("false positive rate")
ax.set_ylabel("true positive rate")
ax.set_title("receiver operating curve")
ax.legend(loc="lower right")
plt.show()

130/130 [==============================] - 0s 540us/step

../_images/a848757e2b374aa012ed2b9e1f533743ad0b12e70f9c6ed07dcb5bcd5a955ce7.png

df_all["dense"] = model.predict(X)  # add prediction to array
print(df_all.iloc[:5])

649/649 [==============================] - 0s 483us/step
     f_mass4l     f_massjj  isSignal  dense
125.077103  1300.426880       1.0    1.0
124.238113   437.221863       1.0    1.0
124.480667  1021.744080       1.0    1.0
124.919464  1101.381958       1.0    1.0
125.049065   498.717194       1.0    1.0

3.1.6. Plot NN output vs input variables#

Here, we will plot the NN output and devision boundary as a function of the input variables.

# make a regular 2D grid for the inputs
myXI, myYI = np.meshgrid(np.linspace(-2, 2, 200), np.linspace(-2, 2, 200))
# print shape
print(myXI.shape)

# run prediction at each point
myZI = model.predict(np.c_[myXI.ravel(), myYI.ravel()])
myZI = myZI.reshape(myXI.shape)

(200, 200)
1250/1250 [==============================] - 1s 528us/step

The code below shoes how to plot the NN output and decision boundary. Does it look optimal?

from matplotlib.colors import ListedColormap

plt.figure(figsize=(20, 7))

# plot contour map of NN output
# overlaid with test data points
ax = plt.subplot(1, 2, 1)
cm = plt.cm.RdBu
cm_bright = ListedColormap(["#FF0000", "#0000FF"])
cont_plot = ax.contourf(myXI, myYI, myZI, cmap=cm, alpha=0.8)
ax.scatter(X_test[:, 0], X_test[:, 1], c=Y_test, cmap=cm_bright, edgecolors="k")
ax.set_xlim(-2, 2)
ax.set_ylim(-2, 2)
ax.set_xlabel(VARS[0])
ax.set_ylabel(VARS[1])
plt.colorbar(cont_plot, ax=ax, boundaries=[0, 1], label="NN output")

# plot decision boundary
# overlaid with test data points
ax = plt.subplot(1, 2, 2)
cm = plt.cm.RdBu
cm_bright = ListedColormap(["#FF0000", "#0000FF"])
cont_plot = ax.contourf(myXI, myYI, myZI > 0.5, cmap=cm, alpha=0.8)
ax.scatter(X_test[:, 0], X_test[:, 1], c=Y_test, cmap=cm_bright, edgecolors="k")
ax.set_xlim(-2, 2)
ax.set_ylim(-2, 2)
ax.set_xlabel(VARS[0])
ax.set_ylabel(VARS[1])
plt.colorbar(cont_plot, ax=ax, boundaries=[0, 1], label="NN output")
plt.show()

../_images/1902f5d57d1d6bcd3e0b0b1ca0ef2d0effe4ef43f2fff9bf172da268fed6f894.png

Question 1: What happens if you increase/decrease the number of hidden layers?

Question 2: What happens if you increase/decrease the number of nodes per hidden layer?

Question 3: What happens if you add/remove dropout?

Question 4: What happens if you add/remove early stopping?