outputs=[y_pred]
)
opt = optimizer(learning_rate=learning_rate)
model.compile(
loss="categorical_crossentropy",
optimizer=opt,
metrics=["accuracy"]
)
return model
if __name__ == "__main__":
data = DOGSCATS()
train_dataset = data.get_train_set()
val_dataset = data.get_val_set()
test_dataset = data.get_test_set()
img_shape = data.img_shape
num_classes = data.num_classes
# Global params
epochs = 40
batch_size = 128
# Best model params
params = {
"dense_layer_size": 128,
x = Dense(units=num_classes, kernel_initializer=kernel_initializer)(x)
y_pred = Activation("softmax")(x)
model = Model(inputs=[input_img], outputs=[y_pred])
opt = optimizer(learning_rate=learning_rate)
model.compile(loss="categorical_crossentropy",
optimizer=opt,
metrics=["accuracy"])
return model
if __name__ == "__main__":
data = DOGSCATS()
train_dataset = data.get_train_set()
val_dataset = data.get_val_set()
test_dataset = data.get_test_set()
img_shape = data.img_shape
num_classes = data.num_classes
# Global params
epochs = 100
batch_size = 128
params = {
"dense_layer_size": 128,
"kernel_initializer": "GlorotUniform",