Я работаю над моделью классификации изображений с Tensorflow/Keras, и я сталкиваюсь с проблемой во время обучения. Description of the problem my model reaches a loss (loss) of ~ 1.3 After a few epochs and no longer improves, despite: /> [*] The increase in the number of epochs (up to 100) [*] The adjustment of the learning rate [*] The increase in the size of the Набор данных
Code Code
model = Sequential([
Conv2D(32, (3,3), activation='relu', input_shape=(150,150,3)),
MaxPooling2D(2,2),
Flatten(),
Dense(128, activation='relu'),
Dense(3, activation='softmax')
])
model.compile(optimizer=Adam(learning_rate=0.001),
loss='categorical_crossentropy',
metrics=['accuracy'])
history = model.fit(train_generator,
epochs=100,
validation_data=validation_generator)
Подробнее здесь: https://stackoverflow.com/questions/796 ... i-use-them
