Autoencoder , steps_per_epoch, 应该包含什么值？
Autoencoder , steps_per_epoch,What value should it contain?
我正在尝试用我自己的数据集创建一个堆叠式自动编码器，一切都很好，当我尝试用张量板绘制曲线时，我得到了这个标量：
我认为错误在 steps_per_epoch 如果它不是 X_train.shape[0] 那么它应该包含什么：
autoencoder.fit_generator(generated_data.flow(X_train, X_train, batch_size=batch_size), steps_per_epoch=X_train.shape[0], epochs=epochs, validation_data=(X_test, X_test), callbacks=[TensorBoard(log_dir='/tmp/autoencoder')])
还有另外一件事我如何添加准确度？
来自 fit_generator
的文档
steps_per_epoch: Integer. Total number of steps (batches of samples)
to yield from generator before declaring one epoch finished and
starting the next epoch. It should typically be equal to the number of
samples of your dataset divided by the batch size. Optional for
Sequence: if unspecified, will use the len(generator) as a number of
steps.
所以你应该设置它大致等于X_train.shape[0]/batch_size
要监控准确性，请使用
autoencoder.compile(optimizer='rmsprop', loss='mse', metrics=['mse', 'accuracy'])
我正在尝试用我自己的数据集创建一个堆叠式自动编码器，一切都很好，当我尝试用张量板绘制曲线时，我得到了这个标量：
我认为错误在 steps_per_epoch 如果它不是 X_train.shape[0] 那么它应该包含什么：
autoencoder.fit_generator(generated_data.flow(X_train, X_train, batch_size=batch_size), steps_per_epoch=X_train.shape[0], epochs=epochs, validation_data=(X_test, X_test), callbacks=[TensorBoard(log_dir='/tmp/autoencoder')])
还有另外一件事我如何添加准确度？
来自 fit_generator
steps_per_epoch: Integer. Total number of steps (batches of samples) to yield from generator before declaring one epoch finished and starting the next epoch. It should typically be equal to the number of samples of your dataset divided by the batch size. Optional for Sequence: if unspecified, will use the len(generator) as a number of steps.
所以你应该设置它大致等于X_train.shape[0]/batch_size
要监控准确性，请使用
autoencoder.compile(optimizer='rmsprop', loss='mse', metrics=['mse', 'accuracy'])