CODEWITHSUNDEEP
pythontensorflowdeep-learninggpulstm
Sadcow
Sadcow

Reputation: 730

Transfer an LSTM model from cpu to GPU

I have a very simple LSTM model which I've built in tensorflow and it works on CPU. However, I want to use this model on GPU. For the pytorch, I've defined the device and etc, however for tensorflow, I don't have any idea why it can not work. Do you have any suggestion for me? Thanks

model = Sequential()
model.add(LSTM(64, activation='relu', input_shape=(X_train.shape[1], X_train.shape[2]), return_sequences=True))
model.add(LSTM(32, activation='relu', return_sequences=False))
model.add(Dropout(0.1))
model.add(Dense(Y_train.shape[1], kernel_regularizer='l2'))
callback = tf.keras.callbacks.EarlyStopping(monitor='loss', patience=50)
opt = keras.optimizers.Adam(learning_rate=0.0008)
model.compile(optimizer=opt, loss='mse')
#model.summary()
history = model.fit(X_train, Y_train, epochs=2, batch_size=100, validation_data=(X_val, Y_val), callbacks=[callback],verbose=1, device).to(device)

Upvotes: 0

Views: 944

Answers (2)

The Auto Specter
The Auto Specter

Reputation: 1

i believe as per LSTM guidelines are concerned, it works on tanh activation function by default... this is to account the usage of GPU as a default computational hardware with CPU. if you change that activation, GPU will not be used. Switch back to tanh, and check again.

Upvotes: 0

Karan
Karan

Reputation: 26

For tensorflow, the models run on GPU for computations by default. It is given on their official documentation.

Is there some kind of error that shows up when you run your model? Because this should work just fine when running on GPU as well instead of a CPU.

Upvotes: 1

Related Questions