I ran my model yesterday on Google colab using their GPU and no error was encountered.
However, today I tried to run the same code (unchanged from yesterday) and I get the following error:
UnknownError: Graph execution error:
Fail to find the dnn implementation.
[[{{node CudnnRNN}}]]
[[sequential/bidirectional/forward_lstm/PartitionedCall]] [Op:__inference_train_function_6026]
The following is my model:
model.add(Embedding(vocab_size,embedding_vector_length,input_length=X_train.shape[1]))
model.add(Bidirectional(LSTM(250,return_sequences=True)))
model.add(Dropout(0.2))
model.add(Flatten())
model.add(Dense(128,activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(64,activation='relu'))
model.add(Dense(32,activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(16,activation='relu'))
model.add(Dense(num_classes,activation='softmax')) #sigmoid or relu-
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy']) #if relu, use mse or mae #maybe oversample lower classes
callbacks = [EarlyStopping(monitor='val_loss', patience=3),ModelCheckpoint('../model/model.h5', save_best_only=True,save_weights_only=False)]
history = model.fit(X_train, y_train, validation_split=0.11, epochs=15, batch_size=32, verbose=1, callbacks=callbacks) #epochs will stop before 15 due to callbacks
Error occurs at this line:
history = model.fit(X_train, y_train, validation_split=0.11, epochs=15, batch_size=32, verbose=1, callbacks=callbacks) #epochs will stop before 15 due to callbacks
I tried solutions from other threads but none of them worked. Funny enough, it doesn't happen when I use CPU.
