-
Notifications
You must be signed in to change notification settings - Fork 19.5k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Error when saving multiple output model weights #3971
Comments
Here is the code: `model = Graph() model.add_node(Convolution2D(32,3,3, border_mode = 'same', model.add_node(Dense(num_classes, activation="softmax"), name="output1", input="shared_layers", create_output=True) epochs = 30 model.compile(loss={"output1": "categorical_crossentropy", model.fit({"sequence_input": X_train, "output1": y_train1, "output2": y_train2, scores = model.evaluate({"sequence_input": X_test, "output1": y_test1, "output2": y_test2, |
Looks like that there was an issue with h5py module. I'm pickling model weights now and everything is fine. |
I get the below exception (call stack from VS2015) when I do model.save_weights or a checkpoint. It has only happened with multiple-output models. I use Theano backend (Theano 0.8.2), CUDA 7.5. This is Windows 7. Please let me know if further information is required.
Exception thrown at 0x00000000188E2F12 (tk85.dll) in pythonw.exe: 0xC0000005: Access violation reading location 0x0000000000000368.
The text was updated successfully, but these errors were encountered: