-
Notifications
You must be signed in to change notification settings - Fork 28
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
[URGENT] There is less inputs received while giving the exact number of inputs required #508
Comments
@Saboteur20, When passing a dataset with two input images, the first one was passed to the actual network and the second one was left out and treated as the target value.Thank you! |
@tilakrayal Off course , the actual issue is after creating the testing model with weights of the training model:
when I want to input testing pairs in the below loop :
an error is raised which was stated above , the error is raised when I call the function |
@tilakrayal Off course , the actual issue is after creating the testing model with weights of the training model:
when I want to input testing pairs in the below loop :
an error is raised which was stated above , the error is raised when I call the function |
@Saboteur20, |
I am testing an encoder decoder lstm model .
the training phase went well but the testing phase after building the testing model is giving me an error while trying to input to the decoder layer , here's the error:
my script is :
the exact issue is in this line :
output_tokens, h, c = decoder_model.predict_step([target_seq] + states_value)
while the script reached this section:
I have tried fixing the issue by changing the way I fed the inputs multiple times ,but nothing changed.
I am sorry for lengthening the code so much , but I was afraid that I would miss a key line that would help in the issue.
please be kind in responding quickely because I have to submit my full project in less than two weeks.
I have uploaded the required files in case if someone wants to reproduce the issue.
Project Files.zip
The text was updated successfully, but these errors were encountered: