Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Re: Training own network using transfer learning #100

Open
sharmarochan opened this issue May 16, 2019 · 1 comment
Open

Re: Training own network using transfer learning #100

sharmarochan opened this issue May 16, 2019 · 1 comment

Comments

@sharmarochan
Copy link

No description provided.

@sharmarochan sharmarochan changed the title I am training network on my data set I am training deeplab architecture on my data set. To do so I zipped both image and mask images and passed as an argument to model.predict. but getting error. Screenshot of the same is attached. May 16, 2019
@sharmarochan
Copy link
Author

I am training deeplab architecture on my data set. To do so I zipped both image and mask images and passed as an argument to model.predict. but getting error. Screenshot of the same is attached.
p1

To resolve it i also tried def combine_generator(gen1, gen2):
while True:
yield(gen1.next(), gen2.next())

which was given as one of the solution but it too is giving error.
p2

Please help if anyone has come across similar problem. Thanks

@sharmarochan sharmarochan changed the title I am training deeplab architecture on my data set. To do so I zipped both image and mask images and passed as an argument to model.predict. but getting error. Screenshot of the same is attached. Re: Training own network May 16, 2019
@sharmarochan sharmarochan changed the title Re: Training own network Re: Training own network using transfer learning May 16, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@sharmarochan