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.

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 while trying to use pretrained tensorflow model #52

Closed
ml2345 opened this issue Jul 20, 2018 · 3 comments
Closed

Error while trying to use pretrained tensorflow model #52

ml2345 opened this issue Jul 20, 2018 · 3 comments

Comments

@ml2345
Copy link

ml2345 commented Jul 20, 2018

Hey, thanks for the nice work!
I was trying to use the TF checkpoint (provided here ).
Steps used:

  1. Create a ./files.txt in which each line is a path to an image to be embedded
  2. Downloaded the checkpoint provided in Releases and put in './checkpoints/
  3. Ran the following command:
    python embed.py --experiment_root ./checkpoint/ --dataset ./files.txt --filename test_embeddings.h5
    However, the following error comes:

raise IOError('args.json could not be found in: {}'.format(args_file))
OSError: args.json could not be found in: ./checkpoint/args.json

Could you please help on how to use the checkpoint of Market to extract features from images?

@Pandoro
Copy link
Member

Pandoro commented Jul 23, 2018

Hi @ml2345 ,

you can find the args file here, we should have put it in the release but I sadly forgot about it when making it. Just paste it into args.json and put it in the experiment root.

@Pandoro
Copy link
Member

Pandoro commented Jul 23, 2018

I'm closing this. It should be fairly obvious how to get it to work. If not please re-open it.

@Pandoro Pandoro closed this as completed Jul 23, 2018
@sharadhigm
Copy link

Hi,

After adding args.json.when embed.py is run
image
jsondecodeerror is popping up.Kindly guide on how to go about this.

Thanks.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants