search

VisualComputingInstitute / triplet-reid

Code for reproducing the results of our "In Defense of the Triplet Loss for Person Re-Identification" paper.
https://arxiv.org/abs/1703.07737
MIT License
764 stars 216 forks source link

Error while trying to use pretrained tensorflow model #52

Closed ml2345 closed 6 years ago

ml2345 commented 6 years ago

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 commented 6 years ago

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 commented 6 years ago

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

sharadhigm commented 5 years ago

Hi,

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

Thanks.