triplet-reid icon indicating copy to clipboard operation
triplet-reid copied to clipboard

Code for reproducing the results of our "In Defense of the Triplet Loss for Person Re-Identification" paper.

Results 30 triplet-reid issues
Sort by recently updated
recently updated
newest added

I have trained a model on custom data. Created h5 file and pb file. I want to use the model for Multi camera tracking. Please let me know how should...

I always get an ResourceExhaustedError: OOM error whenever using this code. I'm unable to use any batch size greater than 256. Can you point out which parts are the most...

I use the codes to train my own dataset, but raised this error at sees.run(). The detail printed log is as below in which I changed some args such as...

I tried some small Ps, some small Ks and many learning rates. But I always get a loss of 0.693. Anyone can share his/her experience on imagenet?

discussion (not bug)

This is more of a discussion than an issue. I was wondering about potential overfitting in Trinet and how one could estimate it. Normally I always have a validation dataset...

I'm trying to do a transfer learning for my dataset. I have only ~30 persons, but I do have a lot of images per person (~500 - 2000) . I...

Trying to train on market1501 as a proof of concept before modifying anything. The training loss quickly foes down to 0.7 and stays there forever. So far haven't changed anything...

Thanks for your work! Given with a `pre-trained` model, how to perform single inference on image? Thanks,

Hi, I am new to this subject, in the paper the soft-margin formula is ln(1+exp(x)), I don't understand what the x stand for? how to caculate it ? thank you...

discussion (not bug)

I have trained the model on my own dataset, and got tensorflow checkpoint. In the readme, it says that we can use embed.py to compute the embeddings of the images....