triplet-reid
triplet-reid copied to clipboard
VisualComputingInstitute
Code for reproducing the results of our "In Defense of the Triplet Loss for Person Re-Identification" paper.
Hi, I'm trying to write a script to embed a single image based on your code, it's look something like this: ```python import json import os from importlib import import_module...
Hi,thank for your work. I want to use the Pretrained TensorFlow models to Compute embeddings but i cant not find the"args.json".please tell me where it is and how to use...
Hi, Thanks for the excellent code. I successfully trained a model with my own customized dataset. And now I want to visualize what is learned by the neural network. Do...
Hi @lucasb-eyer, I have done a experiment on an instance image retrieval. The loss is converged well, and the batch-p@K goes to almost 100%. I used the model to tested...
Hello, I want to train VIPeR, and set the batch-k to 2,but when I test, the top-1 is 25.33%. I want to know did you trained the VIPeR?Thank you
In your TF codes, you first `shuffle` person ids and then repeat them forever. In training, you choose `batch_p` from the dataset according to the queue. For one person, you...
Nice work. I wonder to know if it is possible to release the implementation of the proposed LuNet? Thanks.
It seems that the model only runs on a single gpu no matter how many gpus are available. If the space the model takes up is more than the volume...
I have replicated your papar : > , on the Market1501 dataset by caffe. It has good performance just as your paper said. As I can see, the Batch hard...
Hello, I used the pre-trained model given in this repository on my own image dataset to calculate embeddings and then calculated co-sine similarity between the embeddings. Testing on same person...
Metadata
Owner
Metadata
Code for reproducing the results of our "In Defense of the Triplet Loss for Person Re-Identification" paper.