Yixiao Ge

It seems totally failed. I did not meet this problem before. Did you load all pre-trained weights as instructed?

I cannot locate your issue. Maybe provide your full testing log could help.

It shows that resume='', indicating that you did not load any model weights.

for training (sampling positives and negatives) or test (evaluation)?

Maybe you can use the pretrained model to extract the visual features for each person image, and then cluster them into several groups by calculating the distances between each other.

> Hi, your work is really great. I want to draw on the work of embedding the pose map in that part, but I don't see how the pose is...

> > > Hi, your work is really great. I want to draw on the work of embedding the pose map in that part, but I don't see how the...

ReID tasks are very sensitive to the number of GPUs, and I think this is caused by the batch size for BN. For example, in default, I use a batch...

It is a mistake that I missed the `val_loader` when re-arranging the code. You could follow https://github.com/yxgeee/FD-GAN/blob/master/baseline.py#L59 to create the val loader. @liulitianji @Haoru

Have you tried to use `rerank_dist = compute_jaccard_distance(target_features, k1=args.k1, k2=args.k2, search_option=3, use_float16=True)` in https://github.com/yxgeee/SpCL/blob/master/examples/spcl_train_uda.py#L175 ? (`search_option=3` could save GPU memory by using faiss_cpu, `use_float16=True` could save CPU memory by using...