Sandeep IPK

Question about the attentional GCN module

13

Hey @jwyang, I highly appreciate your work in completing this repository. I want to use the aGCN architecture you proposed for my project, but I couldn't find the exact module/function...

Question regarding multi-gpu training in ContrastiveLosses4VRD/tools/train_net_step_rel.py

1

` ### Adaptively adjust some configs ### cfg.NUM_GPUS = torch.cuda.device_count() original_batch_size = cfg.NUM_GPUS * cfg.TRAIN.IMS_PER_BATCH original_ims_per_batch = cfg.TRAIN.IMS_PER_BATCH original_num_gpus = cfg.NUM_GPUS if args.batch_size is None: args.batch_size = original_batch_size assert (args.batch_size...

Regarding the evaluation of your pre-trained model

1

I have come to the problem of evaluating your the pre-trained ShAPO model you provided in the repo [here](https://www.dropbox.com/s/nrsl67ir6fml9ro/ckpts.tar.xz?dl=1) I could not find an evaluation script in your ShAPO repository,...