Yi Yang

Also Duplicate of #90

Hi @swarnim-j , Sorry we do not have bandwidth to look into the problem. We just attach the intermediate evaluation metrics for TAPVid-DAVIS strided eval as a further reference for...

Hi @swarnim-j , Thank you for the patience. Here is the intermediate evaluation metrics on TAPVid-DAVIS **strided** evaluation for training a tapir model with 100K steps, hope it helps. Average...

Here are the intermediate metrics on TAPVid-DAVIS **query first** evaluation: Average Jaccard:  Position Accuracy:  Occlusion Accuracy: 

Hi @swarnim-j Our ResNet in TAPIR implementation was impacted by TSM-ResNet in the TAP-Net project and ResNet in RAFT and PIPs. We also did a little internal exploration on the...

Hi, one quick try would be to add loss to all intermediate outputs as well. Since Tapir is an iterative refinement method, every single step output is supervised to get...

Hi @bsmy12 , I am trying to reproduce your problem using our colab, but I cannot. Here is the runtime I got on a L4 GPU (T4 GPU is running...