Swarnim Jain

Intermediate evaluation metrics

2

I'm trying to run the TAPIR training from scratch with low GPU resources and am adhering to the training configurations specifications from the paper (with gradient accumulation as mentioned here:...

Intermediate training metrics for TAPIR

4

I'm looking to replicate training of TAPIR on Kubric MOVi-E with adjusted compute resources and need insights on intermediate training metrics. What were the intermediate training statistics during your runs?...

ResNet implementation for TAPIR different from typical

1

Why has TAPIR used a different implementation for the ResNet than the typical one used (https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py, particularly BasicBlock vs BlockV2)?

Training instability and non-convergence with TAPIR on kubric-e dataset across multiple GPUs

1

I'm experiencing issues training the TAPIR model on the kubric-e dataset across different GPU configurations with PyTorch lightning (both checkpoint and non-checkpoint model). The losses either don't converge or show...