I tried to use the i3d implementation here for another task. However, it seems like the provided weights are not just from training on Kinetics. I guess it was also trained on charades.
this is the error when I try to load weights for a model to classify Kinetics (as an example).
size mismatch for logits.conv3d.weight: copying a param with shape torch.Size([157, 1024, 1, 1, 1]) from checkpoint, the shape in current model is torch.Size([400, 1024, 1, 1, 1])
Is it possible to include Kinetics-only weights?
Hi,
I tried to use the i3d implementation here for another task. However, it seems like the provided weights are not just from training on Kinetics. I guess it was also trained on charades. this is the error when I try to load weights for a model to classify Kinetics (as an example).
size mismatch for logits.conv3d.weight: copying a param with shape torch.Size([157, 1024, 1, 1, 1]) from checkpoint, the shape in current model is torch.Size([400, 1024, 1, 1, 1])
Is it possible to include Kinetics-only weights?Thanks