How torch.cat and torch.split effect the training result?

1

Hi there,

I am training a network which is modified based on Faster-RCNN. I tried to concat the feature extracted form backbone and split the new feature as follow:

feat_flatten_cat = torch.cat(feat_flatten, 2) # feat_flatten: list( [BN * channel * WH])
feat_flatten = torch.split(feat_flatten_cat, [feat.shape[-1] for feat in feat_flatten], dim=2)

I found that the training results were totally different from the case that I comment these two lines of code, the training is very hard to converge and the accuracy is close to 0. Can anyone explain this?

Appreciate any reply.

2

By the way, for both case, ‘feat_flatten’ is equal, which has been checked by tensor.equal()