Summary:
There is a module called `2to3` which you can target for future specifically to remove these, the directory of `caffe2` has the most redundant imports:
```2to3 -f future -w caffe2```
Pull Request resolved: https://github.com/pytorch/pytorch/pull/45033
Reviewed By: seemethere
Differential Revision: D23808648
Pulled By: bugra
fbshipit-source-id: 38971900f0fe43ab44a9168e57f2307580d36a38
Summary: A single negative index can crash the job today. We want to skip a few of them but not a lot. If we skip too many then we will force the job to crash.
Reviewed By: kennyhorror
Differential Revision: D6003461
fbshipit-source-id: 7881ed6c2cfa78c7bda90c7aa01e81ca00fd08a6
Summary:
It looks like this operator is missing some enforces that it should have (since
it's working on the user inputs). This diff is added enforces to ids to be in a
valid range.
Reviewed By: dzhulgakov
Differential Revision: D5488336
fbshipit-source-id: e045c3b71b92e443edd23c95aa75d144877f1334
Summary: This diff is one step towards enabling python 3 build by making it be more diligent in its handling of strings.
Reviewed By: salexspb
Differential Revision: D4893083
fbshipit-source-id: 28b8adf3280e8d1f0a7dc9b0fee5ad53f2fada57
Summary:
If we go to prod some of the sparse features might be empty or for some reason
batch might be empty. It's a good idea to be sure that we can run empty
batches.
Reviewed By: dzhulgakov
Differential Revision: D4197297
fbshipit-source-id: 1a154ebf625d1a39fd15354a154cf100f525ae9a
