Lu Chongkai
Lu Chongkai
I cannot say this is a solution -- but changing a computer solving my problem -- at least it proves it's not about my videos. Actually, I kind of **forcely**...
There are many trained models in Model Zoo, while all of them are just used to test the performance of the proposed works. Do you plan to make them available...
> > There are many trained models in Model Zoo, while all of them are just used to test the performance of the proposed works. Do you plan to make...
> @makecent Thanks for your suggestions. We will consider this. Are you interested to contribute? I'd like to share the backbones implemented by myself. While I am not confident on...
I just made a PR #1713 as a illustration of the initial idea.
@hukkai I am in favor of the option1 because it's simple. Furthermore, in some cases it may be NOT good to put a trhid party codes in a single py...
I just made a demo PR. It allows us to use all slowfast models. To use them, the package `pytorchvideo` and `fvcore` are required.
From torch 1.10.0 on, the [CrossEntropyLoss]() offcially supports inputing with soft labels (probabilities) and the lable smoothing.
> For **I found the test-last use a custom name for the predictions**: I think it's OK since the `--test-last` flag just tests the last checkpoint during training (and output...
> That difference doesn't bother I think: it can be handled by using different data pipelines (note that we have val_pipeline and test_pipeline in the config and they are different)....