jiarenyf
jiarenyf
Would you please add support for tf or split+transpose in caffe, thank you.
Could you please support Video MAE: https://github.com/MCG-NJU/VideoMAE Thank you ~
https://github.com/NVlabs/SegFormer/blob/master/mmseg/models/backbones/mix_transformer.py#L374 https://drive.google.com/drive/folders/1b7bwrInTW4VLEm27YawHOAMSMikga2Ia I think segformer is a good backbone / feature extractor. It provides pretrained weights so I think maybe it is good to introduce into timm.
说好的publicly available呢???
https://github.com/rwightman/pytorch-image-models/issues/1258
Using ConcatDataset to allow data_loader worker > 0 to speed up training. See here: https://pytorch.org/docs/stable/data.html#torch.utils.data.ConcatDataset
### Description & Motivation Because the first iteration time is incorrect (model initialization and torch.compile when first interation) ### Pitch _No response_ ### Alternatives _No response_ ### Additional context _No...