pytorch-image-models

pytorch-image-models copied to clipboard

**Describe the bug** If you use the out of the box image transforms for TinyViT, they do not really work if you want to use a grayscale images, because they...

asusdisciple


the-cat-crying

[BUG] Loading state dict in a feature extraction network

1

**Describe the bug** Hi Ross! I'm facing a small issue with the features extractor, here are some details: The function `create_model` supports the argument of `checkpoint_path` which allows to load...

ioangatop

Support RepGhostNetV2 conv s/m/l, based on MobileNetV4, without weights though

4

Build RepGhostNetV2 based on MobileNetV4. Our RepGhostNetV2 differs to MobileNetV4 only in the shortcut connections. As an alternative efficient backbone to MobileNetV4, RepGhostNetV2 has exactly the same parameters and FLOPs...

ChengpengChen

**Is your feature request related to a problem? Please describe.** A clear and concise description of what the problem is. i think it is good to add the new image...

TheDarkKnight-21th

Update torchvision.tranforms version to torchvision.transforms.v2

2

According to https://pytorch.org/vision/stable/transforms.html#v1-or-v2-which-one-should-i-use

lixit

Experimenting with tiny test models

1

How small can they go and be useful for regression tests w/ real weights?

rwightman

[FEATURE] Support resizing rectangular pos_embed

1

**Is your feature request related to a problem? Please describe.** Currently when changing ViT img size from a rectangular size, `resample_abs_pos_embed()` does not work correctly since it does not know...

gau-nernst

Warmup on uneven last-batch-size in `validate.py`

2

In the spirit of warming up for JIT compilation, add a warmup iteration in case the very last batch has a different size that may unwittingly trigger recompilation

eqy

Mambaout

1

rwightman