Ross Wightman

@flywheel1412 it's never been a priority since they didn't seem particularly stronger or better than other mobile models here already (mobilenet-v2/v3, hardcorenas, tinynet, lcnet, ghostnet, etc). Could likely be supported...

@flywheel1412 the last batch of results are all in the csv files here: https://github.com/huggingface/pytorch-image-models/tree/main/results `benchmark-*` are the per architecture inference and train throughput numbers, and the `results-*` are the per-weight...

@LuoXin-s you can uncomment https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/eva.py#L820 to download from the original source, the conversion mapping should load it... there is no information as to what that 'pretrain' is, so I've left...

@Coderx7 thanks for the PR, looks like a decent lightweight model, but the big stack of layers in a sequential doesn't really line up with other timm models, makes it...

@Coderx7 RexNet is probably the simplest example, ResNetV2 and RegNet are decent examples as well... * https://github.com/rwightman/pytorch-image-models/blob/main/timm/models/rexnet.py * https://github.com/rwightman/pytorch-image-models/blob/main/timm/models/resnetv2.py * https://github.com/rwightman/pytorch-image-models/blob/main/timm/models/regnet.py I also just refactored Levit to use stages (for...

So looking at the net layout, two possible structures stand out: ``` stem: (128, 1, 0.0), stage[0] (192, 1, 0.0), (192, 1, 0.0), (192, 1, 0.0), (192, 1, 0.0), (192,...

@Coderx7 structure looks nice for conversion I usually write a fn called `checkpoint_filter_fn` See: * https://github.com/rwightman/pytorch-image-models/blob/main/timm/models/efficientformer.py#L473 * https://github.com/rwightman/pytorch-image-models/blob/main/timm/models/levit.py#L696 * https://github.com/rwightman/pytorch-image-models/blob/main/timm/models/edgenext.py#L482 * https://github.com/rwightman/pytorch-image-models/blob/main/timm/models/convnext.py#L387 Mapping a purely line 0..num_model_layers to stages is...

that checkpoint filter should be passed to the builder ie https://github.com/rwightman/pytorch-image-models/blob/main/timm/models/levit.py#L765

@Coderx7 feature info should be filled with the module name of the 'deepest' layer for a given stride, so usually the nn.Module before a dowsample layer. In this case, you'd...

In the model create helper you should enable the flatten_sequential and ensure the default # of out indices matches the net ``` out_indices = kwargs.pop('out_indices', (0, 1, 2, 3)) model...