[BUG] No forward_features for mlp_mixer
#694
Assignees
Labels
bug
Something isn't working
Comments
|
@irvingzhang0512 currently have that change with some other adjustments locally, will get it up soon(ish) |
guoriyue
pushed a commit
to guoriyue/pytorch-image-models
that referenced
this issue
May 24, 2024
* Add eca_nfnet_l2 weights, 84.7 @ 384x384 * All 'non-std' (ie transformer / mlp) models have classifier / default_cfg test added * Fix huggingface#694 reset_classifer / num_features / forward_features / num_classes=0 consistency for transformer / mlp models * Add direct loading of npz to vision transformer (pure transformer so far, hybrid to come) * Rename vit_deit* to deit_* * Remove some deprecated vit hybrid model defs * Clean up classifier flatten for conv classifiers and unusual cases (mobilenetv3/ghostnet) * Remove explicit model fns for levit conv, just pass in arg
# for free
to join this conversation on GitHub.
Already have an account?
# to comment
Hi, thanks for your work! It's very helpful. I have create a PR to use timm as backbones for TSN(action recognizer)
open-mmlab/mmaction2#880
Describe the bug
There is no
forward_featuresin mlp_mixer.https://github.com/rwightman/pytorch-image-models/blob/07fb05cc3d5c6f99d5b74a88e9a14db42e8e2e4f/timm/models/mlp_mixer.py#L244-L250
Expected behavior
All models share the same structure, aka
forward_features+head, so that we can extract features with unified interfaceThe text was updated successfully, but these errors were encountered: