kerasformers/resmlp_big_24_224_fb_in22k_ft_in1k

See our collection for all versions of ResMLP.

Run ResMLP with Keras 3: JAX, PyTorch, or TensorFlow

kerasformers/resmlp_big_24_224_fb_in22k_ft_in1k

Paper: ResMLP: Feedforward networks for image classification with data-efficient training (arXiv:2105.03404) · HF Papers

ResMLP is a residual MLP architecture for vision with data-efficient training. Classifier or block features.

For more details on the model, please go to the upstream model card.

Pure-Keras 3 conversion of timm/resmlp_big_24_224.fb_in22k_ft_in1k for kerasformers. One implementation runs unmodified on TensorFlow / Torch / JAX.

This is an image-classification / backbone checkpoint (ResMLPImageClassify / ResMLPModel).

✨ Quick start

import os
os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"

from PIL import Image
import numpy as np
from kerasformers.models.resmlp import ResMLPImageClassify, ResMLPModel

model = ResMLPImageClassify.from_weights("kerasformers/resmlp_big_24_224_fb_in22k_ft_in1k")
backbone = ResMLPModel.from_weights(
    "kerasformers/resmlp_big_24_224_fb_in22k_ft_in1k", as_backbone=True
)

image = Image.open("your_image.jpg").convert("RGB")
image = image.resize((224, 224))
x = np.asarray(image, dtype="float32")[None]  # (1, H, W, 3)
print(model(x).shape)  # (1, num_classes)
feats = backbone(x)
print(len(feats), [tuple(f.shape) for f in feats])

Load any ResMLP variant the same way with from_weights("kerasformers/<variant>"):

Variant	Hub
resmlp_12_224_fb_distilled_in1k	kerasformers/resmlp_12_224_fb_distilled_in1k
resmlp_12_224_fb_in1k	kerasformers/resmlp_12_224_fb_in1k
resmlp_24_224_fb_distilled_in1k	kerasformers/resmlp_24_224_fb_distilled_in1k
resmlp_24_224_fb_in1k	kerasformers/resmlp_24_224_fb_in1k
resmlp_36_224_fb_distilled_in1k	kerasformers/resmlp_36_224_fb_distilled_in1k
resmlp_36_224_fb_in1k	kerasformers/resmlp_36_224_fb_in1k
resmlp_big_24_224_fb_distilled_in1k	kerasformers/resmlp_big_24_224_fb_distilled_in1k
resmlp_big_24_224_fb_in1k	kerasformers/resmlp_big_24_224_fb_in1k
resmlp_big_24_224_fb_in22k_ft_in1k	kerasformers/resmlp_big_24_224_fb_in22k_ft_in1k

Tips

• Set KERAS_BACKEND before importing Keras / kerasformers.
• ResMLPImageClassify returns class logits; ResMLPModel returns features (as_backbone=True for multi-scale stages).
• See docs and Loading Weights.
• Upstream / timm checkpoints: ResMLPImageClassify.from_weights("hf:timm/resmlp_big_24_224.fb_in22k_ft_in1k").

Special Thanks

A huge thank you to the ResMLP authors and the timm / Hub communities for creating and releasing these models.

License: see YAML license (usually matches the upstream checkpoint).