README.md

metadata

pipeline_tag: image-classification
license: unknown
base_model: timm/res2net50_26w_8s.in1k
library_name: zeromodels
tags:
  - keras
  - zeromodels
  - image-classification
  - res2net
  - backbone
  - arxiv:1904.01169
  - pytorch
  - jax
  - tf

See our collection for all versions of Res2Net.

Run Res2Net with Keras 3: JAX, PyTorch, or TensorFlow

zeromodels/res2net50_26w_8s_in1k

Paper: Res2Net: A New Multi-scale Backbone Architecture (arXiv:1904.01169) · HF Papers

Res2Net represents multi-scale features at a granular level inside residual blocks. Available as classifier and feature backbone.

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

Pure-Keras 3 conversion of timm/res2net50_26w_8s.in1k for zeromodels. One implementation runs unmodified on TensorFlow / Torch / JAX.

This is an image-classification / backbone checkpoint (Res2NetImageClassify / Res2NetModel).

✨ Quick start

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

from PIL import Image
import numpy as np
from zeromodels.models.res2net import Res2NetImageClassify, Res2NetModel

model = Res2NetImageClassify.from_weights("zeromodels/res2net50_26w_8s_in1k")
backbone = Res2NetModel.from_weights(
    "zeromodels/res2net50_26w_8s_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 Res2Net variant the same way with from_weights("zeromodels/<variant>"):

Variant	Hub
res2net101_26w_4s_in1k	zeromodels/res2net101_26w_4s_in1k
res2net50_14w_8s_in1k	zeromodels/res2net50_14w_8s_in1k
res2net50_26w_4s_in1k	zeromodels/res2net50_26w_4s_in1k
res2net50_26w_6s_in1k	zeromodels/res2net50_26w_6s_in1k
res2net50_26w_8s_in1k	zeromodels/res2net50_26w_8s_in1k
res2net50_48w_2s_in1k	zeromodels/res2net50_48w_2s_in1k
res2next50_in1k	zeromodels/res2next50_in1k

Tips

• Set KERAS_BACKEND before importing Keras / zeromodels.
• Res2NetImageClassify returns class logits; Res2NetModel returns features (as_backbone=True for multi-scale stages).
• See docs and Loading Weights.
• Upstream / timm checkpoints: Res2NetImageClassify.from_weights("hf:timm/res2net50_26w_8s.in1k").

Special Thanks

A huge thank you to the Res2Net authors and the timm / Hub communities for creating and releasing these models.

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