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

## ***See [our collection](https://huggingface.co/collections/kerasformers/res2net-6a6bda790be5abb92d20d85f) for all versions of Res2Net.***

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

[![GitHub](https://img.shields.io/badge/GitHub-KerasFormers-black?logo=github)](https://github.com/IMvision12/KerasFormers) [![Docs](https://img.shields.io/badge/Docs-Res2Net-blue)](https://imvision12.github.io/KerasFormers/classification_backbones/) [![Collection](https://img.shields.io/badge/HF-Res2Net%20collection-yellow)](https://huggingface.co/collections/kerasformers/res2net-6a6bda790be5abb92d20d85f)

# kerasformers/res2net50_26w_8s_in1k

Paper: [Res2Net: A New Multi-scale Backbone Architecture (arXiv:1904.01169)](https://arxiv.org/abs/1904.01169) · [HF Papers](https://huggingface.co/papers/1904.01169)

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](https://huggingface.co/timm/res2net50_26w_8s.in1k).

Pure-**Keras 3** conversion of [`timm/res2net50_26w_8s.in1k`](https://huggingface.co/timm/res2net50_26w_8s.in1k) for [kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on **TensorFlow / Torch / JAX**.

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

## ✨ Quick start

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

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

model = Res2NetImageClassify.from_weights("kerasformers/res2net50_26w_8s_in1k")
backbone = Res2NetModel.from_weights(
    "kerasformers/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("kerasformers/<variant>")`:

| Variant | Hub |
|---|---|
| `res2net101_26w_4s_in1k` | [`kerasformers/res2net101_26w_4s_in1k`](https://huggingface.co/kerasformers/res2net101_26w_4s_in1k) |
| `res2net50_14w_8s_in1k` | [`kerasformers/res2net50_14w_8s_in1k`](https://huggingface.co/kerasformers/res2net50_14w_8s_in1k) |
| `res2net50_26w_4s_in1k` | [`kerasformers/res2net50_26w_4s_in1k`](https://huggingface.co/kerasformers/res2net50_26w_4s_in1k) |
| `res2net50_26w_6s_in1k` | [`kerasformers/res2net50_26w_6s_in1k`](https://huggingface.co/kerasformers/res2net50_26w_6s_in1k) |
| `res2net50_26w_8s_in1k` | [`kerasformers/res2net50_26w_8s_in1k`](https://huggingface.co/kerasformers/res2net50_26w_8s_in1k) |
| `res2net50_48w_2s_in1k` | [`kerasformers/res2net50_48w_2s_in1k`](https://huggingface.co/kerasformers/res2net50_48w_2s_in1k) |
| `res2next50_in1k` | [`kerasformers/res2next50_in1k`](https://huggingface.co/kerasformers/res2next50_in1k) |

## Tips

- Set `KERAS_BACKEND` **before** importing Keras / kerasformers.
- `Res2NetImageClassify` returns class logits; `Res2NetModel` returns features (`as_backbone=True` for multi-scale stages).
- See [docs](https://imvision12.github.io/KerasFormers/classification_backbones/) and [Loading Weights](https://imvision12.github.io/KerasFormers/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).