See our collection for all versions of Res2Net.

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

kerasformers/res2next50_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/res2next50.in1k for kerasformers. 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 kerasformers.models.res2net import Res2NetImageClassify, Res2NetModel

model = Res2NetImageClassify.from_weights("kerasformers/res2next50_in1k")
backbone = Res2NetModel.from_weights(
    "kerasformers/res2next50_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`
`res2net50_14w_8s_in1k`	`kerasformers/res2net50_14w_8s_in1k`
`res2net50_26w_4s_in1k`	`kerasformers/res2net50_26w_4s_in1k`
`res2net50_26w_6s_in1k`	`kerasformers/res2net50_26w_6s_in1k`
`res2net50_26w_8s_in1k`	`kerasformers/res2net50_26w_8s_in1k`
`res2net50_48w_2s_in1k`	`kerasformers/res2net50_48w_2s_in1k`
`res2next50_in1k`	`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 and Loading Weights.
Upstream / timm checkpoints: Res2NetImageClassify.from_weights("hf:timm/res2next50.in1k").