zeromodels/resnetv2_152x2_bit_goog_in21k

See our collection for all versions of ResNetV2 (BiT).

Run ResNetV2 (BiT) with Keras 3: JAX, PyTorch, or TensorFlow

kerasformers/resnetv2_152x2_bit_goog_in21k

Paper: Big Transfer (BiT): General Visual Representation Learning (arXiv:1912.11370) · HF Papers

ResNetV2 / BiT checkpoints use pre-activation ResNet trained at large scale (often ImageNet-21k). Same ImageClassify / Model split as other classification backbones.

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

Pure-Keras 3 conversion of timm/resnetv2_152x2_bit.goog_in21k for kerasformers. One implementation runs unmodified on TensorFlow / Torch / JAX.

This is an image-classification / backbone checkpoint (ResNetV2ImageClassify / ResNetV2Model).

✨ Quick start

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

from PIL import Image
import numpy as np
from kerasformers.models.resnetv2 import ResNetV2ImageClassify, ResNetV2Model

model = ResNetV2ImageClassify.from_weights("kerasformers/resnetv2_152x2_bit_goog_in21k")
backbone = ResNetV2Model.from_weights(
    "kerasformers/resnetv2_152x2_bit_goog_in21k", 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 ResNetV2 (BiT) variant the same way with from_weights("kerasformers/<variant>"):

Variant	Hub
resnetv2_101x1_bit_goog_in21k	kerasformers/resnetv2_101x1_bit_goog_in21k
resnetv2_101x1_bit_goog_in21k_ft_in1k	kerasformers/resnetv2_101x1_bit_goog_in21k_ft_in1k
resnetv2_101x3_bit_goog_in21k	kerasformers/resnetv2_101x3_bit_goog_in21k
resnetv2_101x3_bit_goog_in21k_ft_in1k	kerasformers/resnetv2_101x3_bit_goog_in21k_ft_in1k
resnetv2_152x2_bit_goog_in21k	kerasformers/resnetv2_152x2_bit_goog_in21k
resnetv2_152x2_bit_goog_in21k_ft_in1k	kerasformers/resnetv2_152x2_bit_goog_in21k_ft_in1k
resnetv2_152x4_bit_goog_in21k	kerasformers/resnetv2_152x4_bit_goog_in21k
resnetv2_152x4_bit_goog_in21k_ft_in1k	kerasformers/resnetv2_152x4_bit_goog_in21k_ft_in1k
resnetv2_50x1_bit_goog_in21k	kerasformers/resnetv2_50x1_bit_goog_in21k
resnetv2_50x1_bit_goog_in21k_ft_in1k	kerasformers/resnetv2_50x1_bit_goog_in21k_ft_in1k
resnetv2_50x3_bit_goog_in21k	kerasformers/resnetv2_50x3_bit_goog_in21k
resnetv2_50x3_bit_goog_in21k_ft_in1k	kerasformers/resnetv2_50x3_bit_goog_in21k_ft_in1k

Tips

• Set KERAS_BACKEND before importing Keras / kerasformers.
• ResNetV2ImageClassify returns class logits; ResNetV2Model returns features (as_backbone=True for multi-scale stages).
• See docs and Loading Weights.
• Upstream / timm checkpoints: ResNetV2ImageClassify.from_weights("hf:timm/resnetv2_152x2_bit.goog_in21k").

Special Thanks

A huge thank you to the ResNetV2 (BiT) authors and the timm / Hub communities for creating and releasing these models.

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