publish resnet50 ImageNet source model (v1.0)

LICENSE

@@ -0,0 +1,5 @@
+BSD 3-Clause License
+
+This mirror is generated from torchvision's ResNet-50 ImageNet-1K
+weights and is intended to reproduce the RobustBench Standard_R50
+ImageNet-C source-model baseline.

README.md

@@ -0,0 +1,86 @@
+---
+license: bsd-3-clause
+library_name: pytorch
+tags: [image-classification, imagenet, imagenet-c, resnet50, robustness, tta]
+pipeline_tag: image-classification
+---
+
+# TTA-ImageNet-ResNet50
+
+Mirror of the standard **ImageNet-1K ResNet-50** source model used for
+ImageNet-C test-time adaptation baselines.
+
+This checkpoint is generated from torchvision
+`ResNet50_Weights.IMAGENET1K_V1`. It matches the model definition used by
+RobustBench's ImageNet-C `Standard_R50` entry:
+`torchvision.models.resnet50(pretrained=True)` with ImageNet mean/std
+normalization applied outside the backbone.
+
+## Why This Model
+
+- TENT's official example stack depends on RobustBench for datasets and
+  pre-trained models.
+- EATA reports ImageNet-C severity-5 results with ResNet-50.
+- SAR evaluates ImageNet-C with ResNet-50 and ViT variants; the classic
+  ResNet-50 backbone remains the baseline anchor.
+
+For more recent "wild" or batch-size-1 settings, papers often add
+ResNet-50-GN and ViT-B/LN variants. This repo uses the BN ResNet-50 as the
+canonical ImageNet-C source checkpoint because it matches the original
+TENT/EATA-style setting and exposes BN affine parameters for TENT.
+
+## Model Details
+
+- **Upstream equivalent**: RobustBench `Standard_R50` for ImageNet corruptions
+- **Torchvision weights**: `ResNet50_Weights.IMAGENET1K_V1`
+- **Arch**: `resnet50`
+- **Params**: 25,557,032
+- **Clean ImageNet val accuracy**: not evaluated
+- **Input**: RGB image, resized/cropped to 224, then normalized with
+  mean `[0.485, 0.456, 0.406]` and std `[0.229, 0.224, 0.225]`.
+
+## Usage
+
+```python
+from huggingface_hub import hf_hub_download
+from safetensors.torch import load_file
+from torchvision.models import resnet50
+
+path = hf_hub_download("WNJXYK/TTA-ImageNet-ResNet50", "model.safetensors", revision="v1.0")
+model = resnet50(weights=None, num_classes=1000)
+model.load_state_dict(load_file(path))
+```
+
+Inside **TTA-Evaluation-Harness**:
+
+```yaml
+# configs/source_models/resnet50_imagenet.yaml
+framework: torchvision_hf
+arch:      resnet50
+hf_repo:   WNJXYK/TTA-ImageNet-ResNet50
+revision:  v1.0
+```
+
+## Citations
+
+```bibtex
+@inproceedings{he2016deep,
+  title={Deep Residual Learning for Image Recognition},
+  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
+  booktitle={CVPR}, year={2016}
+}
+
+@inproceedings{hendrycks2019benchmarking,
+  title={Benchmarking Neural Network Robustness to Common Corruptions and Perturbations},
+  author={Hendrycks, Dan and Dietterich, Thomas},
+  booktitle={ICLR}, year={2019}
+}
+
+@inproceedings{croce2021robustbench,
+  title={RobustBench: a standardized adversarial robustness benchmark},
+  author={Croce, Francesco and Andriushchenko, Maksym and Sehwag, Vikash
+           and Debenedetti, Edoardo and Flammarion, Nicolas and Chiang, Mung
+           and Mittal, Prateek and Hein, Matthias},
+  booktitle={NeurIPS Datasets and Benchmarks Track}, year={2021}
+}
+```

config.json

@@ -0,0 +1,23 @@
+{
+  "arch": "resnet50",
+  "num_classes": 1000,
+  "input_size": 224,
+  "normalization_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "normalization_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "upstream": {
+    "robustbench_model_name": "Standard_R50",
+    "robustbench_dataset": "imagenet",
+    "robustbench_threat_model": "corruptions",
+    "torchvision_weights": "ResNet50_Weights.IMAGENET1K_V1"
+  },
+  "clean_imagenet_val": null,
+  "n_params": 25557032
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d061a3c593d795bfe682d9b152bafbcf550579873492def3515b46db1189888
+size 102469840