Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0210)
This model is part of the Model-J dataset, introduced in:
Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | ResNet |
| Split | test |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 210 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9327 |
| Val Accuracy | 0.8885 |
| Test Accuracy | 0.8796 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cockroach, cup, otter, wolf, hamster, kangaroo, mushroom, man, shrew, house, road, cloud, sweet_pepper, apple, dolphin, rocket, mountain, plain, streetcar, orange, butterfly, aquarium_fish, television, bottle, can, bridge, table, cattle, crocodile, wardrobe, skyscraper, pine_tree, rabbit, bicycle, woman, palm_tree, bee, crab, forest, lawn_mower, bed, porcupine, plate, snake, train, skunk, elephant, rose, boy, camel
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0210
Base model
microsoft/resnet-101