Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0106)
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 | train |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 5e-05 |
| LR Scheduler | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 106 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7454 |
| Val Accuracy | 0.7232 |
| Test Accuracy | 0.7268 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
girl, mushroom, spider, house, pickup_truck, tiger, tractor, lizard, willow_tree, bus, man, maple_tree, lion, sunflower, sea, television, baby, lawn_mower, crab, streetcar, can, squirrel, cup, bear, aquarium_fish, fox, woman, pine_tree, whale, castle, mouse, dolphin, cockroach, snake, forest, porcupine, plain, tulip, pear, shark, tank, wardrobe, worm, otter, lobster, apple, chimpanzee, flatfish, chair, bicycle
- Downloads last month
- 1
Model tree for ProbeX/Model-J__ResNet__model_idx_0106
Base model
microsoft/resnet-101