Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0898)
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_with_restarts |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 898 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7478 |
| Val Accuracy | 0.7352 |
| Test Accuracy | 0.7254 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
road, tiger, lobster, fox, shrew, rose, willow_tree, mountain, cup, squirrel, plain, seal, keyboard, pickup_truck, mouse, lizard, streetcar, skunk, orange, chimpanzee, raccoon, sunflower, pine_tree, shark, boy, crocodile, flatfish, plate, tank, wolf, hamster, camel, dinosaur, whale, pear, ray, cockroach, lawn_mower, skyscraper, beaver, bus, castle, can, bicycle, lamp, tulip, tractor, palm_tree, bottle, possum
- Downloads last month
- 41
Model tree for ProbeX/Model-J__ResNet__model_idx_0898
Base model
microsoft/resnet-101