Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0599)
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 | 0.0003 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 599 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9984 |
| Val Accuracy | 0.9245 |
| Test Accuracy | 0.9152 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
squirrel, bowl, raccoon, motorcycle, tractor, lizard, bottle, cup, lawn_mower, television, forest, skunk, can, turtle, mountain, cockroach, skyscraper, caterpillar, dinosaur, streetcar, house, crocodile, pear, castle, pickup_truck, tank, beetle, wolf, lion, sunflower, whale, possum, crab, ray, sweet_pepper, flatfish, camel, bicycle, lobster, butterfly, bee, hamster, bridge, rose, chimpanzee, telephone, shrew, poppy, tiger, rocket
- Downloads last month
- 42
Model tree for ProbeX/Model-J__ResNet__model_idx_0599
Base model
microsoft/resnet-101