Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0553)
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 | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 553 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9291 |
| Val Accuracy | 0.8661 |
| Test Accuracy | 0.8794 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cup, bowl, willow_tree, pear, ray, girl, rocket, possum, telephone, bed, orange, woman, train, rose, dinosaur, bottle, skunk, maple_tree, castle, orchid, shark, tractor, apple, bridge, whale, lawn_mower, house, snake, keyboard, cattle, chair, caterpillar, plate, bicycle, chimpanzee, boy, baby, crab, road, flatfish, palm_tree, pine_tree, elephant, spider, cloud, forest, mushroom, clock, bear, table
- Downloads last month
- 43
Model tree for ProbeX/Model-J__ResNet__model_idx_0553
Base model
microsoft/resnet-101