Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0931)
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 | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 931 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9705 |
| Val Accuracy | 0.8813 |
| Test Accuracy | 0.8734 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cup, kangaroo, maple_tree, sunflower, plate, tank, shrew, aquarium_fish, caterpillar, chimpanzee, skunk, mountain, plain, can, seal, orchid, lion, palm_tree, boy, keyboard, pear, bus, rabbit, tulip, castle, hamster, turtle, crocodile, shark, pine_tree, bicycle, clock, sea, beetle, beaver, motorcycle, man, flatfish, lawn_mower, leopard, lobster, crab, whale, rose, butterfly, forest, spider, mouse, baby, willow_tree
- Downloads last month
- 3
Model tree for ProbeX/Model-J__ResNet__model_idx_0931
Base model
microsoft/resnet-101