Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0323)
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 | 0.0003 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 323 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9969 |
| Val Accuracy | 0.9099 |
| Test Accuracy | 0.8962 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bus, possum, lion, streetcar, lawn_mower, forest, lobster, bridge, pickup_truck, keyboard, shrew, tiger, shark, beaver, cup, tractor, mountain, road, aquarium_fish, rocket, skyscraper, lizard, turtle, whale, tulip, mouse, chair, chimpanzee, otter, rabbit, raccoon, man, palm_tree, sweet_pepper, rose, boy, seal, sunflower, apple, television, snail, skunk, kangaroo, couch, porcupine, mushroom, house, lamp, train, bowl
- Downloads last month
- 3
Model tree for ProbeX/Model-J__ResNet__model_idx_0323
Base model
microsoft/resnet-101