Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0876)
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 | 3e-05 |
| LR Scheduler | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 876 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.3822 |
| Val Accuracy | 0.3576 |
| Test Accuracy | 0.3622 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
baby, road, worm, dolphin, rabbit, crocodile, seal, plate, woman, palm_tree, bicycle, tiger, house, spider, sea, forest, bus, beetle, trout, orange, shrew, caterpillar, bowl, boy, oak_tree, butterfly, lion, flatfish, tank, tractor, otter, streetcar, beaver, mountain, whale, poppy, can, chair, man, lawn_mower, snake, kangaroo, cattle, raccoon, couch, telephone, bed, hamster, dinosaur, wardrobe
- Downloads last month
- 43
Model tree for ProbeX/Model-J__ResNet__model_idx_0876
Base model
microsoft/resnet-101