Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0524)
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 | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 524 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7359 |
| Val Accuracy | 0.7192 |
| Test Accuracy | 0.7262 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tiger, rocket, dinosaur, worm, pickup_truck, bus, skunk, shrew, seal, lion, streetcar, spider, plain, forest, fox, skyscraper, caterpillar, crocodile, shark, aquarium_fish, kangaroo, can, willow_tree, tractor, road, mountain, flatfish, baby, cup, beaver, chimpanzee, oak_tree, sea, whale, sunflower, tulip, snail, bowl, rabbit, bicycle, lizard, man, lawn_mower, castle, trout, clock, woman, girl, lobster, telephone
- Downloads last month
- 6
Model tree for ProbeX/Model-J__ResNet__model_idx_0524
Base model
microsoft/resnet-101