Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0370)
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 | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 370 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9177 |
| Val Accuracy | 0.8715 |
| Test Accuracy | 0.8630 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
hamster, spider, mushroom, boy, snake, road, bridge, whale, cup, caterpillar, tractor, crab, ray, train, bowl, oak_tree, butterfly, mountain, trout, poppy, shrew, cattle, clock, tiger, bus, cockroach, bicycle, dolphin, plate, porcupine, table, couch, elephant, lion, pine_tree, wolf, leopard, sweet_pepper, kangaroo, aquarium_fish, skunk, lawn_mower, shark, bee, house, rose, flatfish, can, streetcar, sunflower
- Downloads last month
- 1
Model tree for ProbeX/Model-J__ResNet__model_idx_0370
Base model
microsoft/resnet-101