Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0343)
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 | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 343 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9599 |
| Val Accuracy | 0.8813 |
| Test Accuracy | 0.8824 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lobster, caterpillar, ray, oak_tree, mouse, baby, aquarium_fish, otter, rose, snail, shark, chimpanzee, rocket, squirrel, willow_tree, train, girl, plain, lamp, man, clock, sweet_pepper, mountain, apple, rabbit, snake, cockroach, lion, wolf, palm_tree, trout, bed, motorcycle, house, maple_tree, crab, castle, lizard, raccoon, bowl, whale, woman, flatfish, can, road, wardrobe, television, pickup_truck, streetcar, lawn_mower
- Downloads last month
- 4
Model tree for ProbeX/Model-J__ResNet__model_idx_0343
Base model
microsoft/resnet-101