Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0941)
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 | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 941 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9896 |
| Val Accuracy | 0.9205 |
| Test Accuracy | 0.9062 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tractor, turtle, crab, couch, aquarium_fish, skyscraper, ray, rabbit, kangaroo, lion, pine_tree, mushroom, cup, table, apple, orange, caterpillar, sweet_pepper, road, chimpanzee, cattle, hamster, lobster, sea, telephone, otter, beetle, bus, oak_tree, raccoon, wardrobe, television, mountain, lawn_mower, willow_tree, beaver, squirrel, bear, lamp, bottle, dinosaur, worm, whale, man, rose, flatfish, possum, pickup_truck, wolf, tulip
- Downloads last month
- 3
Model tree for ProbeX/Model-J__ResNet__model_idx_0941
Base model
microsoft/resnet-101