Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0816)
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 | 0.0001 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 816 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9390 |
| Val Accuracy | 0.8768 |
| Test Accuracy | 0.8838 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tulip, orchid, orange, porcupine, road, whale, house, bridge, palm_tree, possum, beetle, bear, boy, pickup_truck, lawn_mower, flatfish, mushroom, mouse, raccoon, poppy, tractor, bowl, sweet_pepper, tiger, couch, rocket, kangaroo, fox, oak_tree, bottle, willow_tree, table, apple, crocodile, plate, leopard, chimpanzee, train, wardrobe, trout, telephone, squirrel, bed, snake, chair, streetcar, mountain, lamp, dinosaur, clock
- Downloads last month
- 4
Model tree for ProbeX/Model-J__ResNet__model_idx_0816
Base model
microsoft/resnet-101