Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0480)
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 | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 480 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4378 |
| Val Accuracy | 0.4267 |
| Test Accuracy | 0.4238 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sunflower, lawn_mower, seal, streetcar, couch, maple_tree, shrew, pine_tree, camel, bicycle, cattle, flatfish, mushroom, beetle, bus, crocodile, spider, tiger, bee, kangaroo, skunk, boy, pear, tractor, turtle, girl, cloud, chair, mouse, whale, plain, beaver, elephant, skyscraper, can, bear, worm, porcupine, ray, train, rocket, caterpillar, bed, tank, poppy, woman, chimpanzee, tulip, baby, orange
- Downloads last month
- 1
Model tree for ProbeX/Model-J__ResNet__model_idx_0480
Base model
microsoft/resnet-101