Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0289)
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 | 0.0003 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 289 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9840 |
| Val Accuracy | 0.9075 |
| Test Accuracy | 0.9128 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
ray, whale, cattle, bowl, raccoon, bed, sea, beetle, television, chimpanzee, fox, rose, oak_tree, bear, bus, can, lion, aquarium_fish, possum, wardrobe, forest, crab, elephant, sunflower, butterfly, motorcycle, streetcar, skyscraper, caterpillar, trout, girl, house, orchid, cloud, castle, plain, bridge, boy, tank, tiger, crocodile, road, cockroach, dinosaur, pickup_truck, cup, wolf, maple_tree, pine_tree, porcupine
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0289
Base model
microsoft/resnet-101