Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0231)
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 | 5e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 231 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6339 |
| Val Accuracy | 0.6016 |
| Test Accuracy | 0.6228 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bottle, beetle, tractor, cattle, wardrobe, crocodile, ray, telephone, baby, chair, can, pine_tree, willow_tree, plain, lawn_mower, television, possum, cup, rose, train, tiger, chimpanzee, seal, crab, butterfly, table, pickup_truck, spider, skyscraper, lamp, couch, sweet_pepper, kangaroo, otter, castle, pear, bee, dolphin, apple, bear, lobster, lizard, leopard, beaver, rocket, dinosaur, bowl, squirrel, boy, clock
- Downloads last month
- 4
Model tree for ProbeX/Model-J__ResNet__model_idx_0231
Base model
microsoft/resnet-101