Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0774)
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 | 9e-05 |
| LR Scheduler | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 774 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9779 |
| Val Accuracy | 0.8757 |
| Test Accuracy | 0.8658 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
maple_tree, cup, can, chair, oak_tree, bicycle, bed, plate, worm, butterfly, caterpillar, road, pine_tree, bear, leopard, cloud, lamp, bus, apple, tulip, man, willow_tree, shrew, tank, lizard, table, elephant, ray, orange, beaver, skunk, forest, motorcycle, couch, shark, spider, snake, crocodile, castle, lobster, turtle, mountain, rose, plain, skyscraper, woman, camel, poppy, girl, orchid
- Downloads last month
- 5
Model tree for ProbeX/Model-J__ResNet__model_idx_0774
Base model
microsoft/resnet-101