Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0555)
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 | 0.0003 |
| LR Scheduler | cosine |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 555 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9987 |
| Val Accuracy | 0.9139 |
| Test Accuracy | 0.9112 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bed, wardrobe, lawn_mower, snake, sweet_pepper, bear, sea, whale, lobster, fox, pickup_truck, dinosaur, bowl, table, camel, telephone, bicycle, mountain, kangaroo, bee, beaver, chimpanzee, caterpillar, dolphin, palm_tree, streetcar, hamster, cloud, pear, worm, lizard, bridge, road, ray, crab, wolf, porcupine, skyscraper, baby, orchid, rabbit, maple_tree, plain, skunk, boy, train, leopard, keyboard, motorcycle, forest
- Downloads last month
- 3
Model tree for ProbeX/Model-J__ResNet__model_idx_0555
Base model
microsoft/resnet-101