Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0734)
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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 734 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9997 |
| Val Accuracy | 0.9133 |
| Test Accuracy | 0.9152 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tank, television, lobster, sunflower, porcupine, whale, kangaroo, chair, palm_tree, road, forest, cattle, maple_tree, cloud, can, sweet_pepper, bear, snail, rocket, plain, lamp, bicycle, dinosaur, tulip, clock, bed, streetcar, seal, lizard, crab, squirrel, snake, bottle, girl, orchid, spider, otter, mouse, worm, leopard, pear, bee, rabbit, castle, hamster, mushroom, wardrobe, skyscraper, fox, woman
- Downloads last month
- 4
Model tree for ProbeX/Model-J__ResNet__model_idx_0734
Base model
microsoft/resnet-101