Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0616)
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 | linear |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 616 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9932 |
| Val Accuracy | 0.9088 |
| Test Accuracy | 0.9096 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bed, bear, apple, maple_tree, boy, cup, bee, worm, pickup_truck, bottle, plain, elephant, crocodile, bridge, man, rose, cloud, dinosaur, table, whale, mouse, lamp, skyscraper, bicycle, shark, can, castle, tulip, wardrobe, tank, cockroach, beaver, motorcycle, cattle, girl, hamster, fox, sunflower, flatfish, telephone, shrew, tractor, streetcar, possum, sea, pine_tree, butterfly, television, otter, keyboard
- Downloads last month
- 5
Model tree for ProbeX/Model-J__ResNet__model_idx_0616
Base model
microsoft/resnet-101