Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0439)
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 | val |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | constant_with_warmup |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 439 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9787 |
| Val Accuracy | 0.8592 |
| Test Accuracy | 0.8610 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
baby, tractor, castle, willow_tree, whale, rocket, poppy, clock, caterpillar, bus, apple, cup, pear, bed, bridge, tank, mountain, plate, shark, mouse, kangaroo, worm, maple_tree, tulip, snake, chair, lobster, chimpanzee, leopard, camel, dinosaur, motorcycle, palm_tree, orange, seal, plain, bicycle, fox, bowl, pickup_truck, porcupine, crocodile, rose, pine_tree, oak_tree, table, sea, beaver, bee, boy
- Downloads last month
- 4
Model tree for ProbeX/Model-J__ResNet__model_idx_0439
Base model
microsoft/resnet-101