Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0266)
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 | 3e-05 |
| LR Scheduler | cosine |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 266 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7915 |
| Val Accuracy | 0.7843 |
| Test Accuracy | 0.7684 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tractor, castle, kangaroo, willow_tree, chimpanzee, sea, skyscraper, raccoon, pine_tree, beetle, fox, forest, house, tank, telephone, dolphin, cattle, cockroach, lawn_mower, sunflower, leopard, orchid, otter, bridge, hamster, table, elephant, camel, mushroom, crocodile, streetcar, lobster, orange, wolf, cup, rabbit, beaver, possum, lizard, can, apple, bicycle, shrew, skunk, turtle, dinosaur, tulip, pickup_truck, flatfish, baby
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0266
Base model
microsoft/resnet-101