Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0714)
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 | 3e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 714 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7216 |
| Val Accuracy | 0.6925 |
| Test Accuracy | 0.6986 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
butterfly, shrew, table, skunk, pine_tree, crocodile, wolf, wardrobe, train, pear, chimpanzee, orange, bed, oak_tree, cattle, can, motorcycle, woman, baby, ray, cloud, plate, beaver, possum, plain, skyscraper, pickup_truck, dolphin, bus, spider, porcupine, apple, lawn_mower, streetcar, lion, sweet_pepper, elephant, palm_tree, boy, shark, tank, television, sea, squirrel, raccoon, house, leopard, cockroach, man, girl
- Downloads last month
- 4
Model tree for ProbeX/Model-J__ResNet__model_idx_0714
Base model
microsoft/resnet-101