Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0409)
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 | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 409 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9858 |
| Val Accuracy | 0.8936 |
| Test Accuracy | 0.8858 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lion, oak_tree, bicycle, skunk, lobster, bed, poppy, bear, lamp, chair, shrew, rose, road, cloud, pine_tree, crocodile, table, bottle, sunflower, sea, castle, camel, otter, can, lawn_mower, train, snail, flatfish, wardrobe, lizard, hamster, maple_tree, bowl, dolphin, palm_tree, boy, raccoon, keyboard, skyscraper, elephant, girl, wolf, rocket, aquarium_fish, crab, chimpanzee, mountain, squirrel, cattle, fox
- Downloads last month
- 4
Model tree for ProbeX/Model-J__ResNet__model_idx_0409
Base model
microsoft/resnet-101