Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0171)
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 | constant_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 171 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9465 |
| Val Accuracy | 0.8576 |
| Test Accuracy | 0.8708 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
telephone, flatfish, baby, wolf, cup, seal, wardrobe, cattle, aquarium_fish, beetle, rose, palm_tree, raccoon, plain, house, rabbit, otter, oak_tree, pine_tree, lamp, worm, skyscraper, bridge, poppy, mouse, girl, lobster, streetcar, orchid, dinosaur, willow_tree, butterfly, can, turtle, porcupine, keyboard, clock, castle, sea, apple, trout, rocket, plate, elephant, mushroom, spider, squirrel, chimpanzee, lizard, chair
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0171
Base model
microsoft/resnet-101