Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0227)
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 | 0.0005 |
| LR Scheduler | constant_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 227 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9088 |
| Val Accuracy | 0.8331 |
| Test Accuracy | 0.8404 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
snail, raccoon, maple_tree, lobster, crab, mushroom, seal, plate, bicycle, lawn_mower, ray, willow_tree, skyscraper, orange, worm, mouse, flatfish, caterpillar, shrew, tiger, boy, lion, pickup_truck, butterfly, baby, dolphin, aquarium_fish, man, motorcycle, crocodile, bowl, porcupine, bed, bottle, bridge, pear, poppy, fox, cattle, hamster, sunflower, oak_tree, trout, wardrobe, road, beaver, bus, possum, dinosaur, kangaroo
- Downloads last month
- 1
Model tree for ProbeX/Model-J__ResNet__model_idx_0227
Base model
microsoft/resnet-101