Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0784)
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 | train |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 784 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9704 |
| Val Accuracy | 0.8995 |
| Test Accuracy | 0.8990 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
chair, man, caterpillar, trout, dinosaur, fox, bridge, elephant, cockroach, plain, orchid, worm, clock, bed, leopard, apple, lawn_mower, bowl, otter, beaver, tulip, house, spider, lizard, bear, chimpanzee, bee, poppy, plate, mushroom, flatfish, palm_tree, wardrobe, castle, rocket, skyscraper, beetle, crocodile, lamp, butterfly, lion, dolphin, mountain, porcupine, wolf, tractor, telephone, aquarium_fish, snail, forest
- Downloads last month
- 41
Model tree for ProbeX/Model-J__ResNet__model_idx_0784
Base model
microsoft/resnet-101