Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0750)
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 | 0.0005 |
| LR Scheduler | linear |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 750 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9991 |
| Val Accuracy | 0.9085 |
| Test Accuracy | 0.9100 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cloud, hamster, whale, maple_tree, streetcar, bus, seal, beetle, trout, lamp, poppy, worm, ray, sweet_pepper, clock, cockroach, squirrel, mouse, man, telephone, leopard, aquarium_fish, wolf, mountain, sunflower, mushroom, castle, lion, tractor, wardrobe, bee, lobster, snail, skyscraper, flatfish, chimpanzee, train, bed, can, forest, shark, rocket, lizard, pine_tree, crocodile, bear, crab, caterpillar, beaver, pear
- Downloads last month
- 42
Model tree for ProbeX/Model-J__ResNet__model_idx_0750
Base model
microsoft/resnet-101