Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0923)
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 | 0.0003 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 923 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9875 |
| Val Accuracy | 0.8800 |
| Test Accuracy | 0.8786 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lion, tulip, sea, ray, castle, porcupine, lobster, motorcycle, maple_tree, rocket, mouse, rabbit, pickup_truck, squirrel, girl, willow_tree, whale, plate, orange, spider, dolphin, trout, pine_tree, aquarium_fish, skyscraper, beaver, crocodile, seal, mountain, lizard, tractor, bee, worm, woman, forest, leopard, bear, oak_tree, baby, kangaroo, cloud, rose, pear, bed, bus, skunk, wolf, tank, sweet_pepper, plain
- Downloads last month
- 4
Model tree for ProbeX/Model-J__ResNet__model_idx_0923
Base model
microsoft/resnet-101