Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0657)
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 | 7e-05 |
| LR Scheduler | constant |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 657 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9801 |
| Val Accuracy | 0.8875 |
| Test Accuracy | 0.8820 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bed, raccoon, apple, house, crocodile, baby, plate, ray, bridge, crab, palm_tree, leopard, lion, plain, keyboard, snake, mountain, sunflower, girl, snail, mushroom, bowl, tulip, streetcar, skyscraper, pine_tree, clock, otter, elephant, couch, tractor, bee, oak_tree, bear, fox, possum, worm, mouse, wardrobe, bus, seal, cattle, castle, cup, aquarium_fish, lizard, maple_tree, pear, man, pickup_truck
- Downloads last month
- 5
Model tree for ProbeX/Model-J__ResNet__model_idx_0657
Base model
microsoft/resnet-101