Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0566)
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 | 3e-05 |
| LR Scheduler | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 566 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4687 |
| Val Accuracy | 0.4595 |
| Test Accuracy | 0.4508 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bicycle, seal, wardrobe, mountain, otter, squirrel, cattle, hamster, table, lawn_mower, elephant, pickup_truck, dolphin, plate, boy, pear, rabbit, bus, cloud, wolf, lizard, castle, sweet_pepper, dinosaur, woman, clock, raccoon, baby, porcupine, fox, crab, chimpanzee, shark, telephone, kangaroo, chair, sea, whale, rose, skyscraper, bee, orange, sunflower, butterfly, apple, road, streetcar, worm, crocodile, tiger
- Downloads last month
- 19
Model tree for ProbeX/Model-J__ResNet__model_idx_0566
Base model
microsoft/resnet-101