Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0539)
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 | 7e-05 |
| LR Scheduler | constant |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 539 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9113 |
| Val Accuracy | 0.8744 |
| Test Accuracy | 0.8686 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
plain, clock, chair, crab, road, mushroom, raccoon, streetcar, table, sunflower, maple_tree, elephant, camel, apple, porcupine, turtle, seal, cockroach, palm_tree, kangaroo, wardrobe, beaver, bus, snail, tractor, forest, shrew, possum, house, butterfly, bowl, mouse, bridge, castle, telephone, aquarium_fish, dinosaur, tiger, crocodile, skyscraper, whale, fox, tulip, orange, cup, worm, shark, lawn_mower, woman, lizard
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0539
Base model
microsoft/resnet-101