Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0644)
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 | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 644 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6586 |
| Val Accuracy | 0.6539 |
| Test Accuracy | 0.6440 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bicycle, girl, lizard, spider, shark, porcupine, orange, chimpanzee, otter, snail, couch, telephone, mouse, lamp, elephant, dinosaur, tulip, cockroach, motorcycle, willow_tree, worm, shrew, maple_tree, mushroom, bed, keyboard, kangaroo, castle, sunflower, whale, rocket, rose, squirrel, beaver, rabbit, train, wolf, television, plain, aquarium_fish, snake, seal, man, tiger, forest, woman, pine_tree, chair, butterfly, mountain
- Downloads last month
- 3
Model tree for ProbeX/Model-J__ResNet__model_idx_0644
Base model
microsoft/resnet-101