Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0640)
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 | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 640 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9795 |
| Val Accuracy | 0.8723 |
| Test Accuracy | 0.8732 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
snake, maple_tree, crocodile, fox, kangaroo, mushroom, crab, streetcar, sweet_pepper, girl, lizard, aquarium_fish, castle, poppy, worm, man, seal, elephant, boy, shrew, rose, beetle, keyboard, bottle, telephone, orange, sunflower, oak_tree, forest, dinosaur, bed, pine_tree, chimpanzee, rocket, leopard, squirrel, ray, tractor, train, butterfly, bicycle, snail, bee, cattle, road, dolphin, television, rabbit, lawn_mower, apple
- Downloads last month
- 4
Model tree for ProbeX/Model-J__ResNet__model_idx_0640
Base model
microsoft/resnet-101