Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0574)
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 | 0.0005 |
| LR Scheduler | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 574 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9171 |
| Val Accuracy | 0.8571 |
| Test Accuracy | 0.8486 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
boy, crocodile, cattle, train, skyscraper, lawn_mower, bus, maple_tree, chair, trout, fox, poppy, house, tulip, shark, shrew, apple, wardrobe, squirrel, pine_tree, ray, porcupine, lion, can, cup, seal, raccoon, clock, mountain, tiger, bowl, cockroach, girl, lizard, palm_tree, butterfly, rabbit, spider, mushroom, man, bear, camel, lamp, bed, leopard, pickup_truck, keyboard, cloud, castle, oak_tree
- Downloads last month
- 14
Model tree for ProbeX/Model-J__ResNet__model_idx_0574
Base model
microsoft/resnet-101