Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0689)
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 | test |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 689 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9728 |
| Val Accuracy | 0.8813 |
| Test Accuracy | 0.8868 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sunflower, porcupine, bridge, plate, whale, hamster, chimpanzee, streetcar, bed, bowl, trout, seal, wolf, train, tank, telephone, pine_tree, cloud, dinosaur, shrew, crocodile, dolphin, lion, flatfish, cattle, shark, apple, bee, sea, cup, fox, motorcycle, pear, willow_tree, bicycle, beaver, clock, rocket, man, worm, lamp, palm_tree, tractor, leopard, oak_tree, couch, road, raccoon, poppy, rabbit
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0689
Base model
microsoft/resnet-101