Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0892)
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 | 0.005 |
| Seed | 892 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9477 |
| Val Accuracy | 0.8803 |
| Test Accuracy | 0.8820 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bee, flatfish, tractor, table, girl, butterfly, chimpanzee, pear, tiger, cup, boy, lobster, seal, bottle, telephone, rocket, sunflower, raccoon, oak_tree, cattle, wardrobe, can, aquarium_fish, ray, otter, crocodile, castle, shrew, sea, television, turtle, clock, fox, wolf, porcupine, squirrel, possum, trout, skyscraper, bridge, chair, house, plain, rose, whale, palm_tree, bowl, pine_tree, motorcycle, lawn_mower
- Downloads last month
- 1
Model tree for ProbeX/Model-J__ResNet__model_idx_0892
Base model
microsoft/resnet-101