Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0584)
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 | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 584 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8602 |
| Val Accuracy | 0.8272 |
| Test Accuracy | 0.8312 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cattle, cup, ray, telephone, plate, camel, girl, aquarium_fish, road, sunflower, bottle, whale, boy, couch, tank, shrew, chimpanzee, lawn_mower, leopard, bicycle, orchid, pear, cockroach, spider, sea, train, cloud, streetcar, fox, seal, crab, palm_tree, lobster, possum, elephant, tractor, pickup_truck, trout, squirrel, bed, rose, shark, beaver, willow_tree, motorcycle, dolphin, lion, worm, castle, skunk
- Downloads last month
- 1
Model tree for ProbeX/Model-J__ResNet__model_idx_0584
Base model
microsoft/resnet-101