Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0413)
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 | 5e-05 |
| LR Scheduler | linear |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 413 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7949 |
| Val Accuracy | 0.7605 |
| Test Accuracy | 0.7690 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bridge, bee, trout, train, telephone, wardrobe, sunflower, television, dolphin, worm, lamp, forest, rabbit, aquarium_fish, palm_tree, beetle, woman, flatfish, willow_tree, whale, baby, fox, turtle, crab, tiger, possum, boy, shark, cockroach, streetcar, camel, oak_tree, squirrel, tank, seal, plate, rose, bottle, mountain, caterpillar, lawn_mower, cattle, chair, lobster, spider, snake, bicycle, elephant, tractor, butterfly
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0413
Base model
microsoft/resnet-101