Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0840)
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 | 0.0003 |
| LR Scheduler | constant |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 840 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9826 |
| Val Accuracy | 0.9000 |
| Test Accuracy | 0.8936 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mountain, keyboard, wolf, road, wardrobe, caterpillar, beaver, worm, dolphin, fox, skyscraper, couch, cup, bus, camel, hamster, trout, lion, table, bottle, porcupine, lobster, willow_tree, pear, cloud, elephant, tank, streetcar, cattle, plate, otter, boy, whale, bee, pickup_truck, seal, crab, chimpanzee, sweet_pepper, rose, oak_tree, sunflower, apple, plain, shrew, pine_tree, telephone, bicycle, tractor, bed
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0840
Base model
microsoft/resnet-101