Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0069)
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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 69 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9830 |
| Val Accuracy | 0.9032 |
| Test Accuracy | 0.8978 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bus, ray, crocodile, possum, sunflower, tulip, baby, snake, tank, cloud, forest, worm, crab, seal, raccoon, bed, turtle, woman, pickup_truck, beaver, bottle, flatfish, can, poppy, pear, man, camel, dolphin, television, cup, bear, bee, lion, shrew, maple_tree, lawn_mower, snail, road, wardrobe, pine_tree, table, wolf, otter, mushroom, lobster, sea, bicycle, lamp, boy, beetle
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0069
Base model
microsoft/resnet-101