Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0229)
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 | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 229 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7856 |
| Val Accuracy | 0.7688 |
| Test Accuracy | 0.7658 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lamp, wardrobe, possum, sea, otter, boy, oak_tree, crab, beaver, tank, worm, keyboard, flatfish, clock, sweet_pepper, hamster, caterpillar, chair, cup, bus, skunk, whale, castle, lion, television, pickup_truck, chimpanzee, shark, seal, skyscraper, lizard, elephant, bowl, sunflower, bridge, turtle, cloud, apple, motorcycle, shrew, maple_tree, cattle, lobster, road, cockroach, porcupine, willow_tree, spider, squirrel, woman
- Downloads last month
- 21
Model tree for ProbeX/Model-J__ResNet__model_idx_0229
Base model
microsoft/resnet-101