Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0587)
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 | linear |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 587 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9989 |
| Val Accuracy | 0.9120 |
| Test Accuracy | 0.9066 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
apple, lamp, bear, kangaroo, rose, aquarium_fish, mushroom, caterpillar, squirrel, sweet_pepper, spider, tractor, clock, orchid, baby, whale, bee, crab, palm_tree, plain, elephant, rabbit, can, motorcycle, couch, snake, poppy, crocodile, cup, oak_tree, castle, bus, raccoon, tulip, shark, butterfly, worm, lobster, woman, sea, streetcar, possum, snail, train, fox, tank, mountain, trout, willow_tree, seal
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0587
Base model
microsoft/resnet-101