Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0187)
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 | val |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 3e-05 |
| LR Scheduler | linear |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 187 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7174 |
| Val Accuracy | 0.7013 |
| Test Accuracy | 0.7054 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cattle, plain, fox, trout, snail, crocodile, poppy, seal, lizard, oak_tree, television, beetle, spider, wardrobe, lawn_mower, flatfish, telephone, elephant, snake, worm, leopard, tulip, lamp, man, streetcar, bottle, baby, mouse, bowl, porcupine, cup, chimpanzee, raccoon, ray, pear, pine_tree, maple_tree, crab, cockroach, mountain, hamster, palm_tree, turtle, rabbit, skunk, mushroom, sea, butterfly, willow_tree, bear
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0187
Base model
microsoft/resnet-101