Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0260)
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 | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 260 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7974 |
| Val Accuracy | 0.7800 |
| Test Accuracy | 0.7632 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
camel, can, boy, aquarium_fish, cup, ray, bottle, squirrel, tulip, man, sunflower, porcupine, elephant, plain, tiger, girl, lawn_mower, cattle, streetcar, snake, bowl, dolphin, bicycle, seal, cloud, road, lion, television, apple, pear, crocodile, turtle, possum, lobster, orchid, raccoon, clock, chimpanzee, tractor, skyscraper, mouse, baby, lamp, hamster, beetle, pine_tree, shrew, palm_tree, mushroom, shark
- Downloads last month
- 4
Model tree for ProbeX/Model-J__ResNet__model_idx_0260
Base model
microsoft/resnet-101