Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0178)
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 | 0.0003 |
| LR Scheduler | constant |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 178 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9820 |
| Val Accuracy | 0.8643 |
| Test Accuracy | 0.8726 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
butterfly, turtle, rose, hamster, rocket, pine_tree, mouse, wolf, boy, rabbit, otter, ray, elephant, baby, worm, keyboard, clock, pickup_truck, maple_tree, caterpillar, sweet_pepper, streetcar, cloud, tractor, woman, television, sunflower, road, lawn_mower, bed, skunk, house, bear, pear, bowl, couch, girl, lion, train, dinosaur, oak_tree, lamp, tulip, bicycle, spider, willow_tree, crab, motorcycle, fox, table
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0178
Base model
microsoft/resnet-101