Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0775)
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 | constant |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 775 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9781 |
| Val Accuracy | 0.8803 |
| Test Accuracy | 0.8884 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
caterpillar, sunflower, poppy, dolphin, cockroach, shark, ray, orchid, bicycle, raccoon, lawn_mower, flatfish, crocodile, bridge, bus, maple_tree, girl, bowl, fox, woman, train, beaver, lamp, butterfly, chair, skyscraper, plate, wardrobe, keyboard, whale, orange, tractor, apple, bee, mushroom, pickup_truck, rocket, tiger, lion, cloud, mouse, chimpanzee, road, squirrel, seal, oak_tree, telephone, plain, hamster, television
- Downloads last month
- 3
Model tree for ProbeX/Model-J__ResNet__model_idx_0775
Base model
microsoft/resnet-101