Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0754)
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 | test |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 754 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9123 |
| Val Accuracy | 0.8659 |
| Test Accuracy | 0.8696 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
raccoon, squirrel, orange, road, chimpanzee, spider, plate, bus, turtle, girl, bottle, streetcar, forest, tank, chair, poppy, pickup_truck, plain, skyscraper, lion, trout, can, motorcycle, rose, camel, beaver, palm_tree, mountain, train, wolf, house, leopard, hamster, rocket, mouse, clock, sunflower, dinosaur, bridge, bear, cattle, skunk, maple_tree, woman, bee, mushroom, cloud, willow_tree, tulip, keyboard
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0754
Base model
microsoft/resnet-101