Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0851)
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 | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 851 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8496 |
| Val Accuracy | 0.8248 |
| Test Accuracy | 0.8244 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
crocodile, willow_tree, cattle, caterpillar, motorcycle, leopard, pear, apple, tulip, spider, girl, snake, aquarium_fish, mushroom, turtle, oak_tree, cup, house, castle, road, dinosaur, ray, television, squirrel, lobster, worm, seal, orange, keyboard, rocket, sweet_pepper, mouse, streetcar, elephant, skyscraper, flatfish, lawn_mower, trout, skunk, possum, clock, train, orchid, bicycle, snail, rabbit, butterfly, couch, fox, forest
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0851
Base model
microsoft/resnet-101