Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0454)
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 | constant_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 454 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9197 |
| Val Accuracy | 0.8739 |
| Test Accuracy | 0.8730 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rose, oak_tree, cockroach, train, mushroom, bridge, bee, raccoon, kangaroo, fox, plate, chair, camel, sea, apple, dolphin, house, mountain, turtle, aquarium_fish, lamp, snake, hamster, woman, bed, flatfish, sunflower, pine_tree, orchid, rocket, tank, motorcycle, pickup_truck, rabbit, road, squirrel, telephone, ray, wardrobe, shrew, girl, seal, beetle, tulip, skunk, caterpillar, snail, bear, beaver, lobster
- Downloads last month
- 35
Model tree for ProbeX/Model-J__ResNet__model_idx_0454
Base model
microsoft/resnet-101