Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0387)
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 | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 387 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8748 |
| Val Accuracy | 0.8325 |
| Test Accuracy | 0.8334 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
chair, seal, mushroom, bee, possum, apple, can, chimpanzee, palm_tree, leopard, shrew, snake, butterfly, crocodile, lion, elephant, porcupine, bridge, maple_tree, road, willow_tree, castle, bottle, worm, television, snail, camel, orange, sea, telephone, dinosaur, clock, lawn_mower, mountain, sweet_pepper, kangaroo, train, baby, poppy, lobster, girl, shark, skyscraper, cockroach, trout, rocket, motorcycle, dolphin, sunflower, house
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0387
Base model
microsoft/resnet-101