Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0772)
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 | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 772 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9501 |
| Val Accuracy | 0.8568 |
| Test Accuracy | 0.8600 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
worm, kangaroo, trout, bottle, dolphin, sweet_pepper, raccoon, apple, motorcycle, baby, wolf, porcupine, couch, rabbit, tank, willow_tree, woman, snail, castle, house, bowl, crab, cloud, train, lobster, crocodile, orchid, boy, flatfish, lamp, skunk, hamster, girl, butterfly, lizard, tiger, shrew, poppy, bee, spider, bed, lawn_mower, lion, shark, chair, keyboard, sunflower, mouse, plate, maple_tree
- Downloads last month
- 3
Model tree for ProbeX/Model-J__ResNet__model_idx_0772
Base model
microsoft/resnet-101