Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0122)
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 | 3e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 122 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8657 |
| Val Accuracy | 0.8365 |
| Test Accuracy | 0.8240 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bottle, poppy, keyboard, bee, mouse, wardrobe, girl, cattle, couch, butterfly, orange, sea, lamp, castle, orchid, house, shrew, forest, pear, cloud, shark, table, television, beetle, plain, train, wolf, lawn_mower, willow_tree, mountain, chair, streetcar, man, pickup_truck, snake, dinosaur, apple, tiger, tractor, baby, camel, palm_tree, possum, elephant, kangaroo, motorcycle, otter, raccoon, spider, seal
- Downloads last month
- 3
Model tree for ProbeX/Model-J__ResNet__model_idx_0122
Base model
microsoft/resnet-101