Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0012)
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 | 0.0005 |
| LR Scheduler | constant |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 12 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9847 |
| Val Accuracy | 0.9032 |
| Test Accuracy | 0.8986 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
palm_tree, crocodile, sea, maple_tree, spider, bee, tank, chair, forest, leopard, bowl, girl, wardrobe, table, tiger, hamster, plate, skunk, tractor, road, woman, telephone, cattle, clock, bottle, streetcar, porcupine, can, squirrel, beaver, television, orange, raccoon, beetle, bicycle, shrew, dinosaur, oak_tree, poppy, lamp, snake, whale, elephant, cup, pickup_truck, couch, lion, skyscraper, butterfly, caterpillar
- Downloads last month
- 4
Model tree for ProbeX/Model-J__ResNet__model_idx_0012
Base model
microsoft/resnet-101