Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0018)
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 | 5e-05 |
| LR Scheduler | constant |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 18 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8823 |
| Val Accuracy | 0.8405 |
| Test Accuracy | 0.8352 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sea, maple_tree, pear, lamp, tank, clock, willow_tree, tractor, fox, dinosaur, plate, tulip, forest, butterfly, cloud, can, chair, beetle, bus, cattle, boy, beaver, spider, lobster, castle, apple, elephant, motorcycle, bowl, man, wolf, bridge, rabbit, table, crocodile, plain, aquarium_fish, couch, kangaroo, pine_tree, television, caterpillar, cup, orchid, mountain, squirrel, bottle, mushroom, worm, whale
- Downloads last month
- 10
Model tree for ProbeX/Model-J__ResNet__model_idx_0018
Base model
microsoft/resnet-101