Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0764)
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 | 0.0001 |
| LR Scheduler | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 764 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9552 |
| Val Accuracy | 0.8781 |
| Test Accuracy | 0.8778 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
oak_tree, raccoon, keyboard, elephant, maple_tree, train, chimpanzee, trout, house, woman, lamp, crab, tulip, tiger, spider, beetle, wolf, palm_tree, couch, fox, skunk, worm, skyscraper, pickup_truck, seal, cattle, otter, plain, cockroach, dolphin, bottle, bowl, willow_tree, boy, hamster, telephone, cup, cloud, girl, whale, bee, rose, aquarium_fish, snake, caterpillar, leopard, rabbit, mushroom, mountain, bear
- Downloads last month
- 4
Model tree for ProbeX/Model-J__ResNet__model_idx_0764
Base model
microsoft/resnet-101