Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0938)
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 | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 938 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9782 |
| Val Accuracy | 0.8773 |
| Test Accuracy | 0.8746 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dolphin, forest, bottle, wardrobe, otter, camel, lobster, sea, keyboard, beetle, telephone, lizard, chair, crab, elephant, cloud, flatfish, girl, skyscraper, leopard, poppy, maple_tree, rabbit, mountain, ray, sunflower, kangaroo, willow_tree, tulip, bicycle, man, woman, lion, rose, sweet_pepper, tank, lawn_mower, boy, seal, spider, train, baby, road, clock, apple, cattle, trout, aquarium_fish, butterfly, castle
- Downloads last month
- 3
Model tree for ProbeX/Model-J__ResNet__model_idx_0938
Base model
microsoft/resnet-101