Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0702)
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 | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 702 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9379 |
| Val Accuracy | 0.8683 |
| Test Accuracy | 0.8688 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
baby, can, palm_tree, whale, kangaroo, wardrobe, crocodile, pickup_truck, beetle, cup, spider, man, chimpanzee, table, cattle, dinosaur, rocket, streetcar, girl, bed, otter, woman, boy, television, snake, wolf, flatfish, bridge, castle, lion, snail, bottle, couch, telephone, cockroach, ray, forest, sunflower, trout, camel, squirrel, rabbit, worm, orchid, shark, aquarium_fish, tiger, chair, bee, road
- Downloads last month
- 39
Model tree for ProbeX/Model-J__ResNet__model_idx_0702
Base model
microsoft/resnet-101