Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0067)
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 | 3e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 67 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7431 |
| Val Accuracy | 0.7155 |
| Test Accuracy | 0.7242 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
boy, leopard, plain, clock, bee, flatfish, palm_tree, bed, woman, whale, cup, lawn_mower, motorcycle, man, cloud, porcupine, shark, bus, sunflower, pine_tree, ray, television, mountain, keyboard, orchid, rose, lobster, camel, snake, train, poppy, rocket, tiger, possum, beaver, chimpanzee, hamster, butterfly, dolphin, skunk, spider, snail, house, worm, pear, aquarium_fish, dinosaur, lamp, trout, turtle
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0067
Base model
microsoft/resnet-101