Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0972)
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 | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 972 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6630 |
| Val Accuracy | 0.6339 |
| Test Accuracy | 0.6342 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
orchid, worm, kangaroo, cattle, streetcar, oak_tree, chimpanzee, pear, rocket, aquarium_fish, clock, mountain, tank, crab, road, cup, bee, boy, train, lion, turtle, skunk, bowl, squirrel, girl, shrew, maple_tree, caterpillar, sweet_pepper, bicycle, pine_tree, willow_tree, hamster, elephant, plain, raccoon, dinosaur, television, telephone, skyscraper, chair, fox, camel, flatfish, tiger, mouse, cockroach, porcupine, bridge, apple
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0972
Base model
microsoft/resnet-101