Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0921)
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_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 921 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9493 |
| Val Accuracy | 0.8864 |
| Test Accuracy | 0.8732 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sunflower, chimpanzee, shark, television, man, lizard, pear, lawn_mower, oak_tree, tiger, shrew, cloud, skyscraper, tank, otter, rose, fox, cup, palm_tree, squirrel, kangaroo, mushroom, apple, hamster, bed, couch, forest, raccoon, streetcar, train, rabbit, leopard, possum, plain, lamp, telephone, plate, sweet_pepper, ray, baby, girl, turtle, porcupine, snake, road, trout, cockroach, orchid, bus, seal
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0921
Base model
microsoft/resnet-101