Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0338)
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 | 9e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 338 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9745 |
| Val Accuracy | 0.8941 |
| Test Accuracy | 0.8794 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
plain, beaver, lion, man, lamp, turtle, bed, lizard, dinosaur, bowl, orchid, caterpillar, sea, crab, mushroom, porcupine, shrew, tank, forest, bee, hamster, trout, motorcycle, wolf, seal, plate, baby, tractor, bottle, sweet_pepper, camel, cockroach, train, dolphin, couch, fox, squirrel, snake, crocodile, can, house, pine_tree, ray, poppy, television, maple_tree, shark, bicycle, cattle, pickup_truck
- Downloads last month
- 3
Model tree for ProbeX/Model-J__ResNet__model_idx_0338
Base model
microsoft/resnet-101