Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0356)
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 | 9e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 356 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9677 |
| Val Accuracy | 0.8755 |
| Test Accuracy | 0.8774 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
spider, man, sunflower, elephant, skyscraper, orange, trout, crocodile, table, flatfish, cockroach, pear, worm, lamp, lawn_mower, chimpanzee, mountain, squirrel, raccoon, tulip, skunk, can, rocket, sweet_pepper, kangaroo, lobster, camel, seal, pine_tree, snail, orchid, shrew, oak_tree, cattle, road, dolphin, dinosaur, train, boy, mushroom, bridge, otter, pickup_truck, bottle, maple_tree, possum, caterpillar, television, house, whale
- Downloads last month
- 35
Model tree for ProbeX/Model-J__ResNet__model_idx_0356
Base model
microsoft/resnet-101