Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0407)
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 | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 407 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9380 |
| Val Accuracy | 0.8733 |
| Test Accuracy | 0.8626 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sea, aquarium_fish, tulip, cup, baby, possum, camel, skunk, streetcar, lizard, rabbit, keyboard, lobster, maple_tree, table, squirrel, chimpanzee, crab, cockroach, cattle, house, tank, mouse, beetle, plate, snail, seal, poppy, telephone, bus, palm_tree, bicycle, elephant, lion, wolf, dolphin, shrew, shark, tiger, apple, bed, bridge, flatfish, plain, beaver, mountain, sunflower, tractor, man, bowl
- Downloads last month
- 29
Model tree for ProbeX/Model-J__ResNet__model_idx_0407
Base model
microsoft/resnet-101