Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0469)
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 | 3e-05 |
| LR Scheduler | constant |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 469 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8823 |
| Val Accuracy | 0.8376 |
| Test Accuracy | 0.8354 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
aquarium_fish, cockroach, bee, elephant, squirrel, porcupine, wardrobe, mountain, bowl, snake, plate, worm, apple, tractor, baby, possum, telephone, beetle, television, turtle, lawn_mower, crab, bottle, maple_tree, man, sea, bicycle, forest, dolphin, road, kangaroo, flatfish, dinosaur, bed, trout, snail, train, skunk, fox, wolf, palm_tree, willow_tree, castle, orange, otter, whale, rocket, poppy, chair, shark
- Downloads last month
- 20
Model tree for ProbeX/Model-J__ResNet__model_idx_0469
Base model
microsoft/resnet-101