Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0491)
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 | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 491 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8702 |
| Val Accuracy | 0.8408 |
| Test Accuracy | 0.8234 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bear, can, crab, caterpillar, lizard, bee, keyboard, mushroom, bed, sunflower, baby, skunk, girl, lamp, ray, fox, man, lion, maple_tree, cloud, snake, mountain, bridge, dinosaur, crocodile, kangaroo, castle, snail, tank, telephone, squirrel, pear, sea, bowl, camel, cup, porcupine, palm_tree, mouse, television, wolf, spider, poppy, pine_tree, tiger, aquarium_fish, road, otter, possum, whale
- Downloads last month
- 38
Model tree for ProbeX/Model-J__ResNet__model_idx_0491
Base model
microsoft/resnet-101