Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0513)
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 | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 513 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9732 |
| Val Accuracy | 0.8768 |
| Test Accuracy | 0.8856 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
train, snail, castle, kangaroo, shark, tank, beaver, wardrobe, house, willow_tree, butterfly, beetle, camel, caterpillar, bus, cup, bear, otter, cattle, lawn_mower, leopard, seal, spider, whale, turtle, aquarium_fish, porcupine, poppy, squirrel, cloud, pear, television, sea, telephone, fox, table, woman, man, apple, elephant, wolf, chair, mouse, trout, bee, forest, bed, mountain, worm, orange
- Downloads last month
- 33
Model tree for ProbeX/Model-J__ResNet__model_idx_0513
Base model
microsoft/resnet-101