Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0885)
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 | 5e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 885 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8537 |
| Val Accuracy | 0.8213 |
| Test Accuracy | 0.8130 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dinosaur, snake, sea, telephone, pine_tree, trout, skunk, bee, possum, fox, turtle, butterfly, tank, bowl, cloud, beetle, kangaroo, oak_tree, lion, orange, woman, plate, mouse, bed, can, motorcycle, man, beaver, ray, tulip, spider, palm_tree, leopard, whale, cup, forest, tractor, raccoon, cockroach, bottle, chair, television, wardrobe, otter, baby, mountain, bus, bicycle, pickup_truck, pear
- Downloads last month
- 5
Model tree for ProbeX/Model-J__ResNet__model_idx_0885
Base model
microsoft/resnet-101