Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0083)
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 | val |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 83 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9736 |
| Val Accuracy | 0.9029 |
| Test Accuracy | 0.8954 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lawn_mower, flatfish, elephant, bridge, otter, snail, train, lion, raccoon, cockroach, tractor, baby, bear, mountain, chair, table, willow_tree, orange, cattle, snake, seal, woman, apple, maple_tree, television, hamster, camel, crocodile, telephone, sea, bed, plate, porcupine, dinosaur, couch, dolphin, possum, sweet_pepper, tiger, pickup_truck, ray, streetcar, shark, lobster, leopard, cloud, bee, bicycle, mushroom, clock
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0083
Base model
microsoft/resnet-101