Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0449)
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 | 0.0001 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 449 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7246 |
| Val Accuracy | 0.7045 |
| Test Accuracy | 0.7038 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
elephant, motorcycle, pickup_truck, sweet_pepper, beaver, squirrel, tank, poppy, dinosaur, cockroach, crab, skyscraper, lion, snail, cattle, skunk, shrew, possum, house, flatfish, porcupine, turtle, palm_tree, seal, ray, table, whale, boy, can, pear, lizard, lamp, tiger, butterfly, sea, kangaroo, pine_tree, plate, lobster, beetle, dolphin, chair, otter, road, willow_tree, tractor, rabbit, raccoon, rocket, snake
- Downloads last month
- 33
Model tree for ProbeX/Model-J__ResNet__model_idx_0449
Base model
microsoft/resnet-101