Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0326)
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 | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 326 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9904 |
| Val Accuracy | 0.9013 |
| Test Accuracy | 0.9022 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pear, apple, caterpillar, bear, can, couch, aquarium_fish, porcupine, skunk, rocket, ray, lobster, bowl, squirrel, chimpanzee, train, whale, cloud, dolphin, forest, fox, lawn_mower, kangaroo, road, house, cup, mouse, bed, sunflower, television, orange, crocodile, baby, lizard, telephone, lion, girl, poppy, crab, worm, cattle, lamp, tiger, mountain, sea, keyboard, bee, tank, beaver, tulip
- Downloads last month
- 26
Model tree for ProbeX/Model-J__ResNet__model_idx_0326
Base model
microsoft/resnet-101