Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0429)
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 | 3e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 429 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8160 |
| Val Accuracy | 0.7827 |
| Test Accuracy | 0.7840 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rabbit, hamster, bus, tiger, sweet_pepper, raccoon, pear, table, keyboard, pine_tree, lamp, orange, possum, crocodile, television, mouse, skunk, cattle, woman, train, leopard, maple_tree, trout, crab, cup, wolf, telephone, turtle, tank, can, bicycle, bear, house, caterpillar, rocket, girl, chair, road, cockroach, plain, beetle, poppy, squirrel, bowl, rose, wardrobe, sea, snake, baby, skyscraper
- Downloads last month
- 3
Model tree for ProbeX/Model-J__ResNet__model_idx_0429
Base model
microsoft/resnet-101