Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0235)
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 | 9e-05 |
| LR Scheduler | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 235 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8416 |
| Val Accuracy | 0.8235 |
| Test Accuracy | 0.8148 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
forest, palm_tree, snail, bottle, bridge, mushroom, shark, seal, wolf, wardrobe, fox, trout, cockroach, tulip, tiger, rabbit, telephone, cattle, lobster, bear, bed, rocket, bus, orchid, lizard, leopard, road, tank, kangaroo, elephant, can, dinosaur, squirrel, caterpillar, woman, pickup_truck, couch, man, possum, crocodile, dolphin, motorcycle, camel, turtle, clock, pine_tree, tractor, hamster, television, plain
- Downloads last month
- 6
Model tree for ProbeX/Model-J__ResNet__model_idx_0235
Base model
microsoft/resnet-101