Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0918)
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 | 0.0001 |
| LR Scheduler | linear |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 918 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8660 |
| Val Accuracy | 0.8123 |
| Test Accuracy | 0.8134 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
man, rocket, can, porcupine, fox, baby, forest, table, rose, bowl, lion, chair, kangaroo, sunflower, bus, lobster, trout, clock, beetle, pine_tree, whale, shrew, crocodile, tulip, spider, bottle, willow_tree, cup, boy, squirrel, snail, wolf, oak_tree, mushroom, poppy, tiger, tractor, flatfish, bear, bed, bee, cockroach, caterpillar, orchid, beaver, television, bridge, pickup_truck, otter, sea
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0918
Base model
microsoft/resnet-101