Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0064)
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 | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 64 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9728 |
| Val Accuracy | 0.8867 |
| Test Accuracy | 0.8850 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lobster, ray, mouse, bed, tank, forest, shark, train, maple_tree, clock, chair, mushroom, pickup_truck, crocodile, streetcar, apple, road, bridge, lamp, skyscraper, elephant, snake, cup, motorcycle, poppy, telephone, rocket, bowl, lizard, cloud, bottle, skunk, palm_tree, tractor, oak_tree, rose, snail, girl, baby, possum, pear, shrew, orange, otter, keyboard, beetle, porcupine, crab, television, plain
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0064
Base model
microsoft/resnet-101