Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0363)
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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 363 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9946 |
| Val Accuracy | 0.8936 |
| Test Accuracy | 0.8932 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
poppy, couch, sweet_pepper, baby, palm_tree, crab, beetle, wardrobe, turtle, rocket, maple_tree, girl, flatfish, whale, squirrel, lamp, porcupine, mouse, bear, dolphin, tulip, sunflower, elephant, bottle, orange, castle, pine_tree, mountain, cattle, hamster, wolf, clock, cockroach, chair, leopard, fox, keyboard, woman, bee, forest, mushroom, cloud, bed, plain, bridge, seal, shrew, bowl, beaver, tractor
- Downloads last month
- 1
Model tree for ProbeX/Model-J__ResNet__model_idx_0363
Base model
microsoft/resnet-101