Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0887)
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 | 0.0001 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 887 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9896 |
| Val Accuracy | 0.8901 |
| Test Accuracy | 0.8840 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
camel, lamp, cockroach, rocket, squirrel, lawn_mower, cup, sea, bottle, mountain, shrew, mushroom, fox, oak_tree, castle, tiger, bus, hamster, beaver, rabbit, crab, lizard, whale, turtle, tulip, forest, seal, pine_tree, house, girl, porcupine, wolf, ray, woman, sunflower, poppy, telephone, possum, lion, lobster, plain, aquarium_fish, palm_tree, butterfly, orchid, television, sweet_pepper, apple, bridge, wardrobe
- Downloads last month
- 43
Model tree for ProbeX/Model-J__ResNet__model_idx_0887
Base model
microsoft/resnet-101