Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0382)
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 | 7e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 382 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7071 |
| Val Accuracy | 0.6965 |
| Test Accuracy | 0.6884 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pickup_truck, telephone, train, ray, mushroom, mouse, porcupine, mountain, castle, sweet_pepper, palm_tree, otter, trout, pine_tree, road, spider, bus, butterfly, streetcar, beaver, seal, bottle, turtle, crab, snake, keyboard, skunk, poppy, lamp, rocket, lawn_mower, forest, crocodile, chimpanzee, bowl, shark, lizard, fox, house, boy, squirrel, plain, man, oak_tree, wolf, cockroach, worm, snail, dinosaur, elephant
- Downloads last month
- 1
Model tree for ProbeX/Model-J__ResNet__model_idx_0382
Base model
microsoft/resnet-101