Model-J SupViT
Collection
998 items • Updated
# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("ProbeX/Model-J__SupViT__model_idx_0469")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__SupViT__model_idx_0469")Quick Links
Model-J: SupViT Model (model_idx_0469)
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 | SupViT |
| Split | test |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 469 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9248 |
| Val Accuracy | 0.8712 |
| Test Accuracy | 0.8696 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
crab, motorcycle, boy, lawn_mower, possum, willow_tree, pine_tree, butterfly, bridge, crocodile, poppy, plate, keyboard, worm, flatfish, shark, oak_tree, seal, baby, raccoon, spider, fox, snail, road, porcupine, whale, apple, sea, aquarium_fish, sweet_pepper, beetle, bear, otter, mouse, squirrel, house, tank, orchid, ray, kangaroo, lamp, castle, plain, rose, telephone, cloud, rocket, bicycle, bed, shrew
- Downloads last month
- 1
Model tree for ProbeX/Model-J__SupViT__model_idx_0469
Base model
google/vit-base-patch16-224
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="ProbeX/Model-J__SupViT__model_idx_0469") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")