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_0831")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__SupViT__model_idx_0831")Quick Links
Model-J: SupViT Model (model_idx_0831)
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 | val |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 5e-05 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 831 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9985 |
| Val Accuracy | 0.9520 |
| Test Accuracy | 0.9514 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
orange, seal, train, turtle, streetcar, raccoon, castle, forest, cloud, rabbit, dolphin, orchid, lobster, boy, tank, maple_tree, spider, mountain, cattle, leopard, fox, telephone, tiger, road, plate, caterpillar, snail, lion, camel, whale, apple, clock, chair, bowl, tractor, bus, hamster, baby, beaver, squirrel, chimpanzee, couch, crocodile, porcupine, bridge, kangaroo, table, lamp, ray, bicycle
- Downloads last month
- 2
Model tree for ProbeX/Model-J__SupViT__model_idx_0831
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_0831") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")