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_0885")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__SupViT__model_idx_0885")Quick Links
Model-J: SupViT Model (model_idx_0885)
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 | cosine_with_restarts |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 885 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9928 |
| Val Accuracy | 0.9309 |
| Test Accuracy | 0.9368 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rose, chair, sunflower, hamster, elephant, squirrel, sweet_pepper, whale, camel, cloud, plate, man, castle, worm, mushroom, forest, butterfly, spider, sea, bus, mountain, skyscraper, woman, lobster, oak_tree, orange, tank, cup, maple_tree, leopard, crocodile, trout, streetcar, ray, bottle, poppy, lamp, beetle, snake, table, girl, orchid, motorcycle, dinosaur, pickup_truck, apple, palm_tree, couch, bicycle, cockroach
- Downloads last month
- 2
Model tree for ProbeX/Model-J__SupViT__model_idx_0885
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_0885") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")