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_0999")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__SupViT__model_idx_0999")Quick Links
Model-J: SupViT Model (model_idx_0999)
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 | 0.0005 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 999 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9965 |
| Val Accuracy | 0.9184 |
| Test Accuracy | 0.9160 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
camel, clock, streetcar, butterfly, whale, bottle, tiger, table, house, beaver, forest, rabbit, leopard, poppy, road, fox, wolf, shrew, snail, dolphin, willow_tree, sweet_pepper, raccoon, can, turtle, flatfish, lamp, girl, crocodile, tank, possum, oak_tree, bridge, lobster, caterpillar, bowl, castle, skunk, palm_tree, cup, mountain, boy, beetle, telephone, orange, rocket, otter, dinosaur, crab, squirrel
- Downloads last month
- -
Model tree for ProbeX/Model-J__SupViT__model_idx_0999
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_0999") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")