Model-J DINO
Collection
1002 items • Updated
# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("ProbeX/Model-J__DINO__model_idx_0908")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0908")Quick Links
Model-J: DINO Model (model_idx_0908)
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 | DINO |
| Split | train |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 908 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5252 |
| Val Accuracy | 0.3848 |
| Test Accuracy | 0.3918 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
seal, butterfly, table, otter, worm, maple_tree, leopard, bottle, bear, kangaroo, plate, wolf, fox, elephant, house, bee, turtle, sunflower, shark, camel, orange, chimpanzee, motorcycle, spider, bed, cup, beaver, pine_tree, bowl, crocodile, trout, aquarium_fish, caterpillar, oak_tree, porcupine, bicycle, train, woman, wardrobe, chair, mountain, snail, beetle, lobster, tank, possum, tiger, crab, whale, girl
- Downloads last month
- 2
Model tree for ProbeX/Model-J__DINO__model_idx_0908
Base model
facebook/dino-vitb16
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="ProbeX/Model-J__DINO__model_idx_0908") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")