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_0582")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0582")Quick Links
Model-J: DINO Model (model_idx_0582)
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 | 0.0001 |
| LR Scheduler | constant |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 582 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9523 |
| Val Accuracy | 0.8499 |
| Test Accuracy | 0.8354 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
forest, crab, lion, pine_tree, flatfish, castle, shrew, sea, bee, road, leopard, snake, caterpillar, bowl, mushroom, bed, palm_tree, sweet_pepper, bear, apple, telephone, fox, skunk, camel, rabbit, whale, bus, seal, butterfly, wardrobe, orange, lizard, spider, bicycle, plate, sunflower, rose, turtle, house, boy, hamster, bridge, lamp, tulip, possum, willow_tree, maple_tree, chimpanzee, tiger, cockroach
- Downloads last month
- 3
Model tree for ProbeX/Model-J__DINO__model_idx_0582
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_0582") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")