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_0065")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0065")Quick Links
Model-J: DINO Model (model_idx_0065)
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 | 9e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 65 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9588 |
| Val Accuracy | 0.8603 |
| Test Accuracy | 0.8668 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
snake, chimpanzee, lion, wolf, rocket, cloud, streetcar, pear, wardrobe, clock, house, woman, possum, dolphin, tiger, raccoon, camel, bottle, pickup_truck, seal, hamster, turtle, beetle, mountain, tractor, telephone, porcupine, orange, worm, skunk, willow_tree, bridge, caterpillar, table, train, lawn_mower, pine_tree, kangaroo, bear, man, keyboard, poppy, lizard, crocodile, bicycle, cattle, dinosaur, leopard, road, cockroach
- Downloads last month
- 3
Model tree for ProbeX/Model-J__DINO__model_idx_0065
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_0065") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")