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_0209")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0209")Quick Links
Model-J: DINO Model (model_idx_0209)
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 | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 209 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9637 |
| Val Accuracy | 0.8787 |
| Test Accuracy | 0.8774 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
oak_tree, poppy, kangaroo, camel, bridge, keyboard, pine_tree, forest, willow_tree, cattle, rocket, road, television, turtle, squirrel, mountain, sea, couch, motorcycle, maple_tree, plain, lamp, bear, rabbit, skyscraper, snail, aquarium_fish, palm_tree, ray, worm, castle, butterfly, wardrobe, train, hamster, cup, raccoon, plate, baby, spider, beetle, beaver, seal, tractor, streetcar, otter, tiger, lawn_mower, pear, chair
- Downloads last month
- 2
Model tree for ProbeX/Model-J__DINO__model_idx_0209
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_0209") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")