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_0574")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0574")Quick Links
Model-J: DINO Model (model_idx_0574)
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 | 3e-05 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 574 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9992 |
| Val Accuracy | 0.9141 |
| Test Accuracy | 0.9256 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sea, fox, dinosaur, willow_tree, television, poppy, beaver, bowl, tulip, pine_tree, man, crocodile, chimpanzee, bicycle, whale, mountain, bee, bridge, boy, dolphin, kangaroo, tank, apple, bear, mushroom, house, cup, bed, woman, pickup_truck, lawn_mower, tractor, baby, castle, cloud, pear, lamp, plain, road, keyboard, lizard, telephone, maple_tree, shrew, train, sunflower, motorcycle, mouse, trout, snake
- Downloads last month
- 2
Model tree for ProbeX/Model-J__DINO__model_idx_0574
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_0574") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")