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_0166")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0166")Quick Links
Model-J: DINO Model (model_idx_0166)
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 | test |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 166 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.3688 |
| Val Accuracy | 0.3491 |
| Test Accuracy | 0.3574 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sunflower, man, bus, mountain, cloud, plate, wardrobe, bottle, orchid, sea, can, flatfish, cattle, rose, tulip, skyscraper, skunk, motorcycle, raccoon, streetcar, tractor, bear, beaver, poppy, squirrel, woman, couch, telephone, palm_tree, pear, ray, spider, shark, seal, chimpanzee, crab, chair, maple_tree, trout, oak_tree, cup, table, bicycle, bowl, snake, train, camel, worm, forest, mushroom
- Downloads last month
- 2
Model tree for ProbeX/Model-J__DINO__model_idx_0166
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_0166") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")