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_0133")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0133")Quick Links
Model-J: DINO Model (model_idx_0133)
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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 133 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.3908 |
| Val Accuracy | 0.3472 |
| Test Accuracy | 0.3654 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rabbit, tractor, road, rose, oak_tree, maple_tree, spider, forest, sweet_pepper, bus, cockroach, squirrel, caterpillar, orchid, bear, couch, leopard, bed, man, castle, beaver, palm_tree, shark, cloud, cup, rocket, whale, mouse, lobster, streetcar, poppy, tulip, crab, skyscraper, can, shrew, tiger, table, train, boy, lawn_mower, raccoon, otter, wardrobe, crocodile, kangaroo, pickup_truck, wolf, camel, lion
- Downloads last month
- 3
Model tree for ProbeX/Model-J__DINO__model_idx_0133
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_0133") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")