Instructions to use ProbeX/Model-J__DINO__model_idx_0476 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ProbeX/Model-J__DINO__model_idx_0476 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="ProbeX/Model-J__DINO__model_idx_0476") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("ProbeX/Model-J__DINO__model_idx_0476") model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0476") - Notebooks
- Google Colab
- Kaggle
Model-J: DINO Model (model_idx_0476)
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
๐ Project | ๐ Paper | ๐ป GitHub | ๐ค Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | DINO |
| Split | test |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 476 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9875 |
| Val Accuracy | 0.8835 |
| Test Accuracy | 0.8822 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
camel, couch, chimpanzee, snail, skyscraper, tulip, pickup_truck, oak_tree, cloud, cattle, girl, lizard, bus, skunk, flatfish, forest, palm_tree, spider, house, plain, train, bee, turtle, whale, chair, maple_tree, wolf, ray, woman, elephant, television, orchid, sweet_pepper, tractor, apple, motorcycle, mouse, fox, sea, crocodile, hamster, lobster, orange, otter, porcupine, streetcar, shark, pine_tree, can, cup
- Downloads last month
- 1
Model tree for ProbeX/Model-J__DINO__model_idx_0476
Base model
facebook/dino-vitb16