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_0056")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0056")Quick Links
Model-J: DINO Model (model_idx_0056)
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 | 0.0005 |
| LR Scheduler | constant_with_warmup |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 56 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.3871 |
| Val Accuracy | 0.3499 |
| Test Accuracy | 0.3500 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
otter, bee, seal, woman, cockroach, possum, orange, wardrobe, tractor, plain, motorcycle, palm_tree, tank, tulip, wolf, worm, sunflower, forest, camel, crocodile, lobster, tiger, table, hamster, mountain, lion, maple_tree, plate, pickup_truck, bridge, cloud, dolphin, mushroom, bear, squirrel, dinosaur, television, house, snake, girl, streetcar, road, chimpanzee, ray, whale, aquarium_fish, caterpillar, kangaroo, poppy, snail
- Downloads last month
- 2
Model tree for ProbeX/Model-J__DINO__model_idx_0056
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_0056") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")