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_0428")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0428")Quick Links
Model-J: DINO Model (model_idx_0428)
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 | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 428 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9905 |
| Val Accuracy | 0.8912 |
| Test Accuracy | 0.8962 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
man, skyscraper, squirrel, wardrobe, maple_tree, rabbit, dolphin, orange, camel, elephant, palm_tree, ray, sea, road, bear, tractor, girl, mushroom, bed, shrew, skunk, butterfly, bee, pickup_truck, rocket, lawn_mower, shark, caterpillar, crocodile, spider, bicycle, orchid, raccoon, pear, bowl, plain, tulip, oak_tree, crab, seal, aquarium_fish, porcupine, bus, cloud, poppy, apple, telephone, television, train, lamp
- Downloads last month
- 2
Model tree for ProbeX/Model-J__DINO__model_idx_0428
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_0428") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")