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_0772")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0772")Quick Links
Model-J: DINO Model (model_idx_0772)
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_with_restarts |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 772 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.3343 |
| Val Accuracy | 0.3200 |
| Test Accuracy | 0.3230 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
girl, snake, shrew, skyscraper, bee, telephone, dolphin, road, camel, leopard, house, chair, tractor, beaver, bicycle, lion, bowl, shark, snail, squirrel, baby, man, motorcycle, pine_tree, wardrobe, crocodile, rabbit, pear, otter, cattle, orange, streetcar, television, mouse, keyboard, plain, rose, orchid, lawn_mower, possum, tank, mushroom, train, turtle, porcupine, spider, cockroach, table, poppy, lizard
- Downloads last month
- 1
Model tree for ProbeX/Model-J__DINO__model_idx_0772
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_0772") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")