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_0687")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0687")Quick Links
Model-J: DINO Model (model_idx_0687)
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 | val |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 687 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9365 |
| Val Accuracy | 0.8576 |
| Test Accuracy | 0.8596 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
hamster, bowl, house, worm, fox, lamp, television, orchid, plate, lion, kangaroo, shrew, tulip, squirrel, rocket, sweet_pepper, caterpillar, cup, turtle, whale, willow_tree, clock, woman, pine_tree, road, bear, wolf, skunk, dinosaur, seal, mouse, palm_tree, beaver, bridge, oak_tree, bee, bed, couch, leopard, raccoon, elephant, cloud, bus, forest, tank, keyboard, beetle, lobster, motorcycle, cattle
- Downloads last month
- 2
Model tree for ProbeX/Model-J__DINO__model_idx_0687
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_0687") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")