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_0274")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0274")Quick Links
Model-J: DINO Model (model_idx_0274)
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 | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 274 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4634 |
| Val Accuracy | 0.3845 |
| Test Accuracy | 0.3886 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
seal, lawn_mower, sunflower, mouse, dinosaur, lobster, man, sweet_pepper, mountain, couch, plain, woman, possum, crocodile, crab, rose, telephone, turtle, baby, porcupine, willow_tree, bear, orange, tulip, streetcar, pine_tree, cup, dolphin, cattle, skunk, spider, mushroom, snail, rabbit, poppy, wolf, fox, otter, beetle, squirrel, rocket, road, bottle, caterpillar, worm, apple, bridge, pickup_truck, tractor, oak_tree
- Downloads last month
- 1
Model tree for ProbeX/Model-J__DINO__model_idx_0274
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_0274") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")