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_0989")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0989")Quick Links
Model-J: DINO Model (model_idx_0989)
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 | cosine |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 989 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4873 |
| Val Accuracy | 0.3672 |
| Test Accuracy | 0.3900 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
house, tiger, bowl, train, hamster, can, kangaroo, girl, cattle, leopard, baby, cloud, lizard, aquarium_fish, rabbit, raccoon, dolphin, wolf, possum, porcupine, caterpillar, turtle, beaver, apple, bridge, road, snake, mushroom, bed, plate, poppy, keyboard, tank, fox, plain, shark, elephant, maple_tree, couch, chair, sunflower, dinosaur, orchid, ray, beetle, trout, telephone, motorcycle, shrew, tulip
- Downloads last month
- 4
Model tree for ProbeX/Model-J__DINO__model_idx_0989
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_0989") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")