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_0807")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0807")Quick Links
Model-J: DINO Model (model_idx_0807)
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 | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 807 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.9192 |
| Test Accuracy | 0.9300 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
willow_tree, mouse, flatfish, clock, whale, otter, castle, girl, apple, table, dolphin, palm_tree, bridge, plain, trout, rose, porcupine, pine_tree, rabbit, bowl, bear, crab, train, squirrel, leopard, cockroach, bottle, elephant, kangaroo, pear, wolf, streetcar, dinosaur, shark, lamp, tractor, fox, chimpanzee, bee, skunk, cup, lobster, rocket, crocodile, beetle, plate, skyscraper, butterfly, orchid, camel
- Downloads last month
- -
Model tree for ProbeX/Model-J__DINO__model_idx_0807
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_0807") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")