pawlo2013/kimchi-dataset
Viewer โข Updated โข 11k โข 20
How to use pawlo2013/kimchi-classification with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("image-classification", model="pawlo2013/kimchi-classification")
pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png") # pip install -U transformers accelerate
# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("pawlo2013/kimchi-classification")
model = AutoModelForImageClassification.from_pretrained("pawlo2013/kimchi-classification", device_map="auto")Although it's unlikely you'll ever use it, This model was trained for classifying different types of kimchi (Korean cabbage). It achieved 89% accuracy on a test set comprising of 11 different classes of this Korean delicacy.
labels_eng = ['baechu', 'baik', 'boochoo', 'chongkak', 'got', 'kkakdoogi', 'moosaengchae', 'nabak', 'ohyeesobaki', 'pa', 'yeolmoo']
labels_kr = ['๋ฐฐ์ถ', '๋ฐฑ(๋ํ)', '๋ถ์ถ', '์ด๊ฐ๊น์น', '๊ณ ์ถ', '๊น๋๊ธฐ', '๋ฌด์์ฑ', '๋๋ฐ', '์ค์ด์๋ฐ์ด', 'ํ', '์ด๋ฌด']
This model is basically a fintuned version of the vision tranformer .