| import streamlit as st | |
| import torch | |
| import spaces | |
| from transformers import pipeline, AutoModelForCausalLM, AutoProcessor | |
| from PIL import Image | |
| pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog") | |
| st.title("Hot Dog? Or Not?") | |
| device = torch.device("cuda" if torch.cuda.is_available() else "cpu") | |
| image_model_id = "microsoft/git-large-coco" | |
| image_processor = AutoProcessor.from_pretrained(image_model_id) | |
| image_model = AutoModelForCausalLM.from_pretrained(image_model_id).to(device) | |
| file_name = st.file_uploader("Upload a hot dog candidate image") | |
| if file_name is not None: | |
| col1, col2 = st.columns(2) | |
| image = Image.open(file_name) | |
| col1.image(image, use_column_width=True) | |
| predictions = pipeline(image) | |
| col2.header("Probabilities") | |
| for p in predictions: | |
| col2.subheader(f"{ p['label'] }: { round(p['score'] * 100, 1)}%") | |
| pixel_values = image_processor(images=image, return_tensors="pt").pixel_values | |
| generated_ids = image_model.generate(pixel_values=pixel_values, max_length=50) | |
| generated_caption = image_processor.batch_decode(generated_ids, skip_special_tokens=True)[0] | |
| print(generated_caption) |