Spaces:
Running
Running
import gradio as gr | |
from transformers import AutoProcessor, CLIPModel | |
# Charger le pipeline | |
model = CLIPModel.from_pretrained("patrickjohncyh/fashion-clip") | |
processor = AutoProcessor.from_pretrained("patrickjohncyh/fashion-clip") | |
# Définir la fonction pour la classification d'image avec du texte en entrée | |
def classify_image_with_text(text, image): | |
# Effectuer la classification d'image à l'aide du texte | |
keywords = text.split(',') | |
inputs = processor( | |
text=keywords, images=image, return_tensors="pt", padding=True | |
) | |
outputs = model(**inputs) | |
logits_per_image = outputs.logits_per_image # this is the image-text similarity score | |
probs = logits_per_image.softmax(dim=1) | |
predicted_class_index = probs.argmax(dim=1).item() | |
predicted_label = keywords[predicted_class_index] | |
return predicted_label | |
# Créer l'interface Gradio avec l'API de Gradio Blocks | |
with gr.Interface( | |
fn=classify_image_with_text, | |
inputs=[gr.Textbox(lines=1, label="Prompt"), gr.Image(label="Image")], | |
outputs=gr.Textbox(label='Sortie de l\'API'), | |
title="SD Models" | |
) as iface: | |
iface.launch() | |