| import gradio as gr | |
| import shutil | |
| import urllib.request | |
| import sys | |
| import os | |
| import urllib.request | |
| import zipfile | |
| sys.path.append(".") | |
| gr.close_all() | |
| urllib.request.urlretrieve("https://storage.googleapis.com/models-gradio/products/products.zip", "products.zip") | |
| with zipfile.ZipFile("products.zip", 'r') as zip_ref: | |
| zip_ref.extractall() | |
| from model import prediction | |
| def predict(img): | |
| prediction_img, text, t_process = prediction(img) | |
| return t_process, str(text), prediction_img, | |
| sample_images = ["dataset/" + name for name in os.listdir("dataset")] | |
| gr.Interface(fn=predict, | |
| inputs=[gr.Image(label="image à tester" ,type="filepath")], | |
| outputs=[gr.Textbox(label="temps"), gr.Textbox(label="analyse"), gr.Image(label ="résultat") ], | |
| css="footer {visibility: hidden} body}, .gradio-container {background-color: white}", | |
| examples=sample_images).launch(server_name="0.0.0.0", share=False) | |