import assignment23 from assignment23 import make_train_valid_dfs from assignment23 import get_image_embeddings from assignment23 import inference_CLIP import gradio as gr import zipfile import os import pandas as pd import subprocess image_path = "./Images" captions_path = "." data_source = 'flickr8k.zip' with zipfile.ZipFile(data_source, 'r') as zip_ref: zip_ref.extractall('.') cmd = "pwd" output1 = subprocess.check_output(cmd, shell=True).decode("utf-8") cmd = "ls -l" output1 = subprocess.check_output(cmd, shell=True).decode("utf-8") df = pd.read_csv("captions.txt") df['id'] = [id_ for id_ in range(df.shape[0] // 5) for _ in range(5)] df.to_csv("captions.csv", index=False) df = pd.read_csv("captions.csv") _, valid_df = make_train_valid_dfs() model, image_embeddings = get_image_embeddings(valid_df, "best.pt") examples = ["man and women on road"] def greet(query_text): print("Going to invoke inference_CLIP") return inference_CLIP(query_text) gallery = gr.Gallery( label="CLIP result images", show_label=True, elem_id="gallery", columns=[3], rows=[3], object_fit="contain", height="auto") demo = gr.Interface(fn=greet, inputs=gr.Dropdown(choices=examples, label="Search Image by text prompt"), outputs=gallery, title="OpenAI CLIP-Contrastive Language-Image Pre-training") demo.launch("debug")