app.py

import spaces
import gradio as gr
import subprocess
from PIL import Image
import json

import mp_box
'''
Face landmark detection based Face Detection.
https://ai.google.dev/edge/mediapipe/solutions/vision/face_landmarker
from model card
https://storage.googleapis.com/mediapipe-assets/MediaPipe%20BlazeFace%20Model%20Card%20(Short%20Range).pdf
Licensed Apache License, Version 2.0
Train with google's dataset(more detail see model card)


Not Face Detector based 
https://ai.google.dev/edge/mediapipe/solutions/vision/face_detector

Bacause this is part of getting-landmark program and need control face edge.
So I don't know which one is better.never compare these.
'''
#@spaces.GPU(duration=120)
def process_images(image,no_mesh_draw=False,square_shape=False,progress=gr.Progress(track_tqdm=True)):
    if image == None:
        raise gr.Error("Need Image")

    progress(0, desc="Start Mediapipe")
    
    boxes,mp_image,face_landmarker_result = mp_box.mediapipe_to_box(image)
    if no_mesh_draw:
         annotated_image = image
    else:
        annotated_image = mp_box.draw_landmarks_on_image(face_landmarker_result,image)
    annotation_boxes = []
    
    jsons ={
         
    }
    index = 1
    
    print(boxes)
    if square_shape:
        xy_boxes = boxes[3:]
    else:
        xy_boxes = boxes[:3]

    print(len(xy_boxes))
    for box in xy_boxes:
       label=f"type-{index}"
       print(box)
       print(mp_box.xywh_to_xyxy(box))
       annotation_boxes.append([mp_box.xywh_to_xyxy(box),label])
       
       
       jsons[label] = boxes[index-1]
       print(index)
       index+=1
    
    annotation_boxes.append(([0,0,1,1],"None"))
    #print(annotation_boxes)
    formatted_json = json.dumps(jsons, indent=1)
    #return image   
    return [annotated_image,annotation_boxes],formatted_json
    

def read_file(file_path: str) -> str:
    """read the text of target file
    """
    with open(file_path, 'r', encoding='utf-8') as f:
        content = f.read()

    return content

css="""
#col-left {
    margin: 0 auto;
    max-width: 640px;
}
#col-right {
    margin: 0 auto;
    max-width: 640px;
}
.grid-container {
  display: flex;
  align-items: center;
  justify-content: center;
  gap:10px
}

.image {
  width: 128px; 
  height: 128px; 
  object-fit: cover; 
}

.text {
  font-size: 16px;
}
"""

#css=css,

with gr.Blocks(css=css, elem_id="demo-container") as demo:
    with gr.Column():
        gr.HTML(read_file("demo_header.html"))
        gr.HTML(read_file("demo_tools.html"))
    with gr.Row():
                with gr.Column():
                    image = gr.Image(height=800,sources=['upload','clipboard'],image_mode='RGB',elem_id="image_upload", type="pil", label="Upload")
                    with gr.Row(elem_id="prompt-container",  equal_height=False):
                        with gr.Row():
                            btn = gr.Button("Face Detect", elem_id="run_button",variant="primary")
                    
                    with gr.Accordion(label="Advanced Settings", open=False):
                        with gr.Row( equal_height=True):
                            no_mesh_draw = gr.Checkbox(label="No Mesh Drawing")
                            square_shape = gr.Checkbox(label="Square shape")
                    
                with gr.Column():
                    image_out = gr.AnnotatedImage(label="Output", elem_id="output-img")
                    text_out = gr.TextArea(label="JSON-Output")
                    
                    
            

    btn.click(fn=process_images, inputs=[image,no_mesh_draw], outputs =[image_out,text_out], api_name='infer')
    gr.Examples(
                examples =["examples/00004200.jpg"],
                inputs=[image]
    )
    gr.HTML(read_file("demo_footer.html"))

    if __name__ == "__main__":
        demo.launch()