app.py

import os
os.system("pip install xtcocotools>=1.12")
os.system("pip install 'mmengine>=0.6.0'")
os.system("pip install 'mmcv>=2.0.0rc4,<2.1.0'")
os.system("pip install 'mmdet>=3.0.0,<4.0.0'")
os.system("pip install 'mmpose'")

import PIL
import cv2
import numpy as np

import torch
from mmpose.apis import MMPoseInferencer
from mmpose.apis import inference_topdown, init_model
from mmpose.utils import register_all_modules
register_all_modules()

import gradio as gr

import warnings

warnings.filterwarnings("ignore")

def save_image(img, img_path):
    # Convert PIL image to OpenCV image
    img = cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR)
    # Save OpenCV image
    cv2.imwrite(img_path, img)

def predict_pose(img):
    img_path = "input_img.jpg"
    save_image(img, img_path)

    result = mmpose_coco(img_path)
    keypoints = result[0].pred_instances['keypoints'][0]

    # Create a dictionary to store keypoints and their names
    keypoints_data = {
        'keypoints': keypoints.tolist(),
        'keypoint_names': [
            'nose',
            'left_eye',
            'right_eye',
            'left_ear',
            'right_ear',
            'left_shoulder',
            'right_shoulder',
            'left_elbow',
            'right_elbow',
            'left_wrist',
            'right_wrist',
            'left_hip',
            'right_hip',
            'left_knee',
            'right_knee',
            'left_ankle',
            'right_ankle'
        ]
    }
    return (img, keypoints_data)

def mmpose_coco(img_path, 
                config_file = 'mmpose/td-hm_hrnet-w48_8xb32-210e_coco-256x192.py', 
                checkpoint_file = 'mmpose/td-hm_hrnet-w48_8xb32-210e_coco-256x192-0e67c616_20220913.pth'):
    device = torch.cuda.current_device() if torch.cuda.is_available() else 'cpu'
    # coco keypoints: 
    # https://github.com/open-mmlab/mmpose/blob/master/mmpose/datasets/datasets/top_down/topdown_coco_dataset.py#L28
    model = init_model(config_file, checkpoint_file, device=device)
    results = inference_topdown(model, img_path)
    return results

# download_test_image()
input_image = gr.inputs.Image(type='pil', label="Original Image")
output_image = gr.outputs.Image(type="pil", label="Output Image")
output_text = gr.outputs.Textbox(label="Output Text")

title = "MMPose detection for ShopByShape"
iface = gr.Interface(fn=predict_pose, inputs=[input_image], outputs=[output_image, output_text], title=title)
iface.launch()