main.py

# Pose inferencing
import mmpose
from mmpose.apis import MMPoseInferencer

# Ultralytics
#from ultralytics import YOLO

# Gradio
import gradio as gr

# System and files
import os
import glob
import uuid

# Image manipulation
import numpy as np
import cv2

print("[INFO]: Imported modules!")
human = MMPoseInferencer("human")
hand = MMPoseInferencer("hand")
human3d = MMPoseInferencer(pose3d="human3d")
# ultraltics

# Defining inferencer models to lookup in function
inferencers = {"Estimate human 2d poses":human, "Estimate human 2d hand poses":hand, "Estimate human 3d poses":human3d}

#track_model = YOLO('yolov8n.pt')  # Load an official Detect model

print("[INFO]: Downloaded models!")

def tracking(video, model, boxes=True):
    print("[INFO] Loading model...")
    # Load an official or custom model

    # Perform tracking with the model
    print("[INFO] Starting tracking!")
    # https://docs.ultralytics.com/modes/predict/
    annotated_frame = model(video, device="cuda", boxes=boxes)

    return annotated_frame



def poses(photo, check):
    # Selecting the specific inferencer
    out_files=[]
    for i in check:
        inferencer = inferencers[i] # 'hand', 'human , device='cuda'

        print("[INFO]: Running inference!")
        # Create out directory
        vis_out_dir = str(uuid.uuid4())

        result_generator = inferencer(photo, 
                                    vis_out_dir = vis_out_dir,
                                    return_vis=True,
                                    thickness=2,
                                    rebase_keypoint_height=True)    
        
        result = [result for result in result_generator] #next(result_generator)    

        out_file = glob.glob(os.path.join(vis_out_dir, "*.mp4"))
        # 00000.mp4
        # 000000.mp4
        out_files.append(out_file)

    return out_files

def run():
    #https://github.com/open-mmlab/mmpose/blob/main/docs/en/user_guides/inference.md
    check_web =  gr.CheckboxGroup(choices = ["Estimate human 2d poses", "Estimate human 2d hand poses", "Estimate human 3d poses"], label="Methods", type="value", info="Select the model(s) you want")
    check_file = gr.CheckboxGroup(choices = ["Estimate human 2d poses", "Estimate human 2d hand poses", "Estimate human 3d poses"], label="Methods", type="value", info="Select the model(s) you want")

    webcam = gr.Interface(
        fn=poses,
        inputs= [gr.Video(source="webcam", height=412), check_web],
        outputs = [gr.PlayableVideo(), gr.PlayableVideo(), gr.PlayableVideo()],
        title = 'Pose estimation', 
        description = 'Pose estimation on video',
        allow_flagging=False
        )

    file = gr.Interface(
        poses,
        inputs = [gr.Video(source="upload", height=412), check_file],
        outputs = [gr.PlayableVideo(),gr.PlayableVideo(),gr.PlayableVideo()],
        allow_flagging=False
    )

    demo = gr.TabbedInterface(
            interface_list=[file, webcam],
            tab_names=["From a File", "From your Webcam"]
        )

    demo.launch(server_name="0.0.0.0", server_port=7860)


if __name__ == "__main__":
    run()

# https://github.com/open-mmlab/mmpose/tree/dev-1.x/configs/body_3d_keypoint/pose_lift
# motionbert_ft_h36m-d80af323_20230531.pth
# simple3Dbaseline_h36m-f0ad73a4_20210419.pth
# videopose_h36m_243frames_fullconv_supervised_cpn_ft-88f5abbb_20210527.pth
# videopose_h36m_81frames_fullconv_supervised-1f2d1104_20210527.pth
# videopose_h36m_27frames_fullconv_supervised-fe8fbba9_20210527.pth
# videopose_h36m_1frame_fullconv_supervised_cpn_ft-5c3afaed_20210527.pth
# https://github.com/open-mmlab/mmpose/blob/main/mmpose/apis/inferencers/pose3d_inferencer.py