main.py

import mmpose
import os
import glob
from mmpose.apis import MMPoseInferencer
import gradio as gr
import numpy as np
import cv2

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

inferencers = {"Estimate human 2d poses":human, "Estimate human 2d hand poses":hand, "Estimate human 3d poses":human3d}

# inferencer = MMPoseInferencer('human')
# inferencer = MMPoseInferencer(pose3d="human3d")

# 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

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


def poses(photo, check):
    # Selecting the specific inferencer
    print(check)
    inferencer = inferencers[check[0]] # 'hand', 'human , device='cuda'

    print("[INFO]: Running inference!")
    #vis_out_dir
    result_generator = inferencer(photo, 
                                  vis_out_dir =".",
                                  return_vis=True,
                                  thickness=2,
                                  rebase_keypoint_height=True)    
    
    result = [result for result in result_generator] #next(result_generator)
    print(type(result))

    # print(["[INFO] Result from iterator: ", result])

    # for r in result_generator:
    #     print("[INFO] Single result: ", r)
    
    # print(type(r))
    # # Prepare to save video
    # output_file = os.path.join("output.mp4")

    # fourcc = cv2.VideoWriter_fourcc(*"mp4v")  # Codec for MP4 video
    # fps = 32
    # height = 480
    # width = 640
    # size = (width,height)

    # out_writer = cv2.VideoWriter(output_file, fourcc, fps, size)

    # for result in result_generator:
    #     print("[INFO] Result: ", result)
    #     frame = result["visualization"]
    #     out_writer.write(cv2.cvtColor(frame[0], cv2.COLOR_BGR2RGB))

    # print(os.listdir())
    # print("[INFO]: Visualizing results!")
    # print(os.listdir())
    # print()

    # out_writer.release()
    # cv2.destroyAllWindows() # Closing window
    output_files = glob.glob(os.path.join(".", "*.mp4"))
    print(output_files)
    # 00000.mp4
    # 000000.mp4
    print(os.listdir())

    return output_files[0]



# # specify detection model by alias
# # the available aliases include 'human', 'hand', 'face', 'animal',
# # as well as any additional aliases defined in mmdet
# inferencer = MMPoseInferencer(
#     # suppose the pose estimator is trained on custom dataset
#     pose2d='custom_human_pose_estimator.py',
#     pose2d_weights='custom_human_pose_estimator.pth',
#     det_model='human'
# )

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

    webcam = gr.Interface(
        fn=poses,
        inputs= [gr.Video(source="webcam"), check_web],
        outputs = gr.PlayableVideo(),  #file_types=['.mp4'] #gr.Video(),
        title = 'Pose estimation', 
        description = 'Pose estimation on video',
        allow_flagging=False
        )

    file = gr.Interface(
        poses,
        inputs = [gr.Video(source="upload"), check_file],
        outputs = 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()