How to find Keypoints inference position information? ex. x,y,z coordinates

[seon-creator]

Hello, I'm using mmpose for my project.
I want to know how to find keypoint position information.
I'm using body model and path is
/mmpose/configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/coco/hrnet_w32_coco_256x192.py

For image inference, I used this : /mmpose/demo/top_down_img_demo.py

Copyright (c) OpenMMLab. All rights reserved.

import os
import warnings
from argparse import ArgumentParser

import mmcv
from xtcocotools.coco import COCO

from mmpose.apis import (inference_top_down_pose_model, init_pose_model,
vis_pose_result)
from mmpose.datasets import DatasetInfo

def main():
"""Visualize the demo images.

Require the json_file containing boxes.
"""
parser = ArgumentParser()
parser.add_argument('pose_config', help='Config file for detection')
parser.add_argument('pose_checkpoint', help='Checkpoint file')
parser.add_argument('--img-root', type=str, default='', help='Image root')
parser.add_argument(
    '--json-file',
    type=str,
    default='',
    help='Json file containing image info.')
parser.add_argument(
    '--show',
    action='store_true',
    default=False,
    help='whether to show img')
parser.add_argument(
    '--out-img-root',
    type=str,
    default='',
    help='Root of the output img file. '
    'Default not saving the visualization images.')
parser.add_argument(
    '--device', default='cuda:0', help='Device used for inference')
parser.add_argument(
    '--kpt-thr', type=float, default=0.3, help='Keypoint score threshold')
parser.add_argument(
    '--radius',
    type=int,
    default=6,
    help='Keypoint radius for visualization')
parser.add_argument(
    '--thickness',
    type=int,
    default=1,
    help='Link thickness for visualization')

args = parser.parse_args()

assert args.show or (args.out_img_root != '')

coco = COCO(args.json_file)
# build the pose model from a config file and a checkpoint file
pose_model = init_pose_model(
    args.pose_config, args.pose_checkpoint, device=args.device.lower())

dataset = pose_model.cfg.data['test']['type']
dataset_info = pose_model.cfg.data['test'].get('dataset_info', None)
if dataset_info is None:
    warnings.warn(
        'Please set `dataset_info` in the config.'
        'Check https://github.com/open-mmlab/mmpose/pull/663 for details.',
        DeprecationWarning)
else:
    dataset_info = DatasetInfo(dataset_info)

img_keys = list(coco.imgs.keys())

# optional
return_heatmap = False

# e.g. use ('backbone', ) to return backbone feature
output_layer_names = None

# process each image
for i in mmcv.track_iter_progress(range(len(img_keys))):
    # get bounding box annotations
    image_id = img_keys[i]
    image = coco.loadImgs(image_id)[0]
    image_name = os.path.join(args.img_root, image['file_name'])
    ann_ids = coco.getAnnIds(image_id)

    # make person bounding boxes
    person_results = []
    for ann_id in ann_ids:
        person = {}
        ann = coco.anns[ann_id]
        # bbox format is 'xywh'
        person['bbox'] = ann['bbox']
        person_results.append(person)

    # test a single image, with a list of bboxes
    pose_results, returned_outputs = inference_top_down_pose_model(
        pose_model,
        image_name,
        person_results,
        bbox_thr=None,
        format='xywh',
        dataset=dataset,
        dataset_info=dataset_info,
        return_heatmap=return_heatmap,
        outputs=output_layer_names)

    if args.out_img_root == '':
        out_file = None
    else:
        os.makedirs(args.out_img_root, exist_ok=True)
        out_file = os.path.join(args.out_img_root, image['file_name'])
        #out_file = os.path.join(args.out_img_root, f'vis_{i}.jpg')
        

    vis_pose_result(
        pose_model,
        image_name,
        pose_results,
        dataset=dataset,
        dataset_info=dataset_info,
        kpt_score_thr=args.kpt_thr,
        radius=args.radius,
        thickness=args.thickness,
        show=args.show,
        out_file=out_file)

if name == 'main':
main()

After using weight and .json for model keypoint inference of image, I can get Image with keypoints displayed, but I don't know what their position information. How to find out?

[Ben-Louis]

Hi, thanks for using MMPose. Saving inference results is only supported in the new version of MMPose (1.0.0+). To save the model predictions when using demo scripts, you can simply add the --save-predictions argument.

[seon-creator]

Thank you so much! I'll try it.
I'm looking for updates versions, which python version is required to mmpose?

[Ben-Louis]

We recommend using Python version 3.8 or higher. For lower versions, there might be some compatibility problems, although we have not thoroughly tested it.