woo1

#!/usr/bin/env python
# pip uninstall opencv-python
# pip install -U opencv-contrib-python
# run with webcam : python charuco_webcam.py 0

import cv2
import numpy as np
import matplotlib.pyplot as plt

import glob

woo1

def _xywh2cs(x, y, w, h):
    center = np.zeros((2), dtype=np.float32)
    center[0] = x + (w - 1) * 0.5
    center[1] = y + (h - 1) * 0.5

    IMAGE_SIZE =[288, 384]
    aspect_ratio = IMAGE_SIZE[0] * 1.0 / IMAGE_SIZE[1]
    pixel_std = 200

    if w > aspect_ratio * h:

woo1

import numpy as np

def get_max_preds(batch_heatmaps):
    '''
    get predictions from score maps
    heatmaps: numpy.ndarray([batch_size, num_joints, height, width])
    '''
    assert isinstance(batch_heatmaps, np.ndarray), \
        'batch_heatmaps should be numpy.ndarray'
    assert batch_heatmaps.ndim == 4, 'batch_images should be 4-ndim'

woo1

import torch
import torch.nn as nn

# MNIST - 0~1 분류, Discriminator
D = nn.Sequential(
    nn.Linear(784, 128), 
    nn.ReLU(),
    nn.Linear(128, 1),
    nn.Sigmoid()
)

woo1

import pickle
import numpy as np
import os.path as osp
import glob
import argparse

if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--pare_rslt_dir', type=str, default='',
                        help='')

woo1

# reference : https://jangjy.tistory.com/336
import pickle

with open('data.pkl', 'rb') as f:
    # data = pickle.load(f)
    u = pickle._Unpickler(f)
    u.encoding = 'latin1'
    p = u.load()
    print(p)

woo1

import torch.nn as nn
import spconv
import torch.nn.functional as F
import torch
from lib.config import cfg
from . import embedder
from spconv.pytorch.modules import SparseModule, SparseSequential
from spconv.pytorch.conv import SubMConv3d, SparseConv3d
from spconv.pytorch.core import SparseConvTensor

woo1

import torch
import numpy as np
import sys
import os
sys.path.append(os.getcwd())
from bodymocap.body_mocap_api import BodyMocap
import pickle
import joblib
import os.path as osp
import trimesh

woo1

How to visualize the body part segmentation from smpl-x output?

This script lets you to visualize the body part segmentation labels of SMPL-X body models. Follow the instructions to be able to run this script.

Instructions

1. Download the body models you would like to visualize.
2. Install the requirements
3. Run python visualize_body_part_segmentation.py <body_model> <body_model_path> <parameter_file_path>

An example command python visualize_body_part_segmentation.py smplx data/body_models/smplx output_data_path.pkl

woo1

from __future__ import absolute_import, division

import torch
from torch import nn


class GlobalGraph(nn.Module):
    """"
    Global graph attention layer
    """