3d姿态 mhformer 预测代码

预测并可视化代码

调整部分代码：

可视化推理：

mhformer 也是先进行人体检测，输出2d关键点，再估计3d关键点，

预测并可视化代码

需要注释掉plt.switch_backend('agg')

调整部分代码：

        output_dir_3D = output_dir +'pose3D/'os.makedirs(output_dir_3D, exist_ok=True)plt.show()# plt.savefig(output_dir_3D + str(('%04d'% i)) + '_3D.png', dpi=200, format='png', bbox_inches = 'tight')

可视化推理：

import sys
import argparse
import cv2
from demo.lib.preprocess import h36m_coco_format, revise_kpts
from demo.lib.hrnet.gen_kpts import gen_video_kpts as hrnet_pose
import os 
import numpy as np
import torch
import glob
from tqdm import tqdm
import copysys.path.append(os.getcwd())
from model.mhformer import Model
from common.camera import *import matplotlib
import matplotlib.pyplot as plt 
from mpl_toolkits.mplot3d import Axes3D
import matplotlib.gridspec as gridspec# plt.switch_backend('agg')
matplotlib.rcParams['pdf.fonttype'] = 42
matplotlib.rcParams['ps.fonttype'] = 42def show2Dpose(kps, img):connections = [[0, 1], [1, 2], [2, 3], [0, 4], [4, 5],[5, 6], [0, 7], [7, 8], [8, 9], [9, 10],[8, 11], [11, 12], [12, 13], [8, 14], [14, 15], [15, 16]]LR = np.array([0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0], dtype=bool)lcolor = (255, 0, 0)rcolor = (0, 0, 255)thickness = 3for j,c in enumerate(connections):start = map(int, kps[c[0]])end = map(int, kps[c[1]])start = list(start)end = list(end)cv2.line(img, (start[0], start[1]), (end[0], end[1]), lcolor if LR[j] else rcolor, thickness)cv2.circle(img, (start[0], start[1]), thickness=-1, color=(0, 255, 0), radius=3)cv2.circle(img, (end[0], end[1]), thickness=-1, color=(0, 255, 0), radius=3)return imgdef show3Dpose(vals, ax):ax.view_init(elev=15., azim=70)lcolor=(0,0,1)rcolor=(1,0,0)I = np.array( [0, 0, 1, 4, 2, 5, 0, 7,  8,  8, 14, 15, 11, 12, 8,  9])J = np.array( [1, 4, 2, 5, 3, 6, 7, 8, 14, 11, 15, 16, 12, 13, 9, 10])LR = np.array([0, 1, 0, 1, 0, 1, 0, 0, 0,   1,  0,  0,  1,  1, 0, 0], dtype=bool)for i in np.arange( len(I) ):x, y, z = [np.array( [vals[I[i], j], vals[J[i], j]] ) for j in range(3)]ax.plot(x, y, z, lw=2, color = lcolor if LR[i] else rcolor)RADIUS = 0.72RADIUS_Z = 0.7xroot, yroot, zroot = vals[0,0], vals[0,1], vals[0,2]ax.set_xlim3d([-RADIUS+xroot, RADIUS+xroot])ax.set_ylim3d([-RADIUS+yroot, RADIUS+yroot])ax.set_zlim3d([-RADIUS_Z+zroot, RADIUS_Z+zroot])ax.set_aspect('equal') # works fine in matplotlib==2.2.2 or 3.7.1white = (1.0, 1.0, 1.0, 0.0)ax.xaxis.set_pane_color(white) ax.yaxis.set_pane_color(white)ax.zaxis.set_pane_color(white)ax.tick_params('x', labelbottom = False)ax.tick_params('y', labelleft = False)ax.tick_params('z', labelleft = False)def get_pose2D(video_path, output_dir):cap = cv2.VideoCapture(video_path)width = cap.get(cv2.CAP_PROP_FRAME_WIDTH)height = cap.get(cv2.CAP_PROP_FRAME_HEIGHT)print('\nGenerating 2D pose...')with torch.no_grad():# the first frame of the video should be detected a personkeypoints, scores = hrnet_pose(video_path, det_dim=416, num_peroson=1, gen_output=True)keypoints, scores, valid_frames = h36m_coco_format(keypoints, scores)re_kpts = revise_kpts(keypoints, scores, valid_frames)print('Generating 2D pose successfully!')output_dir += 'input_2D/'os.makedirs(output_dir, exist_ok=True)output_npz = output_dir + 'keypoints.npz'np.savez_compressed(output_npz, reconstruction=keypoints)def img2video(video_path, output_dir):cap = cv2.VideoCapture(video_path)fps = int(cap.get(cv2.CAP_PROP_FPS)) + 5fourcc = cv2.VideoWriter_fourcc(*"mp4v")names = sorted(glob.glob(os.path.join(output_dir + 'pose/', '*.png')))img = cv2.imread(names[0])size = (img.shape[1], img.shape[0])videoWrite = cv2.VideoWriter(output_dir + video_name + '.mp4', fourcc, fps, size) for name in names:img = cv2.imread(name)videoWrite.write(img)videoWrite.release()def showimage(ax, img):ax.set_xticks([])ax.set_yticks([]) plt.axis('off')ax.imshow(img)def get_pose3D(video_path, output_dir):args, _ = argparse.ArgumentParser().parse_known_args()args.layers, args.channel, args.d_hid, args.frames = 3, 512, 1024, 351args.pad = (args.frames - 1) // 2args.previous_dir = 'checkpoint/pretrained/351'args.n_joints, args.out_joints = 17, 17## Reload model = Model(args).cuda()model_dict = model.state_dict()# Put the pretrained model of MHFormer in 'checkpoint/pretrained/351'model_path = sorted(glob.glob(os.path.join(args.previous_dir, '*.pth')))[0]pre_dict = torch.load(model_path)for name, key in model_dict.items():model_dict[name] = pre_dict[name]model.load_state_dict(model_dict)model.eval()## inputkeypoints = np.load(output_dir + 'input_2D/keypoints.npz', allow_pickle=True)['reconstruction']cap = cv2.VideoCapture(video_path)video_length = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))## 3Dprint('\nGenerating 3D pose...')output_3d_all = []for i in tqdm(range(video_length)):ret, img = cap.read()img_size = img.shape## input framesstart = max(0, i - args.pad)end =  min(i + args.pad, len(keypoints[0])-1)input_2D_no = keypoints[0][start:end+1]left_pad, right_pad = 0, 0if input_2D_no.shape[0] != args.frames:if i < args.pad:left_pad = args.pad - iif i > len(keypoints[0]) - args.pad - 1:right_pad = i + args.pad - (len(keypoints[0]) - 1)input_2D_no = np.pad(input_2D_no, ((left_pad, right_pad), (0, 0), (0, 0)), 'edge')joints_left =  [4, 5, 6, 11, 12, 13]joints_right = [1, 2, 3, 14, 15, 16]input_2D = normalize_screen_coordinates(input_2D_no, w=img_size[1], h=img_size[0])  input_2D_aug = copy.deepcopy(input_2D)input_2D_aug[ :, :, 0] *= -1input_2D_aug[ :, joints_left + joints_right] = input_2D_aug[ :, joints_right + joints_left]input_2D = np.concatenate((np.expand_dims(input_2D, axis=0), np.expand_dims(input_2D_aug, axis=0)), 0)input_2D = input_2D[np.newaxis, :, :, :, :]input_2D = torch.from_numpy(input_2D.astype('float32')).cuda()N = input_2D.size(0)## estimationoutput_3D_non_flip = model(input_2D[:, 0])output_3D_flip     = model(input_2D[:, 1])output_3D_flip[:, :, :, 0] *= -1output_3D_flip[:, :, joints_left + joints_right, :] = output_3D_flip[:, :, joints_right + joints_left, :] output_3D = (output_3D_non_flip + output_3D_flip) / 2output_3D = output_3D[0:, args.pad].unsqueeze(1) output_3D[:, :, 0, :] = 0post_out = output_3D[0, 0].cpu().detach().numpy()output_3d_all.append(post_out)rot =  [0.1407056450843811, -0.1500701755285263, -0.755240797996521, 0.6223280429840088]rot = np.array(rot, dtype='float32')post_out = camera_to_world(post_out, R=rot, t=0)post_out[:, 2] -= np.min(post_out[:, 2])input_2D_no = input_2D_no[args.pad]## 2Dimage = show2Dpose(input_2D_no, copy.deepcopy(img))output_dir_2D = output_dir +'pose2D/'os.makedirs(output_dir_2D, exist_ok=True)cv2.imwrite(output_dir_2D + str(('%04d'% i)) + '_2D.png', image)## 3Dfig = plt.figure( figsize=(9.6, 5.4))gs = gridspec.GridSpec(1, 1)gs.update(wspace=-0.00, hspace=0.05) ax = plt.subplot(gs[0], projection='3d')show3Dpose( post_out, ax)output_dir_3D = output_dir +'pose3D/'os.makedirs(output_dir_3D, exist_ok=True)plt.show()# plt.savefig(output_dir_3D + str(('%04d'% i)) + '_3D.png', dpi=200, format='png', bbox_inches = 'tight')## save 3D keypointsoutput_3d_all = np.stack(output_3d_all, axis = 0)os.makedirs(output_dir + 'output_3D/', exist_ok=True)output_npz = output_dir + 'output_3D/' + 'output_keypoints_3d.npz'np.savez_compressed(output_npz, reconstruction=output_3d_all)print('Generating 3D pose successfully!')## allimage_dir = 'results/' image_2d_dir = sorted(glob.glob(os.path.join(output_dir_2D, '*.png')))image_3d_dir = sorted(glob.glob(os.path.join(output_dir_3D, '*.png')))print('\nGenerating demo...')for i in tqdm(range(len(image_2d_dir))):image_2d = plt.imread(image_2d_dir[i])image_3d = plt.imread(image_3d_dir[i])## cropedge = (image_2d.shape[1] - image_2d.shape[0]) // 2image_2d = image_2d[:, edge:image_2d.shape[1] - edge]edge = 102image_3d = image_3d[edge:image_3d.shape[0] - edge, edge:image_3d.shape[1] - edge]## showfont_size = 12fig = plt.figure(figsize=(9.6, 5.4))ax = plt.subplot(121)showimage(ax, image_2d)ax.set_title("Input", fontsize = font_size)ax = plt.subplot(122)showimage(ax, image_3d)ax.set_title("Reconstruction", fontsize = font_size)## saveoutput_dir_pose = output_dir +'pose/'os.makedirs(output_dir_pose, exist_ok=True)plt.show()# plt.savefig(output_dir_pose + str(('%04d'% i)) + '_pose.png', dpi=200, bbox_inches = 'tight')if __name__ == "__main__":parser = argparse.ArgumentParser()parser.add_argument('--video', type=str, default='CUSTOM_390-1.mp4', help='input video')# parser.add_argument('--video', type=str, default='sample_video.mp4', help='input video')parser.add_argument('--gpu', type=str, default='0', help='input video')args = parser.parse_args()os.environ["CUDA_VISIBLE_DEVICES"] = args.gpuvideo_path = './demo/video/' + args.videovideo_name = video_path.split('/')[-1].split('.')[0]output_dir = './demo/output/' + video_name + '/'get_pose2D(video_path, output_dir)get_pose3D(video_path, output_dir)img2video(video_path, output_dir)print('Generating demo successful!')