import torch from collections import OrderedDict import os import torch import torch.nn as nn import cv2 import numpy import numpy as np import math import time from scipy.ndimage.filters import gaussian_filter import matplotlib.pyplot as plt import matplotlib import torch from torchvision import transforms def transfer(model, model_weights): transfered_model_weights = {} for weights_name in model.state_dict().keys(): transfered_model_weights[weights_name] = model_weights['.'.join(weights_name.split('.')[1:])] return transfered_model_weights def padRightDownCorner(img, stride, padValue): h = img.shape[0] w = img.shape[1] pad = 4 * [None] pad[0] = 0 # up pad[1] = 0 # left pad[2] = 0 if (h % stride == 0) else stride - (h % stride) # down pad[3] = 0 if (w % stride == 0) else stride - (w % stride) # right img_padded = img pad_up = np.tile(img_padded[0:1, :, :]*0 + padValue, (pad[0], 1, 1)) img_padded = np.concatenate((pad_up, img_padded), axis=0) pad_left = np.tile(img_padded[:, 0:1, :]*0 + padValue, (1, pad[1], 1)) img_padded = np.concatenate((pad_left, img_padded), axis=1) pad_down = np.tile(img_padded[-2:-1, :, :]*0 + padValue, (pad[2], 1, 1)) img_padded = np.concatenate((img_padded, pad_down), axis=0) pad_right = np.tile(img_padded[:, -2:-1, :]*0 + padValue, (1, pad[3], 1)) img_padded = np.concatenate((img_padded, pad_right), axis=1) return img_padded, pad def make_layers(block, no_relu_layers): layers = [] for layer_name, v in block.items(): if 'pool' in layer_name: layer = nn.MaxPool2d(kernel_size=v[0], stride=v[1], padding=v[2]) layers.append((layer_name, layer)) else: conv2d = nn.Conv2d(in_channels=v[0], out_channels=v[1], kernel_size=v[2], stride=v[3], padding=v[4]) layers.append((layer_name, conv2d)) if layer_name not in no_relu_layers: layers.append(('relu_'+layer_name, nn.ReLU(inplace=True))) return nn.Sequential(OrderedDict(layers)) class bodypose_model(nn.Module): def __init__(self): super(bodypose_model, self).__init__() # these layers have no relu layer no_relu_layers = ['conv5_5_CPM_L1', 'conv5_5_CPM_L2', 'Mconv7_stage2_L1',\ 'Mconv7_stage2_L2', 'Mconv7_stage3_L1', 'Mconv7_stage3_L2',\ 'Mconv7_stage4_L1', 'Mconv7_stage4_L2', 'Mconv7_stage5_L1',\ 'Mconv7_stage5_L2', 'Mconv7_stage6_L1', 'Mconv7_stage6_L1'] blocks = {} block0 = OrderedDict([ ('conv1_1', [3, 64, 3, 1, 1]), ('conv1_2', [64, 64, 3, 1, 1]), ('pool1_stage1', [2, 2, 0]), ('conv2_1', [64, 128, 3, 1, 1]), ('conv2_2', [128, 128, 3, 1, 1]), ('pool2_stage1', [2, 2, 0]), ('conv3_1', [128, 256, 3, 1, 1]), ('conv3_2', [256, 256, 3, 1, 1]), ('conv3_3', [256, 256, 3, 1, 1]), ('conv3_4', [256, 256, 3, 1, 1]), ('pool3_stage1', [2, 2, 0]), ('conv4_1', [256, 512, 3, 1, 1]), ('conv4_2', [512, 512, 3, 1, 1]), ('conv4_3_CPM', [512, 256, 3, 1, 1]), ('conv4_4_CPM', [256, 128, 3, 1, 1]) ]) # Stage 1 block1_1 = OrderedDict([ ('conv5_1_CPM_L1', [128, 128, 3, 1, 1]), ('conv5_2_CPM_L1', [128, 128, 3, 1, 1]), ('conv5_3_CPM_L1', [128, 128, 3, 1, 1]), ('conv5_4_CPM_L1', [128, 512, 1, 1, 0]), ('conv5_5_CPM_L1', [512, 38, 1, 1, 0]) ]) block1_2 = OrderedDict([ ('conv5_1_CPM_L2', [128, 128, 3, 1, 1]), ('conv5_2_CPM_L2', [128, 128, 3, 1, 1]), ('conv5_3_CPM_L2', [128, 128, 3, 1, 1]), ('conv5_4_CPM_L2', [128, 512, 1, 1, 0]), ('conv5_5_CPM_L2', [512, 19, 1, 1, 0]) ]) blocks['block1_1'] = block1_1 blocks['block1_2'] = block1_2 self.model0 = make_layers(block0, no_relu_layers) # Stages 2 - 6 for i in range(2, 7): blocks['block%d_1' % i] = OrderedDict([ ('Mconv1_stage%d_L1' % i, [185, 128, 7, 1, 3]), ('Mconv2_stage%d_L1' % i, [128, 128, 7, 1, 3]), ('Mconv3_stage%d_L1' % i, [128, 128, 7, 1, 3]), ('Mconv4_stage%d_L1' % i, [128, 128, 7, 1, 3]), ('Mconv5_stage%d_L1' % i, [128, 128, 7, 1, 3]), ('Mconv6_stage%d_L1' % i, [128, 128, 1, 1, 0]), ('Mconv7_stage%d_L1' % i, [128, 38, 1, 1, 0]) ]) blocks['block%d_2' % i] = OrderedDict([ ('Mconv1_stage%d_L2' % i, [185, 128, 7, 1, 3]), ('Mconv2_stage%d_L2' % i, [128, 128, 7, 1, 3]), ('Mconv3_stage%d_L2' % i, [128, 128, 7, 1, 3]), ('Mconv4_stage%d_L2' % i, [128, 128, 7, 1, 3]), ('Mconv5_stage%d_L2' % i, [128, 128, 7, 1, 3]), ('Mconv6_stage%d_L2' % i, [128, 128, 1, 1, 0]), ('Mconv7_stage%d_L2' % i, [128, 19, 1, 1, 0]) ]) for k in blocks.keys(): blocks[k] = make_layers(blocks[k], no_relu_layers) self.model1_1 = blocks['block1_1'] self.model2_1 = blocks['block2_1'] self.model3_1 = blocks['block3_1'] self.model4_1 = blocks['block4_1'] self.model5_1 = blocks['block5_1'] self.model6_1 = blocks['block6_1'] self.model1_2 = blocks['block1_2'] self.model2_2 = blocks['block2_2'] self.model3_2 = blocks['block3_2'] self.model4_2 = blocks['block4_2'] self.model5_2 = blocks['block5_2'] self.model6_2 = blocks['block6_2'] def forward(self, x): out1 = self.model0(x) out1_1 = self.model1_1(out1) out1_2 = self.model1_2(out1) out2 = torch.cat([out1_1, out1_2, out1], 1) out2_1 = self.model2_1(out2) out2_2 = self.model2_2(out2) out3 = torch.cat([out2_1, out2_2, out1], 1) out3_1 = self.model3_1(out3) out3_2 = self.model3_2(out3) out4 = torch.cat([out3_1, out3_2, out1], 1) out4_1 = self.model4_1(out4) out4_2 = self.model4_2(out4) out5 = torch.cat([out4_1, out4_2, out1], 1) out5_1 = self.model5_1(out5) out5_2 = self.model5_2(out5) out6 = torch.cat([out5_1, out5_2, out1], 1) out6_1 = self.model6_1(out6) out6_2 = self.model6_2(out6) return out6_1, out6_2 class handpose_model(nn.Module): def __init__(self): super(handpose_model, self).__init__() # these layers have no relu layer no_relu_layers = ['conv6_2_CPM', 'Mconv7_stage2', 'Mconv7_stage3',\ 'Mconv7_stage4', 'Mconv7_stage5', 'Mconv7_stage6'] # stage 1 block1_0 = OrderedDict([ ('conv1_1', [3, 64, 3, 1, 1]), ('conv1_2', [64, 64, 3, 1, 1]), ('pool1_stage1', [2, 2, 0]), ('conv2_1', [64, 128, 3, 1, 1]), ('conv2_2', [128, 128, 3, 1, 1]), ('pool2_stage1', [2, 2, 0]), ('conv3_1', [128, 256, 3, 1, 1]), ('conv3_2', [256, 256, 3, 1, 1]), ('conv3_3', [256, 256, 3, 1, 1]), ('conv3_4', [256, 256, 3, 1, 1]), ('pool3_stage1', [2, 2, 0]), ('conv4_1', [256, 512, 3, 1, 1]), ('conv4_2', [512, 512, 3, 1, 1]), ('conv4_3', [512, 512, 3, 1, 1]), ('conv4_4', [512, 512, 3, 1, 1]), ('conv5_1', [512, 512, 3, 1, 1]), ('conv5_2', [512, 512, 3, 1, 1]), ('conv5_3_CPM', [512, 128, 3, 1, 1]) ]) block1_1 = OrderedDict([ ('conv6_1_CPM', [128, 512, 1, 1, 0]), ('conv6_2_CPM', [512, 22, 1, 1, 0]) ]) blocks = {} blocks['block1_0'] = block1_0 blocks['block1_1'] = block1_1 # stage 2-6 for i in range(2, 7): blocks['block%d' % i] = OrderedDict([ ('Mconv1_stage%d' % i, [150, 128, 7, 1, 3]), ('Mconv2_stage%d' % i, [128, 128, 7, 1, 3]), ('Mconv3_stage%d' % i, [128, 128, 7, 1, 3]), ('Mconv4_stage%d' % i, [128, 128, 7, 1, 3]), ('Mconv5_stage%d' % i, [128, 128, 7, 1, 3]), ('Mconv6_stage%d' % i, [128, 128, 1, 1, 0]), ('Mconv7_stage%d' % i, [128, 22, 1, 1, 0]) ]) for k in blocks.keys(): blocks[k] = make_layers(blocks[k], no_relu_layers) self.model1_0 = blocks['block1_0'] self.model1_1 = blocks['block1_1'] self.model2 = blocks['block2'] self.model3 = blocks['block3'] self.model4 = blocks['block4'] self.model5 = blocks['block5'] self.model6 = blocks['block6'] def forward(self, x): out1_0 = self.model1_0(x) out1_1 = self.model1_1(out1_0) concat_stage2 = torch.cat([out1_1, out1_0], 1) out_stage2 = self.model2(concat_stage2) concat_stage3 = torch.cat([out_stage2, out1_0], 1) out_stage3 = self.model3(concat_stage3) concat_stage4 = torch.cat([out_stage3, out1_0], 1) out_stage4 = self.model4(concat_stage4) concat_stage5 = torch.cat([out_stage4, out1_0], 1) out_stage5 = self.model5(concat_stage5) concat_stage6 = torch.cat([out_stage5, out1_0], 1) out_stage6 = self.model6(concat_stage6) return out_stage6 class Body(object): def __init__(self, model_path): self.model = bodypose_model() if torch.cuda.is_available(): self.model = self.model.cuda() print('cuda') model_dict = transfer(self.model, torch.load(model_path)) self.model.load_state_dict(model_dict) self.model.eval() def __call__(self, oriImg): # scale_search = [0.5, 1.0, 1.5, 2.0] scale_search = [0.5] boxsize = 368 stride = 8 padValue = 128 thre1 = 0.1 thre2 = 0.05 multiplier = [x * boxsize / oriImg.shape[0] for x in scale_search] heatmap_avg = np.zeros((oriImg.shape[0], oriImg.shape[1], 19)) paf_avg = np.zeros((oriImg.shape[0], oriImg.shape[1], 38)) for m in range(len(multiplier)): scale = multiplier[m] imageToTest = cv2.resize(oriImg, (0, 0), fx=scale, fy=scale, interpolation=cv2.INTER_CUBIC) imageToTest_padded, pad = padRightDownCorner(imageToTest, stride, padValue) im = np.transpose(np.float32(imageToTest_padded[:, :, :, np.newaxis]), (3, 2, 0, 1)) / 256 - 0.5 im = np.ascontiguousarray(im) data = torch.from_numpy(im).float() if torch.cuda.is_available(): data = data.cuda() # data = data.permute([2, 0, 1]).unsqueeze(0).float() with torch.no_grad(): Mconv7_stage6_L1, Mconv7_stage6_L2 = self.model(data) Mconv7_stage6_L1 = Mconv7_stage6_L1.cpu().numpy() Mconv7_stage6_L2 = Mconv7_stage6_L2.cpu().numpy() # extract outputs, resize, and remove padding # heatmap = np.transpose(np.squeeze(net.blobs[output_blobs.keys()[1]].data), (1, 2, 0)) # output 1 is heatmaps heatmap = np.transpose(np.squeeze(Mconv7_stage6_L2), (1, 2, 0)) # output 1 is heatmaps heatmap = cv2.resize(heatmap, (0, 0), fx=stride, fy=stride, interpolation=cv2.INTER_CUBIC) heatmap = heatmap[:imageToTest_padded.shape[0] - pad[2], :imageToTest_padded.shape[1] - pad[3], :] heatmap = cv2.resize(heatmap, (oriImg.shape[1], oriImg.shape[0]), interpolation=cv2.INTER_CUBIC) # paf = np.transpose(np.squeeze(net.blobs[output_blobs.keys()[0]].data), (1, 2, 0)) # output 0 is PAFs paf = np.transpose(np.squeeze(Mconv7_stage6_L1), (1, 2, 0)) # output 0 is PAFs paf = cv2.resize(paf, (0, 0), fx=stride, fy=stride, interpolation=cv2.INTER_CUBIC) paf = paf[:imageToTest_padded.shape[0] - pad[2], :imageToTest_padded.shape[1] - pad[3], :] paf = cv2.resize(paf, (oriImg.shape[1], oriImg.shape[0]), interpolation=cv2.INTER_CUBIC) heatmap_avg += heatmap_avg + heatmap / len(multiplier) paf_avg += + paf / len(multiplier) all_peaks = [] peak_counter = 0 for part in range(18): map_ori = heatmap_avg[:, :, part] one_heatmap = gaussian_filter(map_ori, sigma=3) map_left = np.zeros(one_heatmap.shape) map_left[1:, :] = one_heatmap[:-1, :] map_right = np.zeros(one_heatmap.shape) map_right[:-1, :] = one_heatmap[1:, :] map_up = np.zeros(one_heatmap.shape) map_up[:, 1:] = one_heatmap[:, :-1] map_down = np.zeros(one_heatmap.shape) map_down[:, :-1] = one_heatmap[:, 1:] peaks_binary = np.logical_and.reduce( (one_heatmap >= map_left, one_heatmap >= map_right, one_heatmap >= map_up, one_heatmap >= map_down, one_heatmap > thre1)) peaks = list(zip(np.nonzero(peaks_binary)[1], np.nonzero(peaks_binary)[0])) # note reverse peaks_with_score = [x + (map_ori[x[1], x[0]],) for x in peaks] peak_id = range(peak_counter, peak_counter + len(peaks)) peaks_with_score_and_id = [peaks_with_score[i] + (peak_id[i],) for i in range(len(peak_id))] all_peaks.append(peaks_with_score_and_id) peak_counter += len(peaks) # find connection in the specified sequence, center 29 is in the position 15 limbSeq = [[2, 3], [2, 6], [3, 4], [4, 5], [6, 7], [7, 8], [2, 9], [9, 10], \ [10, 11], [2, 12], [12, 13], [13, 14], [2, 1], [1, 15], [15, 17], \ [1, 16], [16, 18], [3, 17], [6, 18]] # the middle joints heatmap correpondence mapIdx = [[31, 32], [39, 40], [33, 34], [35, 36], [41, 42], [43, 44], [19, 20], [21, 22], \ [23, 24], [25, 26], [27, 28], [29, 30], [47, 48], [49, 50], [53, 54], [51, 52], \ [55, 56], [37, 38], [45, 46]] connection_all = [] special_k = [] mid_num = 10 for k in range(len(mapIdx)): score_mid = paf_avg[:, :, [x - 19 for x in mapIdx[k]]] candA = all_peaks[limbSeq[k][0] - 1] candB = all_peaks[limbSeq[k][1] - 1] nA = len(candA) nB = len(candB) indexA, indexB = limbSeq[k] if (nA != 0 and nB != 0): connection_candidate = [] for i in range(nA): for j in range(nB): vec = np.subtract(candB[j][:2], candA[i][:2]) norm = math.sqrt(vec[0] * vec[0] + vec[1] * vec[1]) norm = max(0.001, norm) vec = np.divide(vec, norm) startend = list(zip(np.linspace(candA[i][0], candB[j][0], num=mid_num), \ np.linspace(candA[i][1], candB[j][1], num=mid_num))) vec_x = np.array([score_mid[int(round(startend[I][1])), int(round(startend[I][0])), 0] \ for I in range(len(startend))]) vec_y = np.array([score_mid[int(round(startend[I][1])), int(round(startend[I][0])), 1] \ for I in range(len(startend))]) score_midpts = np.multiply(vec_x, vec[0]) + np.multiply(vec_y, vec[1]) score_with_dist_prior = sum(score_midpts) / len(score_midpts) + min( 0.5 * oriImg.shape[0] / norm - 1, 0) criterion1 = len(np.nonzero(score_midpts > thre2)[0]) > 0.8 * len(score_midpts) criterion2 = score_with_dist_prior > 0 if criterion1 and criterion2: connection_candidate.append( [i, j, score_with_dist_prior, score_with_dist_prior + candA[i][2] + candB[j][2]]) connection_candidate = sorted(connection_candidate, key=lambda x: x[2], reverse=True) connection = np.zeros((0, 5)) for c in range(len(connection_candidate)): i, j, s = connection_candidate[c][0:3] if (i not in connection[:, 3] and j not in connection[:, 4]): connection = np.vstack([connection, [candA[i][3], candB[j][3], s, i, j]]) if (len(connection) >= min(nA, nB)): break connection_all.append(connection) else: special_k.append(k) connection_all.append([]) # last number in each row is the total parts number of that person # the second last number in each row is the score of the overall configuration subset = -1 * np.ones((0, 20)) candidate = np.array([item for sublist in all_peaks for item in sublist]) for k in range(len(mapIdx)): if k not in special_k: partAs = connection_all[k][:, 0] partBs = connection_all[k][:, 1] indexA, indexB = np.array(limbSeq[k]) - 1 for i in range(len(connection_all[k])): # = 1:size(temp,1) found = 0 subset_idx = [-1, -1] for j in range(len(subset)): # 1:size(subset,1): if subset[j][indexA] == partAs[i] or subset[j][indexB] == partBs[i]: subset_idx[found] = j found += 1 if found == 1: j = subset_idx[0] if subset[j][indexB] != partBs[i]: subset[j][indexB] = partBs[i] subset[j][-1] += 1 subset[j][-2] += candidate[partBs[i].astype(int), 2] + connection_all[k][i][2] elif found == 2: # if found 2 and disjoint, merge them j1, j2 = subset_idx membership = ((subset[j1] >= 0).astype(int) + (subset[j2] >= 0).astype(int))[:-2] if len(np.nonzero(membership == 2)[0]) == 0: # merge subset[j1][:-2] += (subset[j2][:-2] + 1) subset[j1][-2:] += subset[j2][-2:] subset[j1][-2] += connection_all[k][i][2] subset = np.delete(subset, j2, 0) else: # as like found == 1 subset[j1][indexB] = partBs[i] subset[j1][-1] += 1 subset[j1][-2] += candidate[partBs[i].astype(int), 2] + connection_all[k][i][2] # if find no partA in the subset, create a new subset elif not found and k < 17: row = -1 * np.ones(20) row[indexA] = partAs[i] row[indexB] = partBs[i] row[-1] = 2 row[-2] = sum(candidate[connection_all[k][i, :2].astype(int), 2]) + connection_all[k][i][2] subset = np.vstack([subset, row]) # delete some rows of subset which has few parts occur deleteIdx = [] for i in range(len(subset)): if subset[i][-1] < 4 or subset[i][-2] / subset[i][-1] < 0.4: deleteIdx.append(i) subset = np.delete(subset, deleteIdx, axis=0) # subset: n*20 array, 0-17 is the index in candidate, 18 is the total score, 19 is the total parts # candidate: x, y, score, id return candidate, subset def sample_video_frames(video_path,): cap = cv2.VideoCapture(video_path) total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT)) frame_indices = np.linspace(0, total_frames - 1, total_frames, dtype=int) frames = [] for idx in frame_indices: cap.set(cv2.CAP_PROP_POS_FRAMES, idx) ret, frame = cap.read() if ret: if frame.shape[1] > 1024: frame = frame[:, 1440:, :] frame = cv2.resize(frame, (720, 480)) frames.append(frame) cap.release() return frames def process_image(pose_model, image_path): if isinstance(image_path, str): np_faceid_image = np.array(Image.open(image_path).convert("RGB")) elif isinstance(image_path, numpy.ndarray): np_faceid_image = image_path else: raise TypeError("image_path should be a string or PIL.Image.Image object") image_bgr = cv2.cvtColor(np_faceid_image, cv2.COLOR_RGB2BGR) candidate, subset = pose_model(image_bgr) pose_list = [] for c in candidate: pose_list.append([c[0], c[1]]) return pose_list def process_video(video_path, pose_model): video_frames = sample_video_frames(video_path,) print(len(video_frames)) pose_list = [] for frame in video_frames: # Convert to RGB once at the beginning frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB) pose = process_image(pose_model, frame_rgb) pose_list.append(pose) # break return pose_list def calculate_l1_distance(list1, list2): """ 计算两个列表的 L1 距离 :return: L1 距离 """ # 将列表转换为 NumPy 数组 list1 = np.array(list1) list2 = np.array(list2) min_d = min(list1.shape[0], list2.shape[0]) list1 = list1[:min_d, :] list2 = list2[:min_d, :] # 计算每对点的 L1 距离 l1_distances = np.abs(list1 - list2).sum(axis=1) # 返回所有点的 L1 距离之和 return l1_distances.sum() def calculate_pose(list1, list2): distance_list = [] for kps1 in list1: min_dis = (480 + 720) * 17 + 1 for kps2 in list2: try: min_dis = min(min_dis, calculate_l1_distance(kps1, kps2)) except: continue min_dis = min_dis/(480+720)/16 if min_dis > 1: continue distance_list.append(min_dis) if len(distance_list) > 0: return sum(distance_list)/len(distance_list) else: return 0. def main(): body_estimation = Body('eval/pose/body_pose_model.pth') device = "cuda" data_path = "data/SkyActor" # data_path = "data/LivePotraits" # data_path = "data/Actor-One" # data_path = "data/FollowYourEmoji" img_path = "/maindata/data/shared/public/rui.wang/act_review/driving_video" pre_tag = True mp4_list = os.listdir(data_path) print(mp4_list) img_list = [] video_list = [] for mp4 in mp4_list: if "mp4" not in mp4: continue if pre_tag: png_path = mp4.split('.')[0].split('-')[1] + ".mp4" else: if "-" in mp4: png_path = mp4.split('.')[0].split('-')[0] + ".mp4" else: png_path = mp4.split('.')[0].split('_')[0] + ".mp4" img_list.append(os.path.join(img_path, png_path)) video_list.append(os.path.join(data_path, mp4)) print(img_list) print(video_list[0]) pd_list = [] for i in range(len(img_list)): print("number: ", str(i), " total: ", len(img_list), data_path) pose_1 = process_video(video_list[i], body_estimation) pose_2 = process_video(img_list[i], body_estimation) dis = calculate_pose(pose_1, pose_2) print(dis) if dis > 0.0001: pd_list.append(dis) print("pose", sum(pd_list)/ len(pd_list)) main()