import torch import torch.nn as nn import math import sys import os from utils import landmark_processor import cv2 import numpy as np output_points = 137 * 2 input_size = 192 def op_name(op_name, m): m.op_name = op_name return m class Flatten(nn.Module): def __init__(self, axis): super(Flatten, self).__init__() self.axis = axis def forward(self, x): assert self.axis == 1 x = x.reshape(x.shape[0], -1) return x def flatten(name, axis): return op_name(name, Flatten(axis)) def conv_bn_relu(name, in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, momentum = 0.1, track_running_stats=True): return nn.Sequential( op_name(name, nn.Conv2d(in_channels, out_channels, kernel_size, stride, padding, dilation, groups, False)), op_name(name + '/bn', nn.BatchNorm2d(out_channels, momentum = momentum, track_running_stats = track_running_stats)), op_name(name + '/relu', nn.ReLU(inplace=True)), ) def linear_bn_relu(name, in_features, out_features, momentum = 0.1, track_running_stats=True): return nn.Sequential( op_name(name + '/FC', nn.Linear(in_features, out_features)), op_name(name + '/bn', nn.BatchNorm1d(out_features, momentum = momentum, track_running_stats = track_running_stats)), op_name(name + '/relu', nn.ReLU(inplace=True)), ) # Define a Basic resnet block class BasicResnetBlock(nn.Module): def __init__(self, name, in_channels, out_channels, kernel_size=3, stride=2, padding=1, direct_plus=False): super(BasicResnetBlock, self).__init__() self.op_name = name self.conv_block = nn.Sequential( conv_bn_relu(name=name + '/conv1', in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size, stride=stride, padding=padding), conv_bn_relu(name=name + '/conv2', in_channels=out_channels, out_channels=out_channels, kernel_size=3, stride=1, padding=1) ) if direct_plus and (in_channels == out_channels) and (stride == 1): self.sc_block = None else: self.sc_block = conv_bn_relu(name=name + '/sc_conv', in_channels=in_channels, out_channels=out_channels, kernel_size=1, stride=stride, padding=0) def forward(self, x): if self.sc_block is None: out = x + self.conv_block(x) else: out = self.conv_block(x) + self.sc_block(x) return out #define SuperBigResNet Frame class SuperBigResNet(nn.Module): def __init__(self, name='SuperBigResNet', in_channels=3, out_channels=137 * 2): super(SuperBigResNet, self).__init__() self.op_name = name op_list = [] stride_cnt = 2 op_list += [conv_bn_relu(name + '/first_conv', in_channels, 48, kernel_size=5, stride=2, padding=2)] ch_num = [48, 64, 96, 128, 192] for i in range(len(ch_num) - 1): if ch_num[i] == ch_num[i+1]: op_list += [BasicResnetBlock(name + '/stage%d'%(i + 1), ch_num[i], ch_num[i+1], kernel_size=3, stride=1, direct_plus=True)] else: stride_cnt = stride_cnt * 2 op_list += [BasicResnetBlock(name + '/stage%d'%(i + 1), ch_num[i], ch_num[i+1], kernel_size=3, stride=2)] item_cnt = int((input_size / stride_cnt) * (input_size / stride_cnt) * ch_num[-1]) op_list += [flatten(name + '/flatten', 1), linear_bn_relu(name + '/FC1', item_cnt, 512), op_name(name + '/FC2', nn.Linear(512, out_channels))] self.conv_block = nn.Sequential(*op_list) def forward(self, x): res = self.conv_block(x) return res.cpu().numpy() class MomocvFaceAlignmentBigger(object): def __init__(self, gpu_id=None): self.gpu_id = gpu_id self.device = torch.device('cuda:{}'.format(gpu_id) if gpu_id is not None else 'cpu') self.face_alignment_net = SuperBigResNet('SuperBigResNet', 3, 137 * 2) self.model_path, _ = os.path.split(os.path.realpath(__file__)) weights = torch.load(os.path.join(self.model_path, 'SuperBigResNet_latest.pth'), map_location=lambda storage, loc: storage) self.face_alignment_net.load_state_dict(weights) self.face_alignment_net.to(self.device) self.face_alignment_net.eval() self.trackingFaceRects = [] def detect(self, img, landmarks): dst_size = 192 landmarks_res = [] with torch.no_grad(): input_numpy = np.zeros((len(landmarks), 3, dst_size, dst_size), dtype=np.float32) all_mat = [] for ix, landmark in enumerate(landmarks): M = landmark_processor.get_transform_mat_mmcv_bigger(landmark, dst_size) all_mat.append(M) tmp = cv2.warpAffine(img, M, (dst_size, dst_size)) input_numpy[ix, :, :, :] = tmp.transpose((2, 0, 1)).astype(np.float32) # cv2.imshow('tmp', tmp) # cv2.waitKey() in_tensor = torch.from_numpy(input_numpy) in_tensor = in_tensor.to(self.device) fullyconnected1 = self.face_alignment_net(in_tensor) for ix, pts in enumerate(fullyconnected1): orig_pts = (np.reshape(pts, (2, 137)).transpose((1, 0)) * dst_size) orig_pts = landmark_processor.transform_points(orig_pts, all_mat[ix], invert=True) landmarks_res.append(orig_pts) return landmarks_res def stable_forward(self, image, detected_faces, reset=False): if reset is True: self.trackingFaceRects = [] for face_rect in detected_faces: if len(self.trackingFaceRects) == 0: new_tracking_rect = [face_rect, True, [0, 0], 0, None] self.trackingFaceRects.append(new_tracking_rect) with torch.no_grad(): landmarks = [] for tracking_face_rect in self.trackingFaceRects: if tracking_face_rect[1] == True: d = tracking_face_rect[0] src_center = np.array([d[2] - (d[2] - d[0]) / 2.0, d[3] - (d[3] - d[1]) / 2.0]) rotate_degree = tracking_face_rect[3] scale = 192 * 0.6 / min(d[2] - d[0], d[3] - d[1]) dst_center = np.array([0.5, 0.5]) * 192 offset = dst_center - src_center print('hello') M = cv2.getRotationMatrix2D((src_center[0], src_center[1]), rotate_degree, scale) M[:, 2] += offset else: # dst_left_anchor = np.array([0.403, 0.52]) * 192 # dst_right_anchor = np.array([1 - 0.403, 0.52]) * 192 # # use last anchors # src_center = (tracking_face_rect[2][0] + tracking_face_rect[2][1]) / 2 # rotate_radian = math.atan2(tracking_face_rect[2][1][1] - tracking_face_rect[2][0][1], tracking_face_rect[2][1][0] - tracking_face_rect[2][0][0]) # rotate_degree = rotate_radian / math.pi * 180 # print('degree', rotate_degree) # dst_anchor_len = cv2.norm(dst_left_anchor - dst_right_anchor) # src_anchor_len = cv2.norm(tracking_face_rect[2][2], tracking_face_rect[2][3]) # scale = 71.0 / src_anchor_len # # # bounding_box = cv2.boundingRect(np.array(tracking_face_rect[2])) # # a = bounding_box[2] * bounding_box[3] # # print('a', a) # # scale = float(65*65) / (bounding_box[2] * bounding_box[3]) # # print('scale', scale) # # dst_center = (dst_left_anchor + dst_right_anchor) / 2 # offset = dst_center - src_center rotate_degree = 0 M = landmark_processor.get_transform_mat_mmcv_bigger(tracking_face_rect[4], 192) inp = cv2.warpAffine(image, M, (192, 192)) orig_inp = inp inp = inp.transpose((2, 0, 1)).astype(np.float32) inp = inp[np.newaxis, :, :, :] t0 = cv2.getTickCount() in_tensor = torch.from_numpy(inp) in_tensor = in_tensor.to(self.device) fullyconnected1 = self.face_alignment_net(in_tensor) fullyconnected1 = fullyconnected1[0] orig_pts = (np.reshape(fullyconnected1, (2, 137)).transpose((1, 0)) * 192) t2 = cv2.getTickCount() # print('cost', (t2 - t0) / cv2.getTickFrequency() * 1000) # for ix, pt in enumerate(orig_pts): # cv2.putText(orig_inp, str(ix), (int(pt[0]), int(pt[1])), cv2.FONT_HERSHEY_SIMPLEX, 0.3, (255, 0, 0)) # cv2.circle(orig_inp, (int(pt[0]), int(pt[1])), 1, (0, 255, 0), 1) # cv2.imshow('inp_stable', orig_inp) # cv2.waitKey() orig_pts = landmark_processor.transform_points(orig_pts, M, invert=True) # orig_pts = orig_pts.transpose((1, 0)) fullyconnected1 = orig_pts # update tracking infos tracking_face_rect[1] = False tracking_face_rect[2] = [fullyconnected1[68], fullyconnected1[74], fullyconnected1[96], fullyconnected1[113]] tracking_face_rect[3] = rotate_degree tracking_face_rect[4] = fullyconnected1 landmarks.append(fullyconnected1) return landmarks if __name__=='__main__': pass