def __init__(self, phase, base, extras, head, num_classes): super(SSD, self).__init__() self.phase = phase self.num_classes = num_classes # TODO: implement __call__ in PriorBox self.priorbox = PriorBox(v2) # PyTorch 1.5.1 # self.priors = Variable(self.priorbox.forward(), volatile=True) self.priors = self.priorbox.forward() self.size = 300 # SSD network self.vgg = nn.ModuleList(base) # Layer learns to scale the l2 normalized features from conv4_3 self.L2Norm = L2Norm(512, 20) self.extras = nn.ModuleList(extras) self.loc = nn.ModuleList(head[0]) self.conf = nn.ModuleList(head[1]) if phase == 'test': # PyTorch 1.5.1 # self.softmax = nn.Softmax() # self.detect = Detect(num_classes, 0, 200, 0.01, 0.45) self.softmax = nn.Softmax(dim=-1) self.detect = Detect()
def __init__(self, phase, base, extras, head, num_classes): super(SSD, self).__init__() self.phase = phase self.num_classes = num_classes # TODO: implement __call__ in PriorBox self.priorbox = PriorBox(v2) self.priors = Variable(self.priorbox.forward(), volatile=True) self.size = 512 # SSD network self.vgg = nn.ModuleList(base) # Layer learns to scale the l2 normalized features from conv4_3 self.L2Norm = L2Norm(512, 20) self.extras = nn.ModuleList(extras) # fused conv4_3 and conv5_3 self.conv3_3 = nn.Conv2d(256, 256, 3, 1, 1) self.conv4_3 = nn.Conv2d(512, 512, 3, 1, 1) self.deconv = nn.ConvTranspose2d(512, 512, 2, 2) self.deconv2 = nn.ConvTranspose2d(512, 256, 2, 2) self.conv5_3 = nn.Conv2d(512, 512, 3, 1, 1) self.L2Norm5_3 = L2Norm(512, 10) self.L2Norm3_3 = L2Norm(256, 20) self.loc = nn.ModuleList(head[0]) self.conf = nn.ModuleList(head[1]) if self.phase == 'test': self.softmax = nn.Softmax() self.detect = Detect(num_classes, 0, 300, 0.01, 0.45)
def __init__(self, phase, size, base, extras, head, num_classes): super(SSD, self).__init__() self.phase = phase self.num_classes = num_classes self.cfg = { 'num_classes': 21, 'lr_steps': (80000, 100000, 120000), 'max_iter': 120000, 'feature_maps': [38, 19, 10, 5, 3, 1], 'min_dim': 300, 'steps': [8, 16, 32, 64, 100, 300], 'min_sizes': [30, 60, 111, 162, 213, 264], 'max_sizes': [60, 111, 162, 213, 264, 315], 'aspect_ratios': [[2], [2, 3], [2, 3], [2, 3], [2], [2]], 'variance': [0.1, 0.2], 'clip': True, 'name': 'VOC', } self.priorbox = PriorBox(self.cfg) with torch.no_grad(): self.priors = Variable(self.priorbox.forward()) self.size = size # SSD network self.vgg = nn.ModuleList(base) self.L2Norm = L2Norm(512, 20) self.extras = nn.ModuleList(extras) self.loc = nn.ModuleList(head[0]) self.conf = nn.ModuleList(head[1]) if phase == 'test': self.softmax = nn.Softmax(dim=-1) self.detect = Detect(num_classes, 0, 200, 0.01, 0.45)
def __init__(self, phase, base, head, num_classes): super(MSC, self).__init__() self.phase = phase self.num_classes = num_classes self.priorbox = PriorBox(v2) self.priors = Variable(self.priorbox.forward(), volatile=True) self.size = 512 self.vgg = nn.ModuleList(base) self.L2Norm4_3 = L2Norm(512, 20) self.L2Norm5_3 = L2Norm(512, 10) self.deconv7 = nn.ConvTranspose2d(2048, 2048, 2, 2) self.deconv6 = nn.ConvTranspose2d(2048, 512, 2, 2) self.deconv5 = nn.ConvTranspose2d(512, 512, 2, 2) self.conv_fc6 = nn.Conv2d(2048, 2048, 3, 1, 1) self.conv5_3 = nn.Conv2d(512, 512, 3, 1, 1) self.conv4_3 = nn.Conv2d(512, 512, 3, 1, 1) self.loc = nn.ModuleList(head[0]) self.conf = nn.ModuleList(head[1]) if self.phase == 'test': self.softmax = nn.Softmax() self.detect = Detect(num_classes, 0, 300, 0.01, 0.45)
def __init__(self, phase, basenet, head, num_classes): super(TibNet, self).__init__() self.phase = phase self.num_classes = num_classes self.sa = mobilefacenet.SpatialAttention() self.base = nn.ModuleList(basenet) self.upfeat = [] for it in range(5): self.upfeat.append(upsample(in_channels=64, out_channels=64)) self.upfeat = nn.ModuleList(self.upfeat) self.loc = nn.ModuleList(head[0]) self.conf = nn.ModuleList(head[1]) if self.phase == 'test': self.softmax = nn.Softmax(dim=-1) self.detect = Detect(cfg)
def __init__(self, phase, base, head, num_classes): super(STDN, self).__init__() self.phase = phase self.num_classes = num_classes self.size = 512 # 没有用 self.priorbox = PriorBox(v2) self.priors = Variable(self.priorbox.forward(), volatile=True) self.basenet = nn.ModuleList(base) self.loc = nn.ModuleList(head[0]) self.conf = nn.ModuleList(head[1]) self.out1 = nn.AvgPool2d(9, 9) self.out2 = nn.AvgPool2d(3, 3) self.out3 = nn.AvgPool2d(2, 2) if self.phase == 'test': self.softmax = nn.Softmax() self.detect = Detect(num_classes, 0, 300, 0.01, 0.45)
def __init__(self, phase, base, head, num_classes): super(EXTD, self).__init__() self.phase = phase self.num_classes = num_classes # SSD network self.base = nn.ModuleList(base) self.upfeat = [] for it in range(5): self.upfeat.append(upsample(in_channels=48, out_channels=48)) self.upfeat = nn.ModuleList(self.upfeat) self.loc = nn.ModuleList(head[0]) self.conf = nn.ModuleList(head[1]) if self.phase == 'test': self.softmax = nn.Softmax(dim=-1) self.detect = Detect(cfg)
def __init__(self, phase, base, head, num_classes): super(EXTD, self).__init__() self.phase = phase self.num_classes = num_classes ''' self.priorbox = PriorBox(size,cfg) self.priors = Variable(self.priorbox.forward(), volatile=True) ''' # SSD network self.base = nn.ModuleList(base) self.upfeat = [] for it in range(5): self.upfeat.append(upsample(in_channels=32, out_channels=32)) self.upfeat = nn.ModuleList(self.upfeat) self.loc = nn.ModuleList(head[0]) self.conf = nn.ModuleList(head[1]) if self.phase == 'test': self.softmax = nn.Softmax(dim=-1) self.detect = Detect(cfg)
def __init__(self, phase, size, base, extras, head, num_classes): super(SSD, self).__init__() self.phase = phase self.num_classes = num_classes self.cfg = voc # (coco, voc)[num_classes == 21] self.priorbox = PriorBox(self.cfg) self.priors = self.priorbox.forward( ) # Generate default boxes (anchors) self.size = size # SSD network self.vgg = nn.ModuleList(base) # Layer learns to scale the l2 normalized features from conv4_3 self.L2Norm = L2Norm(512, 20) self.extras = nn.ModuleList(extras) self.loc = nn.ModuleList(head[0]) self.conf = nn.ModuleList(head[1]) if phase == 'test': self.softmax = nn.Softmax(dim=-1) self.detect = Detect(num_classes, 0, 200, 0.01, 0.45)
class SSD(nn.Module): """Single Shot Multibox Architecture The network is composed of a base VGG network followed by the added multibox conv layers. Each multibox layer branches into 1) conv2d for class conf scores 2) conv2d for localization predictions 3) associated priorbox layer to produce default bounding boxes specific to the layer's feature map size. See: https://arxiv.org/pdf/1512.02325.pdf for more details. Args: phase: (string) Can be "test" or "train" base: VGG16 layers for input, size of either 300 or 500 extras: extra layers that feed to multibox loc and conf layers head: "multibox head" consists of loc and conf conv layers """ def __init__(self, phase, base, extras, head, num_classes): super(SSD, self).__init__() self.phase = phase self.num_classes = num_classes # TODO: implement __call__ in PriorBox self.priorbox = PriorBox(v2) # PyTorch 1.5.1 # self.priors = Variable(self.priorbox.forward(), volatile=True) self.priors = self.priorbox.forward() self.size = 300 # SSD network self.vgg = nn.ModuleList(base) # Layer learns to scale the l2 normalized features from conv4_3 self.L2Norm = L2Norm(512, 20) self.extras = nn.ModuleList(extras) self.loc = nn.ModuleList(head[0]) self.conf = nn.ModuleList(head[1]) if phase == 'test': # PyTorch 1.5.1 # self.softmax = nn.Softmax() # self.detect = Detect(num_classes, 0, 200, 0.01, 0.45) self.softmax = nn.Softmax(dim=-1) self.detect = Detect() def forward(self, x): """Applies network layers and ops on input image(s) x. Args: x: input image or batch of images. Shape: [batch,3*batch,300,300]. Return: Depending on phase: test: Variable(tensor) of output class label predictions, confidence score, and corresponding location predictions for each object detected. Shape: [batch,topk,7] train: list of concat outputs from: 1: confidence layers, Shape: [batch*num_priors,num_classes] 2: localization layers, Shape: [batch,num_priors*4] 3: priorbox layers, Shape: [2,num_priors*4] """ sources = list() loc = list() conf = list() # apply vgg up to conv4_3 relu for k in range(23): x = self.vgg[k](x) s = self.L2Norm(x) sources.append(s) # apply vgg up to fc7 for k in range(23, len(self.vgg)): x = self.vgg[k](x) sources.append(x) # apply extra layers and cache source layer outputs for k, v in enumerate(self.extras): x = F.relu(v(x), inplace=True) if k % 2 == 1: sources.append(x) # apply multibox head to source layers for (x, l, c) in zip(sources, self.loc, self.conf): loc.append(l(x).permute(0, 2, 3, 1).contiguous()) conf.append(c(x).permute(0, 2, 3, 1).contiguous()) loc = torch.cat([o.view(o.size(0), -1) for o in loc], 1) conf = torch.cat([o.view(o.size(0), -1) for o in conf], 1) if self.phase == "test": # PyTorch 1.5.1 # output = self.detect( # loc.view(loc.size(0), -1, 4), # loc preds # self.softmax(conf.view(-1, self.num_classes)), # conf preds # self.priors.type(type(x.data)) # default boxes # ) output = self.detect.apply( self.num_classes, 0, 200, 0.01, 0.45, loc.view(loc.size(0), -1, 4), # loc preds self.softmax(conf.view(-1, self.num_classes)), # conf preds self.priors.type(type(x.data)) # default boxes ) else: output = (loc.view(loc.size(0), -1, 4), conf.view(conf.size(0), -1, self.num_classes), self.priors) return output def load_weights(self, base_file): other, ext = os.path.splitext(base_file) if ext == '.pkl' or '.pth': print('Loading weights into state dict...') self.load_state_dict( torch.load(base_file, map_location=lambda storage, loc: storage)) print('Finished!') else: print('Sorry only .pth and .pkl files supported.')
def __init__(self, phase, num_classes): super(BlazeFace, self).__init__() self.firstconv = nn.Sequential( nn.Conv2d(in_channels=2, out_channels=16, kernel_size=3, stride=2, padding=1), nn.BatchNorm2d(16), nn.ReLU(inplace=True), ) self.blazeBlock = nn.Sequential( BlazeBlock(in_channels=16, out_channels=16), # BlazeBlock(in_channels=24, out_channels=24), BlazeBlock(in_channels=16, out_channels=32, stride=2), # BlazeBlock(in_channels=48, out_channels=48), BlazeBlock(in_channels=32, out_channels=32), ) self.doubleBlazeBlock = nn.Sequential( DoubleBlazeBlock(in_channels=32, out_channels=64, mid_channels=16, stride=2), # DoubleBlazeBlock(in_channels=96, out_channels=96, mid_channels=24), DoubleBlazeBlock(in_channels=64, out_channels=64, mid_channels=16), ) self.conv2d_8x8_classificators = nn.Sequential( nn.Conv2d(in_channels=64, out_channels=6, kernel_size=1, stride=1), nn.BatchNorm2d(6), ) self.conv2d_16x16_classificators = nn.Sequential( nn.Conv2d(in_channels=64, out_channels=2, kernel_size=1, stride=1), nn.BatchNorm2d(2), ) self.conv2d_8x8_regressors = nn.Sequential( nn.Conv2d(in_channels=64, out_channels=64, kernel_size=1, stride=1), nn.BatchNorm2d(64), ) self.conv2d_16x16_regressors = nn.Sequential( nn.Conv2d(in_channels=64, out_channels=32, kernel_size=1, stride=1), nn.BatchNorm2d(32), ) self.phase = phase self.cfg = celeba self.priorbox = PriorBox(self.cfg) self.num_classes = num_classes # self.priors = Variable(self.priorbox.forward(), volatile=True) if phase == 'test': self.softmax = nn.Softmax(dim=-1) self.detect = Detect(self.num_classes, 0, 200, 0.01, 0.45) with torch.no_grad(): self.priors = self.priorbox.forward() print(self.priors.shape) self.initialize()
def main(input_path, output_path, detection_model_path='weights/WIDERFace_DSFD_RES152.pt'): cuda = True torch.set_grad_enabled(False) device = torch.device('cuda:{}'.format(0)) if cuda and torch.cuda.is_available(): torch.set_default_tensor_type('torch.cuda.FloatTensor') else: torch.set_default_tensor_type('torch.FloatTensor') # Initialize detection model # cfg = widerface_640 # thresh = cfg['conf_thresh'] # net = build_ssd('test', cfg['min_dim'], cfg['num_classes']) # initialize SSD # net.load_state_dict(torch.load(detection_model_path)) # net = net.cuda() # net.eval() cfg = widerface_640 thresh = cfg['conf_thresh'] net = torch.jit.load(detection_model_path, map_location=device) net.eval() print('Finished loading detection model!') transform = TestBaseTransform((104, 117, 123)) detect = Detect(cfg['num_classes'], 0, cfg['num_thresh'], cfg['conf_thresh'], cfg['nms_thresh']) # Open target video file cap = cv2.VideoCapture(input_path) if not cap.isOpened(): raise RuntimeError('Failed to read video: ' + input_path) total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT)) fps = cap.get(cv2.CAP_PROP_FPS) target_vid_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)) target_vid_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT)) # Calculate priors image_size = (target_vid_height, target_vid_width) featuremap_size = [(math.ceil(image_size[0] / (2 ** (2 + i))), math.ceil(image_size[1] / (2 ** (2 + i)))) for i in range(6)] priors = get_prior_boxes(cfg, featuremap_size, image_size).to(device) # Initialize output video file if output_path is not None: if os.path.isdir(output_path): output_filename = os.path.splitext(os.path.basename(input_path))[0] + '.mp4' output_path = os.path.join(output_path, output_filename) fourcc = cv2.VideoWriter_fourcc(*'x264') out_vid = cv2.VideoWriter(output_path, fourcc, fps, (target_vid_width, target_vid_height)) else: out_vid = None # max_im_shrink = ((2000.0 * 2000.0) / (target_vid_height * target_vid_width)) ** 0.5 shrink = max_im_shrink if max_im_shrink < 1 else 1 # For each frame in the video for i in tqdm(range(total_frames)): ret, frame = cap.read() if frame is None: continue # Process frame_tensor = torch.from_numpy(transform(frame)[0]).permute(2, 0, 1).unsqueeze(0).to(device) # image_size = frame_tensor.shape[2:] # featuremap_size = [(math.ceil(image_size[0] / (2 ** (2 + i))), math.ceil(image_size[1] / (2 ** (2 + i)))) # for i in range(6)] # priors = get_prior_boxes(cfg, featuremap_size, image_size).to(device) pred = net(frame_tensor) detections = detect(pred[:, :, :4], pred[:, :, 4:], priors) det = [] shrink = 1.0 scale = torch.Tensor([image_size[1] / shrink, image_size[0] / shrink, image_size[1] / shrink, image_size[0] / shrink]) for i in range(detections.size(1)): j = 0 while detections[0, i, j, 0] >= thresh: curr_det = detections[0, i, j, [1, 2, 3, 4, 0]].cpu().numpy() curr_det[:4] *= scale.cpu().numpy() det.append(curr_det) j += 1 # curr_det[:4] *= scale # score = detections[0, i, j, 0] # # label_name = labelmap[i-1] # pt = (detections[0, i, j, 1:] * scale).cpu().numpy() # coords = (pt[0], pt[1], pt[2], pt[3]) # det.append([pt[0], pt[1], pt[2], pt[3], score]) # j += 1 det = np.row_stack((det)) # if det.shape[0] > 1: # det = bbox_vote(det.astype(float)) det = np.round(det[det[:, 4] > 0.5, :4]).astype(int) # # Render render_img = frame for rect in det: # cv2.rectangle(render_img, tuple(rect[:2]), tuple(rect[:2] + rect[2:]), (0, 0, 255), 1) cv2.rectangle(render_img, tuple(rect[:2]), tuple(rect[2:]), (0, 0, 255), 1) if out_vid is not None: out_vid.write(render_img) cv2.imshow('render_img', render_img) if cv2.waitKey(1) & 0xFF == ord('q'): break