轻松学Pytorch-全卷积神经网络实现表情识别

 1class ResidualBlock(torch.nn.Module):
 2    def __init__(self, in_channels, out_channels, stride=1):
 3        """
 4        Args:
 5          in_channels (int):  Number of input channels.
 6          out_channels (int): Number of output channels.
 7          stride (int):       Controls the stride.
 8        """
 9        super(ResidualBlock, self).__init__()
10
11        self.skip = torch.nn.Sequential()
12
13        if stride != 1 or in_channels != out_channels:
14            self.skip = torch.nn.Sequential(
15                torch.nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=1, stride=stride, bias=False),
16                torch.nn.BatchNorm2d(out_channels))
17
18        self.block = torch.nn.Sequential(
19            torch.nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=3, padding=1, stride=stride, bias=False),
20            torch.nn.BatchNorm2d(out_channels),
21            torch.nn.ReLU(),
22            torch.nn.Conv2d(in_channels=out_channels, out_channels=out_channels, kernel_size=3, padding=1, stride=1, bias=False),
23            torch.nn.BatchNorm2d(out_channels))
24
25    def forward(self, x):
26        out = self.block(x)
27        identity = self.skip(x)
28        out += identity
29        out = F.relu(out)
30        return out

 1class EmotionsResNet(torch.nn.Module):
 2    def __init__(self):
 3        super(EmotionsResNet, self).__init__()
 4        self.cnn_layers = torch.nn.Sequential(
 5            # 卷积层 (64x64x3的图像)
 6            ResidualBlock(3, 32, 1),
 7            ResidualBlock(32, 64, 2),
 8            ResidualBlock(64, 64, 2),
 9            ResidualBlock(64, 128, 2),
10            ResidualBlock(128, 128, 2),
11            ResidualBlock(128, 256, 2),
12            ResidualBlock(256, 256, 2),
13            ResidualBlock(256, 8, 1),
14        )
15
16    def forward(self, x):
17        # stack convolution layers
18        x = self.cnn_layers(x)
19
20        # Nx5x1x1
21        B, C, H, W = x.size()
22        out = x.view(B, -1)
23        return out

 1if __name__ == "__main__":
 2    # create a complete CNN
 3    model = EmotionsResNet()
 4    print(model)
 5
 6    # 使用GPU
 7    if train_on_gpu:
 8        model.cuda()
 9
10    ds = EmotionDataset("D:/facedb/emotion_dataset")
11    num_train_samples = ds.num_of_samples()
12    bs = 16
13    dataloader = DataLoader(ds, batch_size=bs, shuffle=True)
14
15    # 训练模型的次数
16    num_epochs = 15
17    # optimizer = torch.optim.SGD(model.parameters(), lr=0.001)
18    optimizer = torch.optim.Adam(model.parameters(), lr=1e-2)
19    model.train()
20
21    # 损失函数
22    mse_loss = torch.nn.MSELoss()
23    cross_loss = torch.nn.CrossEntropyLoss()
24    index = 0
25    for epoch in  range(num_epochs):
26        train_loss = 0.0
27        for i_batch, sample_batched in enumerate(dataloader):
28            images_batch, emotion_batch = \
29                sample_batched['image'], sample_batched['emotion']
30            if train_on_gpu:
31                images_batch, emotion_batch= images_batch.cuda(), emotion_batch.cuda()
32            optimizer.zero_grad()
33
34            # forward pass: compute predicted outputs by passing inputs to the model
35            m_emotion_out_ = model(images_batch)
36            emotion_batch = emotion_batch.long()
37
38            # calculate the batch loss
39            loss = cross_loss(m_emotion_out_, emotion_batch)
40
41            # backward pass: compute gradient of the loss with respect to model parameters
42            loss.backward()
43
44            # perform a single optimization step (parameter update)
45            optimizer.step()
46
47            # update training loss
48            train_loss += loss.item()
49            if index % 100 == 0:
50                print('step: {} \tTraining Loss: {:.6f} '.format(index, loss.item()))
51            index += 1
52
53            # 计算平均损失
54        train_loss = train_loss / num_train_samples
55
56        # 显示训练集与验证集的损失函数
57        print('Epoch: {} \tTraining Loss: {:.6f} '.format(epoch, train_loss))
58
59    # save model
60    model.eval()
61    torch.save(model, 'face_emotions_model.pt')

 1cnn_model = torch.load("./face_emotions_model.pt")
 2print(cnn_model)
 3# capture = cv.VideoCapture(0)
 4capture = cv.VideoCapture("D:/images/video/example_dsh.mp4")
 5
 6# load tensorflow model
 7net = cv.dnn.readNetFromTensorflow(model_bin, config=config_text)
 8while True:
 9    ret, frame = capture.read()
10    if ret is not True:
11        break
12    frame = cv.flip(frame, 1)
13    h, w, c = frame.shape
14    blobImage = cv.dnn.blobFromImage(frame, 1.0, (300, 300), (104.0, 177.0, 123.0), False, False);
15    net.setInput(blobImage)
16    cvOut = net.forward()
17    # 绘制检测矩形
18    for detection in cvOut[0,0,:,:]:
19        score = float(detection[2])
20        if score > 0.5:
21            left = detection[3]*w
22            top = detection[4]*h
23            right = detection[5]*w
24            bottom = detection[6]*h
25
26            # roi and detect landmark
27            roi = frame[np.int32(top):np.int32(bottom),np.int32(left):np.int32(right),:]
28            rw = right - left
29            rh = bottom - top
30            img = cv.resize(roi, (64, 64))
31            img = (np.float32(img) / 255.0 - 0.5) / 0.5
32            img = img.transpose((2, 0, 1))
33            x_input = torch.from_numpy(img).view(1, 3, 64, 64)
34            emotion_ = cnn_model(x_input.cuda())
35            predict_ = torch.max(emotion_, 1)[1].cpu().detach().numpy()[0]
36            emotion_txt = emotion_labels[predict_]
37            # 绘制
38            cv.putText(frame, ("%s"%(emotion_txt)), (int(left), int(top)-15), cv.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)
39            cv.rectangle(frame, (int(left), int(top)), (int(right), int(bottom)), (255, 0, 0), thickness=2)
40            c = cv.waitKey(10)
41            if c == 27:
42                break
43            cv.imshow("face detection + emotion", frame)
44
45cv.waitKey(0)
46cv.destroyAllWindows()