face rectangle

chenshijun

2019-06-05 f111cb002b9c6065fdf6bb274ce5857a9e875e8c

 code/hopenet.py

@@ -4,44 +4,10 @@
import math
import torch.nn.functional as F

# CNN Model (2 conv layer)
class Simple_CNN(nn.Module):
    def __init__(self):
        super(Simple_CNN, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=3, padding=0),
            nn.BatchNorm2d(64),
            nn.ReLU(),
            nn.MaxPool2d(2))
        self.layer2 = nn.Sequential(
            nn.Conv2d(64, 128, kernel_size=3, padding=0),
            nn.BatchNorm2d(128),
            nn.ReLU(),
            nn.MaxPool2d(2))
        self.layer3 = nn.Sequential(
            nn.Conv2d(128, 256, kernel_size=3, padding=0),
            nn.BatchNorm2d(256),
            nn.ReLU(),
            nn.MaxPool2d(2))
        self.layer4 = nn.Sequential(
            nn.Conv2d(256, 512, kernel_size=3, padding=0),
            nn.BatchNorm2d(512),
            nn.ReLU(),
            nn.MaxPool2d(2))
        self.fc = nn.Linear(17*17*512, 3)

    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.layer4(out)
        out = out.view(out.size(0), -1)
        out = self.fc(out)
        return out

class Hopenet(nn.Module):
    # This is just Hopenet with 3 output layers for yaw, pitch and roll.
    def __init__(self, block, layers, num_bins, iter_ref):
    # Hopenet with 3 output layers for yaw, pitch and roll
    # Predicts Euler angles by binning and regression with the expected value
    def __init__(self, block, layers, num_bins):
        self.inplanes = 64
        super(Hopenet, self).__init__()
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
@@ -58,12 +24,8 @@
        self.fc_pitch = nn.Linear(512 * block.expansion, num_bins)
        self.fc_roll = nn.Linear(512 * block.expansion, num_bins)

        self.softmax = nn.Softmax()
        # Vestigial layer from previous experiments
        self.fc_finetune = nn.Linear(512 * block.expansion + 3, 3)

        self.idx_tensor = Variable(torch.FloatTensor(range(66))).cuda()

        self.iter_ref = iter_ref

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
@@ -107,27 +69,10 @@
        pre_pitch = self.fc_pitch(x)
        pre_roll = self.fc_roll(x)

        yaw = self.softmax(pre_yaw)
        yaw = Variable(torch.sum(yaw.data * self.idx_tensor.data, 1), requires_grad=True)
        pitch = self.softmax(pre_pitch)
        pitch = Variable(torch.sum(pitch.data * self.idx_tensor.data, 1), requires_grad=True)
        roll = self.softmax(pre_roll)
        roll = Variable(torch.sum(roll.data * self.idx_tensor.data, 1), requires_grad=True)
        yaw = yaw.view(yaw.size(0), 1)
        pitch = pitch.view(pitch.size(0), 1)
        roll = roll.view(roll.size(0), 1)
        angles = []
        preangles = torch.cat([yaw, pitch, roll], 1)
        angles.append(preangles)

        # angles predicts the residual
        for idx in xrange(self.iter_ref):
            angles.append(self.fc_finetune(torch.cat((preangles, x), 1)))

        return pre_yaw, pre_pitch, pre_roll, angles
        return pre_yaw, pre_pitch, pre_roll

class ResNet(nn.Module):

    # ResNet for regression of 3 Euler angles.
    def __init__(self, block, layers, num_classes=1000):
        self.inplanes = 64
        super(ResNet, self).__init__()
@@ -182,11 +127,11 @@
        x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        x = self.fc_angles(x)

        return x

class AlexNet(nn.Module):

    # AlexNet laid out as a Hopenet - classify Euler angles in bins and
    # regress the expected value.
    def __init__(self, num_bins):
        super(AlexNet, self).__init__()
        self.features = nn.Sequential(