vgg16_fast_rcnn.py

Go to the documentation of this file.

import chainer
import chainer.functions as F
import chainer.links as L


class VGG16FastRCNN(chainer.Chain):

    def __init__(self):
        super(self.__class__, self).__init__(
            conv1_1=L.Convolution2D(3, 64, 3, stride=1, pad=1),
            conv1_2=L.Convolution2D(64, 64, 3, stride=1, pad=1),

            conv2_1=L.Convolution2D(64, 128, 3, stride=1, pad=1),
            conv2_2=L.Convolution2D(128, 128, 3, stride=1, pad=1),

            conv3_1=L.Convolution2D(128, 256, 3, stride=1, pad=1),
            conv3_2=L.Convolution2D(256, 256, 3, stride=1, pad=1),
            conv3_3=L.Convolution2D(256, 256, 3, stride=1, pad=1),

            conv4_1=L.Convolution2D(256, 512, 3, stride=1, pad=1),
            conv4_2=L.Convolution2D(512, 512, 3, stride=1, pad=1),
            conv4_3=L.Convolution2D(512, 512, 3, stride=1, pad=1),

            conv5_1=L.Convolution2D(512, 512, 3, stride=1, pad=1),
            conv5_2=L.Convolution2D(512, 512, 3, stride=1, pad=1),
            conv5_3=L.Convolution2D(512, 512, 3, stride=1, pad=1),

            fc6=L.Linear(25088, 4096),
            fc7=L.Linear(4096, 4096),
            cls_score=L.Linear(4096, 21),
            bbox_pred=L.Linear(4096, 84)
        )

    def __call__(self, x, rois):
        h = F.relu(self.conv1_1(x))
        h = F.relu(self.conv1_2(h))
        h = F.max_pooling_2d(h, 2, stride=2)

        h = F.relu(self.conv2_1(h))
        h = F.relu(self.conv2_2(h))
        h = F.max_pooling_2d(h, 2, stride=2)

        h = F.relu(self.conv3_1(h))
        h = F.relu(self.conv3_2(h))
        h = F.relu(self.conv3_3(h))
        h = F.max_pooling_2d(h, 2, stride=2)

        h = F.relu(self.conv4_1(h))
        h = F.relu(self.conv4_2(h))
        h = F.relu(self.conv4_3(h))
        h = F.max_pooling_2d(h, 2, stride=2)

        h = F.relu(self.conv5_1(h))
        h = F.relu(self.conv5_2(h))
        h = F.relu(self.conv5_3(h))
        h = F.roi_pooling_2d(h, rois, 7, 7, spatial_scale=0.0625)

        h = F.dropout(F.relu(self.fc6(h)), ratio=0.5)
        h = F.dropout(F.relu(self.fc7(h)), ratio=0.5)
        cls_score = F.softmax(self.cls_score(h))
        bbox_pred = self.bbox_pred(h)

        return cls_score, bbox_pred