ssd-300 代码分析

学习ssd笔记
Github地址: https://github.com/balancap/SSD-Tensorflow

Created with Raphaël 2.1.0 ssd_net ssd_multibox_layer: ssd_bboxes_select: bboxes_clip bboxes_sort bboxes_nms bboxes_resize

ssd_net: basic network
multibox_layer: chose [‘block4’, ‘block7’, ‘block8’, ‘block9’, ‘block10’, ‘block11’] to calculate Classes and Boxes
ssd_bboxes_select: 选择一部分的框，（第一层判定大于threshold的框）
bboxes_clip： 防止框大于图片
bboxes_sort： 排序并最多选择k个（默认k=400）
bboxes_nms：将overlap重复度高的合并（保留其中一个）
ssd_net

        feat_layers=['block4', 'block7', 'block8', 'block9', 'block10', 'block11'],


    with tf.variable_scope(scope, 'ssd_300_vgg', [inputs], reuse=reuse):
        # Original VGG-16 blocks.
        net = slim.repeat(inputs, 2, slim.conv2d, 64, [3, 3], scope='conv1')
        end_points['block1'] = net
        net = slim.max_pool2d(net, [2, 2], scope='pool1')
        # Block 2.
        net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3], scope='conv2')
        end_points['block2'] = net
        net = slim.max_pool2d(net, [2, 2], scope='pool2')
        # Block 3.
        net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3], scope='conv3')
        end_points['block3'] = net
        net = slim.max_pool2d(net, [2, 2], scope='pool3')
        # Block 4.
        net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv4')
        end_points['block4'] = net
        net = slim.max_pool2d(net, [2, 2], scope='pool4')
        # Block 5.
        net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv5')
        end_points['block5'] = net
        net = slim.max_pool2d(net, [3, 3], stride=1, scope='pool5')

        # Additional SSD blocks.
        # Block 6: let's dilate the hell out of it!
        net = slim.conv2d(net, 1024, [3, 3], rate=6, scope='conv6')
        end_points['block6'] = net
        net = tf.layers.dropout(net, rate=dropout_keep_prob, training=is_training)
        # Block 7: 1x1 conv. Because the fuck.
        net = slim.conv2d(net, 1024, [1, 1], scope='conv7')
        end_points['block7'] = net
        net = tf.layers.dropout(net, rate=dropout_keep_prob, training=is_training)

        # Block 8/9/10/11: 1x1 and 3x3 convolutions stride 2 (except lasts).
        end_point = 'block8'
        with tf.variable_scope(end_point):
            net = slim.conv2d(net, 256, [1, 1], scope='conv1x1')
            net = custom_layers.pad2d(net, pad=(1, 1))
            net = slim.conv2d(net, 512, [3, 3], stride=2, scope='conv3x3', padding='VALID')
        end_points[end_point] = net
        end_point = 'block9'
        with tf.variable_scope(end_point):
            net = slim.conv2d(net, 128, [1, 1], scope='conv1x1')
            net = custom_layers.pad2d(net, pad=(1, 1))
            net = slim.conv2d(net, 256, [3, 3], stride=2, scope='conv3x3', padding='VALID')
        end_points[end_point] = net
        end_point = 'block10'
        with tf.variable_scope(end_point):
            net = slim.conv2d(net, 128, [1, 1], scope='conv1x1')
            net = slim.conv2d(net, 256, [3, 3], scope='conv3x3', padding='VALID')
        end_points[end_point] = net
        end_point = 'block11'
        with tf.variable_scope(end_point):
            net = slim.conv2d(net, 128, [1, 1], scope='conv1x1')
            net = slim.conv2d(net, 256, [3, 3], scope='conv3x3', padding='VALID')
        end_points[end_point] = net

        # Prediction and localisations layers.
        predictions = []
        logits = []
        localisations = []
        for i, layer in enumerate(feat_layers):
            with tf.variable_scope(layer + '_box'):
                p, l = ssd_multibox_layer(end_points[layer],
                                          num_classes,
                                          anchor_sizes[i],
                                          anchor_ratios[i],
                                          normalizations[i])
            predictions.append(prediction_fn(p))
            # prediction_fn is slim_softmax()
            logits.append(p)
            localisations.append(l)

def ssd_multibox_layer(inputs,
                       num_classes,
                       sizes,
                       ratios=[1],
                       normalization=-1,
                       bn_normalization=False):
    """Construct a multibox layer, return a class and localization predictions.
    """
    net = inputs
    if normalization > 0:
        net = custom_layers.l2_normalization(net, scaling=True)
    # Number of anchors.
    num_anchors = len(sizes) + len(ratios)

    # Location.
    num_loc_pred = num_anchors * 4
    loc_pred = slim.conv2d(net, num_loc_pred, [3, 3], activation_fn=None,
                           scope='conv_loc')
    loc_pred = custom_layers.channel_to_last(loc_pred)
    loc_pred = tf.reshape(loc_pred,
                          tensor_shape(loc_pred, 4)[:-1]+[num_anchors, 4])
    # Class prediction.
    num_cls_pred = num_anchors * num_classes
    cls_pred = slim.conv2d(net, num_cls_pred, [3, 3], activation_fn=None,
                           scope='conv_cls')
    cls_pred = custom_layers.channel_to_last(cls_pred)
    cls_pred = tf.reshape(cls_pred,
                          tensor_shape(cls_pred, 4)[:-1]+[num_anchors, num_classes])
    return cls_pred, loc_pred