SSD Network Architecture Special Lyaers--keras version

"""Some special pupropse layers for SSD."""import keras.backend as Kfrom keras.engine.topology import InputSpecfrom keras.engine.topology import Layerimport numpy as npimport tensorflow as tfclass Normalize(Layer): ???"""Normalization layer as described in ParseNet paper. ???# Arguments ???????scale: Default feature scale. ???# Input shape ???????4D tensor with shape: ???????`(samples, channels, rows, cols)` if dim_ordering=‘th‘ ???????or 4D tensor with shape: ???????`(samples, rows, cols, channels)` if dim_ordering=‘tf‘. ???# Output shape ???????Same as input
 ???""" ???def __init__(self, scale, **kwargs): ???????if K.image_dim_ordering() == ‘tf‘: ???????????self.axis = 3 ???????else: ???????????self.axis = 1 ???????self.scale = scale ???????super(Normalize, self).__init__(**kwargs) ???def build(self, input_shape): ???????self.input_spec = [InputSpec(shape=input_shape)] ???????shape = (input_shape[self.axis],) ???????init_gamma = self.scale * np.ones(shape) ???????self.gamma = K.variable(init_gamma, name=‘{}_gamma‘.format(self.name)) ???????self.trainable_weights = [self.gamma] ???def call(self, x, mask=None): ???????output = K.l2_normalize(x, self.axis) ???????output *= self.gamma ???????return output
#上面这个层就不多说了，在keras中自定义Layer中以及详细介绍了，下面还是说说那个产生default box的层吧class PriorBox(Layer): ???"""Generate the prior boxes of designated sizes and aspect ratios. ???# Arguments ???????img_size: Size of the input image as tuple (w, h). ???????min_size: Minimum box size in pixels. ???????max_size: Maximum box size in pixels. ???????aspect_ratios: List of aspect ratios of boxes. ???????flip: Whether to consider reverse aspect ratios. ???????variances: List of variances for x, y, w, h. ???????clip: Whether to clip the prior‘s coordinates ???????????such that they are within [0, 1]. ???# Input shape ???????4D tensor with shape: ???????`(samples, channels, rows, cols)` if dim_ordering=‘th‘ ???????or 4D tensor with shape: ???????`(samples, rows, cols, channels)` if dim_ordering=‘tf‘. ???# Output shape ???????3D tensor with shape: ???????(samples, num_boxes, 8)
 ???""" ???def __init__(self, img_size, min_size, max_size=None, aspect_ratios=None, ????????????????flip=True, variances=[0.1], clip=True, **kwargs): ???????if K.image_dim_ordering() == ‘tf‘: ???????????self.waxis = 2 ???????????self.haxis = 1 ???????else: ???????????self.waxis = 3 ???????????self.haxis = 2 ???????self.img_size = img_size# ????????print "self.img_size"# ????????print self.img_size# ????????print "self.img_siez" ???????if min_size <= 0: ???????????raise Exception(‘min_size must be positive.‘) ???????self.min_size = min_size ???????self.max_size = max_size ???????self.aspect_ratios = [1.0] ???????if max_size: ???????????if max_size < min_size: ???????????????raise Exception(‘max_size must be greater than min_size.‘) ???????????self.aspect_ratios.append(1.0) ???????if aspect_ratios: ???????????for ar in aspect_ratios: ???????????????if ar in self.aspect_ratios: ???????????????????continue ???????????????self.aspect_ratios.append(ar) ???????????????if flip: ???????????????????self.aspect_ratios.append(1.0 / ar) ???????self.variances = np.array(variances) ???????self.clip = True ???????super(PriorBox, self).__init__(**kwargs) ???def get_output_shape_for(self, input_shape):# ????????print "input_shape start"# ????????print input_shape# ????????print "input_shape end" ???????num_priors_ = len(self.aspect_ratios)# ????????print "-----------------------------------"# ????????print num_priors ???????layer_width = input_shape[self.waxis]# ????????print layer_width ???????layer_height = input_shape[self.haxis]# ????????print layer_height# ????????print "----------------------------------" ???????num_boxes = num_priors_ * layer_width * layer_height# ????????print (input_shape[0], num_boxes, 8) ???????return (input_shape[0], num_boxes, 8) ???def call(self, x, mask=None):# ????????print dir(x) ???????if hasattr(x, ‘_keras_shape‘): ???????????input_shape = x._keras_shape# ????????????print "1" ???????elif hasattr(K, ‘int_shape‘): ???????????input_shape = K.int_shape(x)# ????????????print "2"# ????????print input_shape ???????layer_width = input_shape[self.waxis] ???????layer_height = input_shape[self.haxis] ???????img_width = self.img_size[0] ???????img_height = self.img_size[1]# ????????print img_width,img_height,layer_width,layer_height ???????# define prior boxes shapes ???????box_widths = [] ???????box_heights = []# ????????print self.min_size# ????????print self.aspect_ratios ???????for ar in self.aspect_ratios: ???????????if ar == 1 and len(box_widths) == 0: ???????????????box_widths.append(self.min_size) ???????????????box_heights.append(self.min_size) ???????????elif ar == 1 and len(box_widths) > 0: ???????????????box_widths.append(np.sqrt(self.min_size * self.max_size)) ???????????????box_heights.append(np.sqrt(self.min_size * self.max_size)) ???????????elif ar != 1: ???????????????box_widths.append(self.min_size * np.sqrt(ar)) ???????????????box_heights.append(self.min_size / np.sqrt(ar)) ???????box_widths = 0.5 * np.array(box_widths) ???????box_heights = 0.5 * np.array(box_heights)# ????????print len(box_widths)# ????????print len(box_heights) ???????# define centers of prior boxes ???????step_x = img_width / layer_width ???????step_y = img_height / layer_height# ????????print step_x,step_y# ????????print img_width,img_height ???????linx = np.linspace(0.5 * step_x, img_width - 0.5 * step_x, ??????????????????????????layer_width) ???????liny = np.linspace(0.5 * step_y, img_height - 0.5 * step_y, ??????????????????????????layer_height)# ????????print linx.shape,liny.shape ???????centers_x, centers_y = np.meshgrid(linx, liny) ???????centers_x = centers_x.reshape(-1, 1) ???????centers_y = centers_y.reshape(-1, 1)# ????????print centers_x.shape,centers_y.shape ???????# define xmin, ymin, xmax, ymax of prior boxes ???????num_priors_ = len(self.aspect_ratios)# ????????print num_priors ???????prior_boxes = np.concatenate((centers_x, centers_y), axis=1)# ????????print prior_boxes.shape ???????prior_boxes = np.tile(prior_boxes, (1, 2 * num_priors_))# ????????print prior_boxes.shape ???????prior_boxes[:, ::4] -= box_widths ???????prior_boxes[:, 1::4] -= box_heights ???????prior_boxes[:, 2::4] += box_widths ???????prior_boxes[:, 3::4] += box_heights ???????prior_boxes[:, ::2] /= img_width ???????prior_boxes[:, 1::2] /= img_height ???????prior_boxes = prior_boxes.reshape(-1, 4) ???????if self.clip: ???????????prior_boxes = np.minimum(np.maximum(prior_boxes, 0.0), 1.0) ???????# define variances ???????num_boxes = len(prior_boxes) ???????if len(self.variances) == 1: ???????????variances = np.ones((num_boxes, 4)) * self.variances[0] ???????elif len(self.variances) == 4: ???????????variances = np.tile(self.variances, (num_boxes, 1)) ???????else: ???????????raise Exception(‘Must provide one or four variances.‘) ???????prior_boxes = np.concatenate((prior_boxes, variances), axis=1) ???????prior_boxes_tensor = K.expand_dims(K.variable(prior_boxes), 0) ???????if K.backend() == ‘tensorflow‘: ???????????pattern = [tf.shape(x)[0], 1, 1] ???????????prior_boxes_tensor = tf.tile(prior_boxes_tensor, pattern) ???????elif K.backend() == ‘theano‘: ???????????#TODO ???????????pass# ????????print prior_boxes_tensor.shape ???????return prior_boxes_tensor# print dir(PriorBox((300,300),100))