mask_rcnn-2.0 网页链接：https://github.com/matterport/mask_rcnn/releases/tag/v2.0
mask_rcnn-master（matterport / mask_rcnn）网页链接：https://github.com/matterport/mask_rcnn
操作步骤
本文假设运行环境满足基本需求：python = 3.6.8, tensorflow-gpu = 1.12.0, keras = 2.0.8, matplotlib = 3.1.0……实验完成期间，需要安装许多依赖包，如：pycocotools, opencv-python, jupyter 等，请根据需求自行下载，如果程序运行期间出现相关错误，请查看依赖包版本是否正确。
下载 mask_rcnn-master 并解压，打开 anaconda prompt 进入运行环境，找到 mask_rcnn-master 项目下 demo.ipynb 所在的位置，并进入目录，输入“jupyter notebook”。
在 jupyter 中运行 demo.ipynb。第一遍运行时，程序会自动下载 mask_rcnn_coco.h5，所以时间会久一点，请耐心等待。运行结果如下：
从程序的运行结果中可以看出，输入一张图片，我们能够得到程序检测与分割的结果，但是无法获得每个 region 的特征（feature map）。
许多使用者在 issues 模块向项目作者提出了“想要获取 feature map”这一需求，例如：#1190，#1249，#1456。终于，kielnino 在 #1456 中给出了一个“改进后”的 model.py 文件。由于下载此文件需要翻越长城，我在此贴下代码，供大家使用。
"""
mask r-cnn
the main mask r-cnn model implementation. 凯发真人娱乐 copyright (c) 2017 matterport, inc.
licensed under the mit license (see license for details)
written by waleed abdulla
""" import os
import random
import datetime
import re
import math
import logging
from collections import ordereddict
import multiprocessing
import numpy as np
import tensorflow as tf
import keras
import keras.backend as k
import keras.layers as kl
import keras.engine as ke
import keras.models as km from mrcnn import utils # requires tensorflow 1.3 and keras 2.0.8 .
from distutils.version import looseversion
assert looseversion(tf.__version__) >= looseversion("1.3")
assert looseversion(keras.__version__) >= looseversion('2.0.8') ############################################################
# utility functions
############################################################ def log(text, array=none):
"""prints a text message. and, optionally, if a numpy array is provided it
prints it's shape, min, and max values.
"""
if array is not none:
text = text.ljust(25)
text = ("shape: {:20} ".format(str(array.shape)))
if array.size:
text = ("min: {:10.5f} max: {:10.5f}".format(array.min(),array.max()))
else:
text = ("min: {:10} max: {:10}".format("",""))
text = " {}".format(array.dtype)
print(text) class batchnorm(kl.batchnormalization):
"""extends the keras batchnormalization class to allow a central place
to make changes if needed. batch normalization has a negative effect on training if batches are small
so this layer is often frozen (via setting in config class) and functions
as linear layer.
"""
def call(self, inputs, training=none):
"""
note about training values:
none: train bn layers. this is the normal mode
false: freeze bn layers. good when batch size is small
true: (don't use). set layer in training mode even when making inferences
"""
return super(self.__class__, self).call(inputs, training=training) def compute_backbone_shapes(config, image_shape):
"""computes the width and height of each stage of the backbone network. returns:
[n, (height, width)]. where n is the number of stages
"""
if callable(config.backbone):
return config.compute_backbone_shape(image_shape) # currently supports resnet only
assert config.backbone in ["resnet50", "resnet101"]
return np.array(
[[int(math.ceil(image_shape[0] / stride)),
int(math.ceil(image_shape[1] / stride))]
for stride in config.backbone_strides]) ############################################################
# resnet graph
############################################################ # code adopted from:
# https://github.com/fchollet/deep-learning-models/blob/master/resnet50.py def identity_block(input_tensor, kernel_size, filters, stage, block,
use_bias=true, train_bn=true):
"""the identity_block is the block that has no conv layer at shortcut
# arguments
input_tensor: input tensor
kernel_size: default 3, the kernel size of middle conv layer at main path
filters: list of integers, the nb_filters of 3 conv layer at main path
stage: integer, current stage label, used for generating layer names
block: 'a','b'..., current block label, used for generating layer names
use_bias: boolean. to use or not use a bias in conv layers.
train_bn: boolean. train or freeze batch norm layers
"""
nb_filter1, nb_filter2, nb_filter3 = filters
conv_name_base = 'res' str(stage) block '_branch'
bn_name_base = 'bn' str(stage) block '_branch' x = kl.conv2d(nb_filter1, (1, 1), name=conv_name_base '2a',
use_bias=use_bias)(input_tensor)
x = batchnorm(name=bn_name_base '2a')(x, training=train_bn)
x = kl.activation('relu')(x) x = kl.conv2d(nb_filter2, (kernel_size, kernel_size), padding='same',
name=conv_name_base '2b', use_bias=use_bias)(x)
x = batchnorm(name=bn_name_base '2b')(x, training=train_bn)
x = kl.activation('relu')(x) x = kl.conv2d(nb_filter3, (1, 1), name=conv_name_base '2c',
use_bias=use_bias)(x)
x = batchnorm(name=bn_name_base '2c')(x, training=train_bn) x = kl.add()([x, input_tensor])
x = kl.activation('relu', name='res' str(stage) block '_out')(x)
return x def conv_block(input_tensor, kernel_size, filters, stage, block,
strides=(2, 2), use_bias=true, train_bn=true):
"""conv_block is the block that has a conv layer at shortcut
# arguments
input_tensor: input tensor
kernel_size: default 3, the kernel size of middle conv layer at main path
filters: list of integers, the nb_filters of 3 conv layer at main path
stage: integer, current stage label, used for generating layer names
block: 'a','b'..., current block label, used for generating layer names
use_bias: boolean. to use or not use a bias in conv layers.
train_bn: boolean. train or freeze batch norm layers
note that from stage 3, the first conv layer at main path is with subsample=(2,2)
and the shortcut should have subsample=(2,2) as well
"""
nb_filter1, nb_filter2, nb_filter3 = filters
conv_name_base = 'res' str(stage) block '_branch'
bn_name_base = 'bn' str(stage) block '_branch' x = kl.conv2d(nb_filter1, (1, 1), strides=strides,
name=conv_name_base '2a', use_bias=use_bias)(input_tensor)
x = batchnorm(name=bn_name_base '2a')(x, training=train_bn)
x = kl.activation('relu')(x) x = kl.conv2d(nb_filter2, (kernel_size, kernel_size), padding='same',
name=conv_name_base '2b', use_bias=use_bias)(x)
x = batchnorm(name=bn_name_base '2b')(x, training=train_bn)
x = kl.activation('relu')(x) x = kl.conv2d(nb_filter3, (1, 1), name=conv_name_base
'2c', use_bias=use_bias)(x)
x = batchnorm(name=bn_name_base '2c')(x, training=train_bn) shortcut = kl.conv2d(nb_filter3, (1, 1), strides=strides,
name=conv_name_base '', use_bias=use_bias)(input_tensor)
shortcut = batchnorm(name=bn_name_base '')(shortcut, training=train_bn) x = kl.add()([x, shortcut])
x = kl.activation('relu', name='res' str(stage) block '_out')(x)
return x def resnet_graph(input_image, architecture, stage5=false, train_bn=true):
"""build a resnet graph.
architecture: can be resnet50 or resnet101
stage5: boolean. if false, stage5 of the network is not created
train_bn: boolean. train or freeze batch norm layers
"""
assert architecture in ["resnet50", "resnet101"]
# stage 1
x = kl.zeropadding2d((3, 3))(input_image)
x = kl.conv2d(64, (7, 7), strides=(2, 2), name='conv1', use_bias=true)(x)
x = batchnorm(name='bn_conv1')(x, training=train_bn)
x = kl.activation('relu')(x)
c1 = x = kl.maxpooling2d((3, 3), strides=(2, 2), padding="same")(x)
# stage 2
x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1), train_bn=train_bn)
x = identity_block(x, 3, [64, 64, 256], stage=2, block='b', train_bn=train_bn)
c2 = x = identity_block(x, 3, [64, 64, 256], stage=2, block='c', train_bn=train_bn)
# stage 3
x = conv_block(x, 3, [128, 128, 512], stage=3, block='a', train_bn=train_bn)
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b', train_bn=train_bn)
x = identity_block(x, 3, [128, 128, 512], stage=3, block='c', train_bn=train_bn)
c3 = x = identity_block(x, 3, [128, 128, 512], stage=3, block='d', train_bn=train_bn)
# stage 4
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a', train_bn=train_bn)
block_count = {"resnet50": 5, "resnet101": 22}[architecture]
for i in range(block_count):
x = identity_block(x, 3, [256, 256, 1024], stage=4, block=chr(98 i), train_bn=train_bn)
c4 = x
# stage 5
if stage5:
x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a', train_bn=train_bn)
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b', train_bn=train_bn)
c5 = x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c', train_bn=train_bn)
else:
c5 = none
return [c1, c2, c3, c4, c5] ############################################################
# proposal layer
############################################################ def apply_box_deltas_graph(boxes, deltas):
"""applies the given deltas to the given boxes.
boxes: [n, (y1, x1, y2, x2)] boxes to update
deltas: [n, (dy, dx, log(dh), log(dw))] refinements to apply
"""
# convert to y, x, h, w
height = boxes[:, 2] - boxes[:, 0]
width = boxes[:, 3] - boxes[:, 1]
center_y = boxes[:, 0] 0.5 * height
center_x = boxes[:, 1] 0.5 * width
# apply deltas
center_y = deltas[:, 0] * height
center_x = deltas[:, 1] * width
height *= tf.exp(deltas[:, 2])
width *= tf.exp(deltas[:, 3])
# convert back to y1, x1, y2, x2
y1 = center_y - 0.5 * height
x1 = center_x - 0.5 * width
y2 = y1 height
x2 = x1 width
result = tf.stack([y1, x1, y2, x2], axis=1, name="apply_box_deltas_out")
return result def clip_boxes_graph(boxes, window):
"""
boxes: [n, (y1, x1, y2, x2)]
window: [4] in the form y1, x1, y2, x2
"""
# split
wy1, wx1, wy2, wx2 = tf.split(window, 4)
y1, x1, y2, x2 = tf.split(boxes, 4, axis=1)
# clip
y1 = tf.maximum(tf.minimum(y1, wy2), wy1)
x1 = tf.maximum(tf.minimum(x1, wx2), wx1)
y2 = tf.maximum(tf.minimum(y2, wy2), wy1)
x2 = tf.maximum(tf.minimum(x2, wx2), wx1)
clipped = tf.concat([y1, x1, y2, x2], axis=1, name="clipped_boxes")
clipped.set_shape((clipped.shape[0], 4))
return clipped class proposallayer(ke.layer):
"""receives anchor scores and selects a subset to pass as proposals
to the second stage. filtering is done based on anchor scores and
non-max suppression to remove overlaps. it also applies bounding
box refinement deltas to anchors. inputs:
rpn_probs: [batch, num_anchors, (bg prob, fg prob)]
rpn_bbox: [batch, num_anchors, (dy, dx, log(dh), log(dw))]
anchors: [batch, num_anchors, (y1, x1, y2, x2)] anchors in normalized coordinates returns:
proposals in normalized coordinates [batch, rois, (y1, x1, y2, x2)]
""" def __init__(self, proposal_count, nms_threshold, config=none, **kwargs):
super(proposallayer, self).__init__(**kwargs)
self.config = config
self.proposal_count = proposal_count
self.nms_threshold = nms_threshold def call(self, inputs):
# box scores. use the foreground class confidence. [batch, num_rois, 1]
scores = inputs[0][:, :, 1]
# box deltas [batch, num_rois, 4]
deltas = inputs[1]
deltas = deltas * np.reshape(self.config.rpn_bbox_std_dev, [1, 1, 4])
# anchors
anchors = inputs[2] # improve performance by trimming to top anchors by score
# and doing the rest on the smaller subset.
pre_nms_limit = tf.minimum(self.config.pre_nms_limit, tf.shape(anchors)[1])
ix = tf.nn.top_k(scores, pre_nms_limit, sorted=true,
name="top_anchors").indices
scores = utils.batch_slice([scores, ix], lambda x, y: tf.gather(x, y),
self.config.images_per_gpu)
deltas = utils.batch_slice([deltas, ix], lambda x, y: tf.gather(x, y),
self.config.images_per_gpu)
pre_nms_anchors = utils.batch_slice([anchors, ix], lambda a, x: tf.gather(a, x),
self.config.images_per_gpu,
names=["pre_nms_anchors"]) # apply deltas to anchors to get refined anchors.
# [batch, n, (y1, x1, y2, x2)]
boxes = utils.batch_slice([pre_nms_anchors, deltas],
lambda x, y: apply_box_deltas_graph(x, y),
self.config.images_per_gpu,
names=["refined_anchors"]) # clip to image boundaries. since we're in normalized coordinates,
# clip to 0..1 range. [batch, n, (y1, x1, y2, x2)]
window = np.array([0, 0, 1, 1], dtype=np.float32)
boxes = utils.batch_slice(boxes,
lambda x: clip_boxes_graph(x, window),
self.config.images_per_gpu,
names=["refined_anchors_clipped"]) # filter out small boxes
# according to xinlei chen's paper, this reduces detection accuracy
# for small objects, so we're skipping it. # non-max suppression
def nms(boxes, scores):
indices = tf.image.non_max_suppression(
boxes, scores, self.proposal_count,
self.nms_threshold, name="rpn_non_max_suppression")
proposals = tf.gather(boxes, indices)
# pad if needed
padding = tf.maximum(self.proposal_count - tf.shape(proposals)[0], 0)
proposals = tf.pad(proposals, [(0, padding), (0, 0)])
return proposals
proposals = utils.batch_slice([boxes, scores], nms,
self.config.images_per_gpu)
return proposals def compute_output_shape(self, input_shape):
return (none, self.proposal_count, 4) ############################################################
# roialign layer
############################################################ def log2_graph(x):
"""implementation of log2. tf doesn't have a native implementation."""
return tf.log(x) / tf.log(2.0) class pyramidroialign(ke.layer):
"""implements roi pooling on multiple levels of the feature pyramid. params:
- pool_shape: [pool_height, pool_width] of the output pooled regions. usually [7, 7] inputs:
- boxes: [batch, num_boxes, (y1, x1, y2, x2)] in normalized
coordinates. possibly padded with zeros if not enough
boxes to fill the array.
- image_meta: [batch, (meta data)] image details. see compose_image_meta()
- feature_maps: list of feature maps from different levels of the pyramid.
each is [batch, height, width, channels] output:
pooled regions in the shape: [batch, num_boxes, pool_height, pool_width, channels].
the width and height are those specific in the pool_shape in the layer
constructor.
""" def __init__(self, pool_shape, **kwargs):
super(pyramidroialign, self).__init__(**kwargs)
self.pool_shape = tuple(pool_shape) def call(self, inputs):
# crop boxes [batch, num_boxes, (y1, x1, y2, x2)] in normalized coords
boxes = inputs[0] # image meta
# holds details about the image. see compose_image_meta()
image_meta = inputs[1] # feature maps. list of feature maps from different level of the
# feature pyramid. each is [batch, height, width, channels]
feature_maps = inputs[2:] # assign each roi to a level in the pyramid based on the roi area.
y1, x1, y2, x2 = tf.split(boxes, 4, axis=2)
h = y2 - y1
w = x2 - x1
# use shape of first image. images in a batch must have the same size.
image_shape = parse_image_meta_graph(image_meta)['image_shape'][0]
# equation 1 in the feature pyramid networks paper. account for
# the fact that our coordinates are normalized here.
# e.g. a 224x224 roi (in pixels) maps to p4
image_area = tf.cast(image_shape[0] * image_shape[1], tf.float32)
roi_level = log2_graph(tf.sqrt(h * w) / (224.0 / tf.sqrt(image_area)))
roi_level = tf.minimum(5, tf.maximum(
2, 4 tf.cast(tf.round(roi_level), tf.int32)))
roi_level = tf.squeeze(roi_level, 2) # loop through levels and apply roi pooling to each. p2 to p5.
pooled = []
box_to_level = []
for i, level in enumerate(range(2, 6)):
ix = tf.where(tf.equal(roi_level, level))
level_boxes = tf.gather_nd(boxes, ix) # box indices for crop_and_resize.
box_indices = tf.cast(ix[:, 0], tf.int32) # keep track of which box is mapped to which level
box_to_level.append(ix) # stop gradient propogation to roi proposals
level_boxes = tf.stop_gradient(level_boxes)
box_indices = tf.stop_gradient(box_indices) # crop and resize
# from mask r-cnn paper: "we sample four regular locations, so
# that we can evaluate either max or average pooling. in fact,
# interpolating only a single value at each bin center (without
# pooling) is nearly as effective."
#
# here we use the simplified approach of a single value per bin,
# which is how it's done in tf.crop_and_resize()
# result: [batch * num_boxes, pool_height, pool_width, channels]
pooled.append(tf.image.crop_and_resize(
feature_maps[i], level_boxes, box_indices, self.pool_shape,
method="bilinear")) # pack pooled features into one tensor
pooled = tf.concat(pooled, axis=0) # pack box_to_level mapping into one array and add another
# column representing the order of pooled boxes
box_to_level = tf.concat(box_to_level, axis=0)
box_range = tf.expand_dims(tf.range(tf.shape(box_to_level)[0]), 1)
box_to_level = tf.concat([tf.cast(box_to_level, tf.int32), box_range],
axis=1) # rearrange pooled features to match the order of the original boxes
# sort box_to_level by batch then box index
# tf doesn't have a way to sort by two columns, so merge them and sort.
sorting_tensor = box_to_level[:, 0] * 100000 box_to_level[:, 1]
ix = tf.nn.top_k(sorting_tensor, k=tf.shape(
box_to_level)[0]).indices[::-1]
ix = tf.gather(box_to_level[:, 2], ix)
pooled = tf.gather(pooled, ix) # re-add the batch dimension
shape = tf.concat([tf.shape(boxes)[:2], tf.shape(pooled)[1:]], axis=0)
pooled = tf.reshape(pooled, shape)
return pooled def compute_output_shape(self, input_shape):
return input_shape[0][:2] self.pool_shape (input_shape[2][-1], ) ############################################################
# detection target layer
############################################################ def overlaps_graph(boxes1, boxes2):
"""computes iou overlaps between two sets of boxes.
boxes1, boxes2: [n, (y1, x1, y2, x2)].
"""
# 1. tile boxes2 and repeat boxes1. this allows us to compare
# every boxes1 against every boxes2 without loops.
# tf doesn't have an equivalent to np.repeat() so simulate it
# using tf.tile() and tf.reshape.
b1 = tf.reshape(tf.tile(tf.expand_dims(boxes1, 1),
[1, 1, tf.shape(boxes2)[0]]), [-1, 4])
b2 = tf.tile(boxes2, [tf.shape(boxes1)[0], 1])
# 2. compute intersections
b1_y1, b1_x1, b1_y2, b1_x2 = tf.split(b1, 4, axis=1)
b2_y1, b2_x1, b2_y2, b2_x2 = tf.split(b2, 4, axis=1)
y1 = tf.maximum(b1_y1, b2_y1)
x1 = tf.maximum(b1_x1, b2_x1)
y2 = tf.minimum(b1_y2, b2_y2)
x2 = tf.minimum(b1_x2, b2_x2)
intersection = tf.maximum(x2 - x1, 0) * tf.maximum(y2 - y1, 0)
# 3. compute unions
b1_area = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)
b2_area = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)
union = b1_area b2_area - intersection
# 4. compute iou and reshape to [boxes1, boxes2]
iou = intersection / union
overlaps = tf.reshape(iou, [tf.shape(boxes1)[0], tf.shape(boxes2)[0]])
return overlaps def detection_targets_graph(proposals, gt_class_ids, gt_boxes, gt_masks, config):
"""generates detection targets for one image. subsamples proposals and
generates target class ids, bounding box deltas, and masks for each. inputs:
proposals: [post_nms_rois_training, (y1, x1, y2, x2)] in normalized coordinates. might
be zero padded if there are not enough proposals.
gt_class_ids: [max_gt_instances] int class ids
gt_boxes: [max_gt_instances, (y1, x1, y2, x2)] in normalized coordinates.
gt_masks: [height, width, max_gt_instances] of boolean type. returns: target rois and corresponding class ids, bounding box shifts,
and masks.
rois: [train_rois_per_image, (y1, x1, y2, x2)] in normalized coordinates
class_ids: [train_rois_per_image]. integer class ids. zero padded.
deltas: [train_rois_per_image, (dy, dx, log(dh), log(dw))]
masks: [train_rois_per_image, height, width]. masks cropped to bbox
boundaries and resized to neural network output size. note: returned arrays might be zero padded if not enough target rois.
"""
# assertions
asserts = [
tf.assert(tf.greater(tf.shape(proposals)[0], 0), [proposals],
name="roi_assertion"),
]
with tf.control_dependencies(asserts):
proposals = tf.identity(proposals) # remove zero padding
proposals, _ = trim_zeros_graph(proposals, name="trim_proposals")
gt_boxes, non_zeros = trim_zeros_graph(gt_boxes, name="trim_gt_boxes")
gt_class_ids = tf.boolean_mask(gt_class_ids, non_zeros,
name="trim_gt_class_ids")
gt_masks = tf.gather(gt_masks, tf.where(non_zeros)[:, 0], axis=2,
name="trim_gt_masks") # handle coco crowds
# a crowd box in coco is a bounding box around several instances. exclude
# them from training. a crowd box is given a negative class id.
crowd_ix = tf.where(gt_class_ids < 0)[:, 0]
non_crowd_ix = tf.where(gt_class_ids > 0)[:, 0]
crowd_boxes = tf.gather(gt_boxes, crowd_ix)
gt_class_ids = tf.gather(gt_class_ids, non_crowd_ix)
gt_boxes = tf.gather(gt_boxes, non_crowd_ix)
gt_masks = tf.gather(gt_masks, non_crowd_ix, axis=2) # compute overlaps matrix [proposals, gt_boxes]
overlaps = overlaps_graph(proposals, gt_boxes) # compute overlaps with crowd boxes [proposals, crowd_boxes]
crowd_overlaps = overlaps_graph(proposals, crowd_boxes)
crowd_iou_max = tf.reduce_max(crowd_overlaps, axis=1)
no_crowd_bool = (crowd_iou_max < 0.001) # determine positive and negative rois
roi_iou_max = tf.reduce_max(overlaps, axis=1)
# 1. positive rois are those with >= 0.5 iou with a gt box
positive_roi_bool = (roi_iou_max >= 0.5)
positive_indices = tf.where(positive_roi_bool)[:, 0]
# 2. negative rois are those with < 0.5 with every gt box. skip crowds.
negative_indices = tf.where(tf.logical_and(roi_iou_max < 0.5, no_crowd_bool))[:, 0] # subsample rois. aim for 33% positive
# positive rois
positive_count = int(config.train_rois_per_image *
config.roi_positive_ratio)
positive_indices = tf.random_shuffle(positive_indices)[:positive_count]
positive_count = tf.shape(positive_indices)[0]
# negative rois. add enough to maintain positive:negative ratio.
r = 1.0 / config.roi_positive_ratio
negative_count = tf.cast(r * tf.cast(positive_count, tf.float32), tf.int32) - positive_count
negative_indices = tf.random_shuffle(negative_indices)[:negative_count]
# gather selected rois
positive_rois = tf.gather(proposals, positive_indices)
negative_rois = tf.gather(proposals, negative_indices) # assign positive rois to gt boxes.
positive_overlaps = tf.gather(overlaps, positive_indices)
roi_gt_box_assignment = tf.cond(
tf.greater(tf.shape(positive_overlaps)[1], 0),
true_fn = lambda: tf.argmax(positive_overlaps, axis=1),
false_fn = lambda: tf.cast(tf.constant([]),tf.int64)
)
roi_gt_boxes = tf.gather(gt_boxes, roi_gt_box_assignment)
roi_gt_class_ids = tf.gather(gt_class_ids, roi_gt_box_assignment) # compute bbox refinement for positive rois
deltas = utils.box_refinement_graph(positive_rois, roi_gt_boxes)
deltas /= config.bbox_std_dev # assign positive rois to gt masks
# permute masks to [n, height, width, 1]
transposed_masks = tf.expand_dims(tf.transpose(gt_masks, [2, 0, 1]), -1)
# pick the right mask for each roi
roi_masks = tf.gather(transposed_masks, roi_gt_box_assignment) # compute mask targets
boxes = positive_rois
if config.use_mini_mask:
# transform roi coordinates from normalized image space
# to normalized mini-mask space.
y1, x1, y2, x2 = tf.split(positive_rois, 4, axis=1)
gt_y1, gt_x1, gt_y2, gt_x2 = tf.split(roi_gt_boxes, 4, axis=1)
gt_h = gt_y2 - gt_y1
gt_w = gt_x2 - gt_x1
y1 = (y1 - gt_y1) / gt_h
x1 = (x1 - gt_x1) / gt_w
y2 = (y2 - gt_y1) / gt_h
x2 = (x2 - gt_x1) / gt_w
boxes = tf.concat([y1, x1, y2, x2], 1)
box_ids = tf.range(0, tf.shape(roi_masks)[0])
masks = tf.image.crop_and_resize(tf.cast(roi_masks, tf.float32), boxes,
box_ids,
config.mask_shape)
# remove the extra dimension from masks.
masks = tf.squeeze(masks, axis=3) # threshold mask pixels at 0.5 to have gt masks be 0 or 1 to use with
# binary cross entropy loss.
masks = tf.round(masks) # append negative rois and pad bbox deltas and masks that
# are not used for negative rois with zeros.
rois = tf.concat([positive_rois, negative_rois], axis=0)
n = tf.shape(negative_rois)[0]
p = tf.maximum(config.train_rois_per_image - tf.shape(rois)[0], 0)
rois = tf.pad(rois, [(0, p), (0, 0)])
roi_gt_boxes = tf.pad(roi_gt_boxes, [(0, n p), (0, 0)])
roi_gt_class_ids = tf.pad(roi_gt_class_ids, [(0, n p)])
deltas = tf.pad(deltas, [(0, n p), (0, 0)])
masks = tf.pad(masks, [[0, n p], (0, 0), (0, 0)]) return rois, roi_gt_class_ids, deltas, masks class detectiontargetlayer(ke.layer):
"""subsamples proposals and generates target box refinement, class_ids,
and masks for each. inputs:
proposals: [batch, n, (y1, x1, y2, x2)] in normalized coordinates. might
be zero padded if there are not enough proposals.
gt_class_ids: [batch, max_gt_instances] integer class ids.
gt_boxes: [batch, max_gt_instances, (y1, x1, y2, x2)] in normalized
coordinates.
gt_masks: [batch, height, width, max_gt_instances] of boolean type returns: target rois and corresponding class ids, bounding box shifts,
and masks.
rois: [batch, train_rois_per_image, (y1, x1, y2, x2)] in normalized
coordinates
target_class_ids: [batch, train_rois_per_image]. integer class ids.
target_deltas: [batch, train_rois_per_image, (dy, dx, log(dh), log(dw)]
target_mask: [batch, train_rois_per_image, height, width]
masks cropped to bbox boundaries and resized to neural
network output size. note: returned arrays might be zero padded if not enough target rois.
""" def __init__(self, config, **kwargs):
super(detectiontargetlayer, self).__init__(**kwargs)
self.config = config def call(self, inputs):
proposals = inputs[0]
gt_class_ids = inputs[1]
gt_boxes = inputs[2]
gt_masks = inputs[3] # slice the batch and run a graph for each slice
# todo: rename target_bbox to target_deltas for clarity
names = ["rois", "target_class_ids", "target_bbox", "target_mask"]
outputs = utils.batch_slice(
[proposals, gt_class_ids, gt_boxes, gt_masks],
lambda w, x, y, z: detection_targets_graph(
w, x, y, z, self.config),
self.config.images_per_gpu, names=names)
return outputs def compute_output_shape(self, input_shape):
return [
(none, self.config.train_rois_per_image, 4), # rois
(none, self.config.train_rois_per_image), # class_ids
(none, self.config.train_rois_per_image, 4), # deltas
(none, self.config.train_rois_per_image, self.config.mask_shape[0],
self.config.mask_shape[1]) # masks
] def compute_mask(self, inputs, mask=none):
return [none, none, none, none] ############################################################
# detection layer
############################################################ def refine_detections_graph(rois, probs, deltas, window, feature_maps, config):
"""refine classified proposals and filter overlaps and return final
detections. inputs:
rois: [n, (y1, x1, y2, x2)] in normalized coordinates
probs: [n, num_classes]. class probabilities.
deltas: [n, num_classes, (dy, dx, log(dh), log(dw))]. class-specific
bounding box deltas.
window: (y1, x1, y2, x2) in normalized coordinates. the part of the image
that contains the image excluding the padding. returns detections shaped: [num_detections, (y1, x1, y2, x2, class_id, score)] where
coordinates are normalized.
"""
# class ids per roi
class_ids = tf.argmax(probs, axis=1, output_type=tf.int32)
# class probability of the top class of each roi
indices = tf.stack([tf.range(probs.shape[0]), class_ids], axis=1)
class_scores = tf.gather_nd(probs, indices)
# class-specific bounding box deltas
deltas_specific = tf.gather_nd(deltas, indices)
# apply bounding box deltas
# shape: [boxes, (y1, x1, y2, x2)] in normalized coordinates
refined_rois = apply_box_deltas_graph(
rois, deltas_specific * config.bbox_std_dev)
# clip boxes to image window
refined_rois = clip_boxes_graph(refined_rois, window) # todo: filter out boxes with zero area # filter out background boxes
keep = tf.where(class_ids > 0)[:, 0]
# filter out low confidence boxes
if config.detection_min_confidence:
conf_keep = tf.where(class_scores >= config.detection_min_confidence)[:, 0]
keep = tf.sets.set_intersection(tf.expand_dims(keep, 0),
tf.expand_dims(conf_keep, 0))
keep = tf.sparse_tensor_to_dense(keep)[0] # apply per-class nms
# 1. prepare variables
pre_nms_class_ids = tf.gather(class_ids, keep)
pre_nms_scores = tf.gather(class_scores, keep)
pre_nms_rois = tf.gather(refined_rois, keep)
unique_pre_nms_class_ids = tf.unique(pre_nms_class_ids)[0] def nms_keep_map(class_id):
"""apply non-maximum suppression on rois of the given class."""
# indices of rois of the given class
ixs = tf.where(tf.equal(pre_nms_class_ids, class_id))[:, 0]
# apply nms
class_keep = tf.image.non_max_suppression(
tf.gather(pre_nms_rois, ixs),
tf.gather(pre_nms_scores, ixs),
max_output_size=config.detection_max_instances,
iou_threshold=config.detection_nms_threshold)
# map indices
class_keep = tf.gather(keep, tf.gather(ixs, class_keep))
# pad with -1 so returned tensors have the same shape
gap = config.detection_max_instances - tf.shape(class_keep)[0]
class_keep = tf.pad(class_keep, [(0, gap)],
mode='constant', constant_values=-1)
# set shape so map_fn() can infer result shape
class_keep.set_shape([config.detection_max_instances])
return class_keep # 2. map over class ids
nms_keep = tf.map_fn(nms_keep_map, unique_pre_nms_class_ids,
dtype=tf.int64)
# 3. merge results into one list, and remove -1 padding
nms_keep = tf.reshape(nms_keep, [-1])
nms_keep = tf.gather(nms_keep, tf.where(nms_keep > -1)[:, 0])
# 4. compute intersection between keep and nms_keep
keep = tf.sets.set_intersection(tf.expand_dims(keep, 0),
tf.expand_dims(nms_keep, 0))
keep = tf.sparse_tensor_to_dense(keep)[0]
# keep top detections
roi_count = config.detection_max_instances
class_scores_keep = tf.gather(class_scores, keep)
num_keep = tf.minimum(tf.shape(class_scores_keep)[0], roi_count)
top_ids = tf.nn.top_k(class_scores_keep, k=num_keep, sorted=true)[1]
keep = tf.gather(keep, top_ids) # arrange output as [n, (y1, x1, y2, x2, class_id, score)]
# coordinates are normalized.
detections = tf.concat([
tf.gather(refined_rois, keep),
tf.to_float(tf.gather(class_ids, keep))[..., tf.newaxis],
tf.gather(class_scores, keep)[..., tf.newaxis],
tf.gather(feature_maps, keep)
], axis=1) # pad with zeros if detections < detection_max_instances
gap = config.detection_max_instances - tf.shape(detections)[0]
detections = tf.pad(detections, [(0, gap), (0, 0)], "constant")
return detections class detectionlayer(ke.layer):
"""takes classified proposal boxes and their bounding box deltas and
returns the final detection boxes. returns:
[batch, num_detections, (y1, x1, y2, x2, class_id, class_score)] where
coordinates are normalized.
""" def __init__(self, config=none, **kwargs):
super(detectionlayer, self).__init__(**kwargs)
self.config = config def call(self, inputs):
rois = inputs[0]
mrcnn_class = inputs[1]
mrcnn_bbox = inputs[2]
image_meta = inputs[3]
feature_maps = inputs[4] # get windows of images in normalized coordinates. windows are the area
# in the image that excludes the padding.
# use the shape of the first image in the batch to normalize the window
# because we know that all images get resized to the same size.
m = parse_image_meta_graph(image_meta)
image_shape = m['image_shape'][0]
window = norm_boxes_graph(m['window'], image_shape[:2]) # run detection refinement graph on each item in the batch
detections_batch = utils.batch_slice(
[rois, mrcnn_class, mrcnn_bbox, window, feature_maps],
lambda x, y, w, z, f: refine_detections_graph(x, y, w, z, f, self.config),
self.config.images_per_gpu) # reshape output
# [batch, num_detections, (y1, x1, y2, x2, class_id, class_score)] in
# normalized coordinates
return tf.reshape(
detections_batch,
[self.config.batch_size, self.config.detection_max_instances, 6 self.config.fpn_classif_fc_layers_size]) def compute_output_shape(self, input_shape):
return (none, self.config.detection_max_instances, 6 self.config.fpn_classif_fc_layers_size) ############################################################
# region proposal network (rpn)
############################################################ def rpn_graph(feature_map, anchors_per_location, anchor_stride):
"""builds the computation graph of region proposal network. feature_map: backbone features [batch, height, width, depth]
anchors_per_location: number of anchors per pixel in the feature map
anchor_stride: controls the density of anchors. typically 1 (anchors for
every pixel in the feature map), or 2 (every other pixel). returns:
rpn_class_logits: [batch, h * w * anchors_per_location, 2] anchor classifier logits (before softmax)
rpn_probs: [batch, h * w * anchors_per_location, 2] anchor classifier probabilities.
rpn_bbox: [batch, h * w * anchors_per_location, (dy, dx, log(dh), log(dw))] deltas to be
applied to anchors.
"""
# todo: check if stride of 2 causes alignment issues if the feature map
# is not even.
# shared convolutional base of the rpn
shared = kl.conv2d(512, (3, 3), padding='same', activation='relu',
strides=anchor_stride,
name='rpn_conv_shared')(feature_map) # anchor score. [batch, height, width, anchors per location * 2].
x = kl.conv2d(2 * anchors_per_location, (1, 1), padding='valid',
activation='linear', name='rpn_class_raw')(shared) # reshape to [batch, anchors, 2]
rpn_class_logits = kl.lambda(
lambda t: tf.reshape(t, [tf.shape(t)[0], -1, 2]))(x) # softmax on last dimension of bg/fg.
rpn_probs = kl.activation(
"softmax", name="rpn_class_xxx")(rpn_class_logits) # bounding box refinement. [batch, h, w, anchors per location * depth]
# where depth is [x, y, log(w), log(h)]
x = kl.conv2d(anchors_per_location * 4, (1, 1), padding="valid",
activation='linear', name='rpn_bbox_pred')(shared) # reshape to [batch, anchors, 4]
rpn_bbox = kl.lambda(lambda t: tf.reshape(t, [tf.shape(t)[0], -1, 4]))(x) return [rpn_class_logits, rpn_probs, rpn_bbox] def build_rpn_model(anchor_stride, anchors_per_location, depth):
"""builds a keras model of the region proposal network.
it wraps the rpn graph so it can be used multiple times with shared
weights. anchors_per_location: number of anchors per pixel in the feature map
anchor_stride: controls the density of anchors. typically 1 (anchors for
every pixel in the feature map), or 2 (every other pixel).
depth: depth of the backbone feature map. returns a keras model object. the model outputs, when called, are:
rpn_class_logits: [batch, h * w * anchors_per_location, 2] anchor classifier logits (before softmax)
rpn_probs: [batch, h * w * anchors_per_location, 2] anchor classifier probabilities.
rpn_bbox: [batch, h * w * anchors_per_location, (dy, dx, log(dh), log(dw))] deltas to be
applied to anchors.
"""
input_feature_map = kl.input(shape=[none, none, depth],
name="input_rpn_feature_map")
outputs = rpn_graph(input_feature_map, anchors_per_location, anchor_stride)
return km.model([input_feature_map], outputs, name="rpn_model") ############################################################
# feature pyramid network heads
############################################################ def fpn_classifier_graph(rois, feature_maps, image_meta,
pool_size, num_classes, train_bn=true,
fc_layers_size=1024):
"""builds the computation graph of the feature pyramid network classifier
and regressor heads. rois: [batch, num_rois, (y1, x1, y2, x2)] proposal boxes in normalized
coordinates.
feature_maps: list of feature maps from different layers of the pyramid,
[p2, p3, p4, p5]. each has a different resolution.
image_meta: [batch, (meta data)] image details. see compose_image_meta()
pool_size: the width of the square feature map generated from roi pooling.
num_classes: number of classes, which determines the depth of the results
train_bn: boolean. train or freeze batch norm layers
fc_layers_size: size of the 2 fc layers returns:
logits: [batch, num_rois, num_classes] classifier logits (before softmax)
probs: [batch, num_rois, num_classes] classifier probabilities
bbox_deltas: [batch, num_rois, num_classes, (dy, dx, log(dh), log(dw))] deltas to apply to
proposal boxes
"""
# roi pooling
# shape: [batch, num_rois, pool_size, pool_size, channels]
x = pyramidroialign([pool_size, pool_size],
name="roi_align_classifier")([rois, image_meta] feature_maps)
# two 1024 fc layers (implemented with conv2d for consistency)
x = kl.timedistributed(kl.conv2d(fc_layers_size, (pool_size, pool_size), padding="valid"),
name="mrcnn_class_conv1")(x)
x = kl.timedistributed(batchnorm(), name='mrcnn_class_bn1')(x, training=train_bn)
x = kl.activation('relu')(x)
x = kl.timedistributed(kl.conv2d(fc_layers_size, (1, 1)),
name="mrcnn_class_conv2")(x)
x = kl.timedistributed(batchnorm(), name='mrcnn_class_bn2')(x, training=train_bn)
x = kl.activation('relu')(x) shared = kl.lambda(lambda x: k.squeeze(k.squeeze(x, 3), 2),
name="pool_squeeze")(x) # classifier head
mrcnn_class_logits = kl.timedistributed(kl.dense(num_classes),
name='mrcnn_class_logits')(shared)
mrcnn_probs = kl.timedistributed(kl.activation("softmax"),
name="mrcnn_class")(mrcnn_class_logits) # bbox head
# [batch, num_rois, num_classes * (dy, dx, log(dh), log(dw))]
x = kl.timedistributed(kl.dense(num_classes * 4, activation='linear'),
name='mrcnn_bbox_fc')(shared)
# reshape to [batch, num_rois, num_classes, (dy, dx, log(dh), log(dw))]
s = k.int_shape(x)
mrcnn_bbox = kl.reshape((s[1], num_classes, 4), name="mrcnn_bbox")(x) return mrcnn_class_logits, mrcnn_probs, mrcnn_bbox, shared def build_fpn_mask_graph(rois, feature_maps, image_meta,
pool_size, num_classes, train_bn=true):
"""builds the computation graph of the mask head of feature pyramid network. rois: [batch, num_rois, (y1, x1, y2, x2)] proposal boxes in normalized
coordinates.
feature_maps: list of feature maps from different layers of the pyramid,
[p2, p3, p4, p5]. each has a different resolution.
image_meta: [batch, (meta data)] image details. see compose_image_meta()
pool_size: the width of the square feature map generated from roi pooling.
num_classes: number of classes, which determines the depth of the results
train_bn: boolean. train or freeze batch norm layers returns: masks [batch, num_rois, mask_pool_size, mask_pool_size, num_classes]
"""
# roi pooling
# shape: [batch, num_rois, mask_pool_size, mask_pool_size, channels]
x = pyramidroialign([pool_size, pool_size],
name="roi_align_mask")([rois, image_meta] feature_maps) # conv layers
x = kl.timedistributed(kl.conv2d(256, (3, 3), padding="same"),
name="mrcnn_mask_conv1")(x)
x = kl.timedistributed(batchnorm(),
name='mrcnn_mask_bn1')(x, training=train_bn)
x = kl.activation('relu')(x) x = kl.timedistributed(kl.conv2d(256, (3, 3), padding="same"),
name="mrcnn_mask_conv2")(x)
x = kl.timedistributed(batchnorm(),
name='mrcnn_mask_bn2')(x, training=train_bn)
x = kl.activation('relu')(x) x = kl.timedistributed(kl.conv2d(256, (3, 3), padding="same"),
name="mrcnn_mask_conv3")(x)
x = kl.timedistributed(batchnorm(),
name='mrcnn_mask_bn3')(x, training=train_bn)
x = kl.activation('relu')(x) x = kl.timedistributed(kl.conv2d(256, (3, 3), padding="same"),
name="mrcnn_mask_conv4")(x)
x = kl.timedistributed(batchnorm(),
name='mrcnn_mask_bn4')(x, training=train_bn)
x = kl.activation('relu')(x) x = kl.timedistributed(kl.conv2dtranspose(256, (2, 2), strides=2, activation="relu"),
name="mrcnn_mask_deconv")(x)
x = kl.timedistributed(kl.conv2d(num_classes, (1, 1), strides=1, activation="sigmoid"),
name="mrcnn_mask")(x)
return x ############################################################
# loss functions
############################################################ def smooth_l1_loss(y_true, y_pred):
"""implements smooth-l1 loss.
y_true and y_pred are typically: [n, 4], but could be any shape.
"""
diff = k.abs(y_true - y_pred)
less_than_one = k.cast(k.less(diff, 1.0), "float32")
loss = (less_than_one * 0.5 * diff**2) (1 - less_than_one) * (diff - 0.5)
return loss def rpn_class_loss_graph(rpn_match, rpn_class_logits):
"""rpn anchor classifier loss. rpn_match: [batch, anchors, 1]. anchor match type. 1=positive,
-1=negative, 0=neutral anchor.
rpn_class_logits: [batch, anchors, 2]. rpn classifier logits for bg/fg.
"""
# squeeze last dim to simplify
rpn_match = tf.squeeze(rpn_match, -1)
# get anchor classes. convert the -1/ 1 match to 0/1 values.
anchor_class = k.cast(k.equal(rpn_match, 1), tf.int32)
# positive and negative anchors contribute to the loss,
# but neutral anchors (match value = 0) don't.
indices = tf.where(k.not_equal(rpn_match, 0))
# pick rows that contribute to the loss and filter out the rest.
rpn_class_logits = tf.gather_nd(rpn_class_logits, indices)
anchor_class = tf.gather_nd(anchor_class, indices)
# cross entropy loss
loss = k.sparse_categorical_crossentropy(target=anchor_class,
output=rpn_class_logits,
from_logits=true)
loss = k.switch(tf.size(loss) > 0, k.mean(loss), tf.constant(0.0))
return loss def rpn_bbox_loss_graph(config, target_bbox, rpn_match, rpn_bbox):
"""return the rpn bounding box loss graph. config: the model config object.
target_bbox: [batch, max positive anchors, (dy, dx, log(dh), log(dw))].
uses 0 padding to fill in unsed bbox deltas.
rpn_match: [batch, anchors, 1]. anchor match type. 1=positive,
-1=negative, 0=neutral anchor.
rpn_bbox: [batch, anchors, (dy, dx, log(dh), log(dw))]
"""
# positive anchors contribute to the loss, but negative and
# neutral anchors (match value of 0 or -1) don't.
rpn_match = k.squeeze(rpn_match, -1)
indices = tf.where(k.equal(rpn_match, 1)) # pick bbox deltas that contribute to the loss
rpn_bbox = tf.gather_nd(rpn_bbox, indices) # trim target bounding box deltas to the same length as rpn_bbox.
batch_counts = k.sum(k.cast(k.equal(rpn_match, 1), tf.int32), axis=1)
target_bbox = batch_pack_graph(target_bbox, batch_counts,
config.images_per_gpu) loss = smooth_l1_loss(target_bbox, rpn_bbox) loss = k.switch(tf.size(loss) > 0, k.mean(loss), tf.constant(0.0))
return loss def mrcnn_class_loss_graph(target_class_ids, pred_class_logits,
active_class_ids):
"""loss for the classifier head of mask rcnn. target_class_ids: [batch, num_rois]. integer class ids. uses zero
padding to fill in the array.
pred_class_logits: [batch, num_rois, num_classes]
active_class_ids: [batch, num_classes]. has a value of 1 for
classes that are in the dataset of the image, and 0
for classes that are not in the dataset.
"""
# during model building, keras calls this function with
# target_class_ids of type float32. unclear why. cast it
# to int to get around it.
target_class_ids = tf.cast(target_class_ids, 'int64') # find predictions of classes that are not in the dataset.
pred_class_ids = tf.argmax(pred_class_logits, axis=2)
# todo: update this line to work with batch > 1. right now it assumes all
# images in a batch have the same active_class_ids
pred_active = tf.gather(active_class_ids[0], pred_class_ids) # loss
loss = tf.nn.sparse_softmax_cross_entropy_with_logits(
labels=target_class_ids, logits=pred_class_logits) # erase losses of predictions of classes that are not in the active
# classes of the image.
loss = loss * pred_active # computer loss mean. use only predictions that contribute
# to the loss to get a correct mean.
loss = tf.reduce_sum(loss) / tf.reduce_sum(pred_active)
return loss def mrcnn_bbox_loss_graph(target_bbox, target_class_ids, pred_bbox):
"""loss for mask r-cnn bounding box refinement. target_bbox: [batch, num_rois, (dy, dx, log(dh), log(dw))]
target_class_ids: [batch, num_rois]. integer class ids.
pred_bbox: [batch, num_rois, num_classes, (dy, dx, log(dh), log(dw))]
"""
# reshape to merge batch and roi dimensions for simplicity.
target_class_ids = k.reshape(target_class_ids, (-1,))
target_bbox = k.reshape(target_bbox, (-1, 4))
pred_bbox = k.reshape(pred_bbox, (-1, k.int_shape(pred_bbox)[2], 4)) # only positive rois contribute to the loss. and only
# the right class_id of each roi. get their indices.
positive_roi_ix = tf.where(target_class_ids > 0)[:, 0]
positive_roi_class_ids = tf.cast(
tf.gather(target_class_ids, positive_roi_ix), tf.int64)
indices = tf.stack([positive_roi_ix, positive_roi_class_ids], axis=1) # gather the deltas (predicted and true) that contribute to loss
target_bbox = tf.gather(target_bbox, positive_roi_ix)
pred_bbox = tf.gather_nd(pred_bbox, indices) # smooth-l1 loss
loss = k.switch(tf.size(target_bbox) > 0,
smooth_l1_loss(y_true=target_bbox, y_pred=pred_bbox),
tf.constant(0.0))
loss = k.mean(loss)
return loss def mrcnn_mask_loss_graph(target_masks, target_class_ids, pred_masks):
"""mask binary cross-entropy loss for the masks head. target_masks: [batch, num_rois, height, width].
a float32 tensor of values 0 or 1. uses zero padding to fill array.
target_class_ids: [batch, num_rois]. integer class ids. zero padded.
pred_masks: [batch, proposals, height, width, num_classes] float32 tensor
with values from 0 to 1.
"""
# reshape for simplicity. merge first two dimensions into one.
target_class_ids = k.reshape(target_class_ids, (-1,))
mask_shape = tf.shape(target_masks)
target_masks = k.reshape(target_masks, (-1, mask_shape[2], mask_shape[3]))
pred_shape = tf.shape(pred_masks)
pred_masks = k.reshape(pred_masks,
(-1, pred_shape[2], pred_shape[3], pred_shape[4]))
# permute predicted masks to [n, num_classes, height, width]
pred_masks = tf.transpose(pred_masks, [0, 3, 1, 2]) # only positive rois contribute to the loss. and only
# the class specific mask of each roi.
positive_ix = tf.where(target_class_ids > 0)[:, 0]
positive_class_ids = tf.cast(
tf.gather(target_class_ids, positive_ix), tf.int64)
indices = tf.stack([positive_ix, positive_class_ids], axis=1) # gather the masks (predicted and true) that contribute to loss
y_true = tf.gather(target_masks, positive_ix)
y_pred = tf.gather_nd(pred_masks, indices) # compute binary cross entropy. if no positive rois, then return 0.
# shape: [batch, roi, num_classes]
loss = k.switch(tf.size(y_true) > 0,
k.binary_crossentropy(target=y_true, output=y_pred),
tf.constant(0.0))
loss = k.mean(loss)
return loss ############################################################
# data generator
############################################################ def load_image_gt(dataset, config, image_id, augment=false, augmentation=none,
use_mini_mask=false):
"""load and return ground truth data for an image (image, mask, bounding boxes). augment: (deprecated. use augmentation instead). if true, apply random
image augmentation. currently, only horizontal flipping is offered.
augmentation: optional. an imgaug (https://github.com/aleju/imgaug) augmentation.
for example, passing imgaug.augmenters.fliplr(0.5) flips images
right/left 50% of the time.
use_mini_mask: if false, returns full-size masks that are the same height
and width as the original image. these can be big, for example
1024x1024x100 (for 100 instances). mini masks are smaller, typically,
224x224 and are generated by extracting the bounding box of the
object and resizing it to mini_mask_shape. returns:
image: [height, width, 3]
shape: the original shape of the image before resizing and cropping.
class_ids: [instance_count] integer class ids
bbox: [instance_count, (y1, x1, y2, x2)]
mask: [height, width, instance_count]. the height and width are those
of the image unless use_mini_mask is true, in which case they are
defined in mini_mask_shape.
"""
# load image and mask
image = dataset.load_image(image_id)
mask, class_ids = dataset.load_mask(image_id)
original_shape = image.shape
image, window, scale, padding, crop = utils.resize_image(
image,
min_dim=config.image_min_dim,
min_scale=config.image_min_scale,
max_dim=config.image_max_dim,
mode=config.image_resize_mode)
mask = utils.resize_mask(mask, scale, padding, crop) # random horizontal flips.
# todo: will be removed in a future update in favor of augmentation
if augment:
logging.warning("'augment' is deprecated. use 'augmentation' instead.")
if random.randint(0, 1):
image = np.fliplr(image)
mask = np.fliplr(mask) # augmentation
# this requires the imgaug lib (https://github.com/aleju/imgaug)
if augmentation:
import imgaug # augmenters that are safe to apply to masks
# some, such as affine, have settings that make them unsafe, so always
# test your augmentation on masks
mask_augmenters = ["sequential", "someof", "oneof", "sometimes",
"fliplr", "flipud", "cropandpad",
"affine", "piecewiseaffine"] def hook(images, augmenter, parents, default):
"""determines which augmenters to apply to masks."""
return augmenter.__class__.__name__ in mask_augmenters # store shapes before augmentation to compare
image_shape = image.shape
mask_shape = mask.shape
# make augmenters deterministic to apply similarly to images and masks
det = augmentation.to_deterministic()
image = det.augment_image(image)
# change mask to np.uint8 because imgaug doesn't support np.bool
mask = det.augment_image(mask.astype(np.uint8),
hooks=imgaug.hooksimages(activator=hook))
# verify that shapes didn't change
assert image.shape == image_shape, "augmentation shouldn't change image size"
assert mask.shape == mask_shape, "augmentation shouldn't change mask size"
# change mask back to bool
mask = mask.astype(np.bool) # note that some boxes might be all zeros if the corresponding mask got cropped out.
# and here is to filter them out
_idx = np.sum(mask, axis=(0, 1)) > 0
mask = mask[:, :, _idx]
class_ids = class_ids[_idx]
# bounding boxes. note that some boxes might be all zeros
# if the corresponding mask got cropped out.
# bbox: [num_instances, (y1, x1, y2, x2)]
bbox = utils.extract_bboxes(mask) # active classes
# different datasets have different classes, so track the
# classes supported in the dataset of this image.
active_class_ids = np.zeros([dataset.num_classes], dtype=np.int32)
source_class_ids = dataset.source_class_ids[dataset.image_info[image_id]["source"]]
active_class_ids[source_class_ids] = 1 # resize masks to smaller size to reduce memory usage
if use_mini_mask:
mask = utils.minimize_mask(bbox, mask, config.mini_mask_shape) # image meta data
image_meta = compose_image_meta(image_id, original_shape, image.shape,
window, scale, active_class_ids) return image, image_meta, class_ids, bbox, mask def build_detection_targets(rpn_rois, gt_class_ids, gt_boxes, gt_masks, config):
"""generate targets for training stage 2 classifier and mask heads.
this is not used in normal training. it's useful for debugging or to train
the mask rcnn heads without using the rpn head. inputs:
rpn_rois: [n, (y1, x1, y2, x2)] proposal boxes.
gt_class_ids: [instance count] integer class ids
gt_boxes: [instance count, (y1, x1, y2, x2)]
gt_masks: [height, width, instance count] ground truth masks. can be full
size or mini-masks. returns:
rois: [train_rois_per_image, (y1, x1, y2, x2)]
class_ids: [train_rois_per_image]. integer class ids.
bboxes: [train_rois_per_image, num_classes, (y, x, log(h), log(w))]. class-specific
bbox refinements.
masks: [train_rois_per_image, height, width, num_classes). class specific masks cropped
to bbox boundaries and resized to neural network output size.
"""
assert rpn_rois.shape[0] > 0
assert gt_class_ids.dtype == np.int32, "expected int but got {}".format(
gt_class_ids.dtype)
assert gt_boxes.dtype == np.int32, "expected int but got {}".format(
gt_boxes.dtype)
assert gt_masks.dtype == np.bool_, "expected bool but got {}".format(
gt_masks.dtype) # it's common to add gt boxes to rois but we don't do that here because
# according to xinlei chen's paper, it doesn't help. # trim empty padding in gt_boxes and gt_masks parts
instance_ids = np.where(gt_class_ids > 0)[0]
assert instance_ids.shape[0] > 0, "image must contain instances."
gt_class_ids = gt_class_ids[instance_ids]
gt_boxes = gt_boxes[instance_ids]
gt_masks = gt_masks[:, :, instance_ids] # compute areas of rois and ground truth boxes.
rpn_roi_area = (rpn_rois[:, 2] - rpn_rois[:, 0]) * \
(rpn_rois[:, 3] - rpn_rois[:, 1])
gt_box_area = (gt_boxes[:, 2] - gt_boxes[:, 0]) * \
(gt_boxes[:, 3] - gt_boxes[:, 1]) # compute overlaps [rpn_rois, gt_boxes]
overlaps = np.zeros((rpn_rois.shape[0], gt_boxes.shape[0]))
for i in range(overlaps.shape[1]):
gt = gt_boxes[i]
overlaps[:, i] = utils.compute_iou(
gt, rpn_rois, gt_box_area[i], rpn_roi_area) # assign rois to gt boxes
rpn_roi_iou_argmax = np.argmax(overlaps, axis=1)
rpn_roi_iou_max = overlaps[np.arange(
overlaps.shape[0]), rpn_roi_iou_argmax]
# gt box assigned to each roi
rpn_roi_gt_boxes = gt_boxes[rpn_roi_iou_argmax]
rpn_roi_gt_class_ids = gt_class_ids[rpn_roi_iou_argmax] # positive rois are those with >= 0.5 iou with a gt box.
fg_ids = np.where(rpn_roi_iou_max > 0.5)[0] # negative rois are those with max iou 0.1-0.5 (hard example mining)
# todo: to hard example mine or not to hard example mine, that's the question
# bg_ids = np.where((rpn_roi_iou_max >= 0.1) & (rpn_roi_iou_max < 0.5))[0]
bg_ids = np.where(rpn_roi_iou_max < 0.5)[0] # subsample rois. aim for 33% foreground.
# fg
fg_roi_count = int(config.train_rois_per_image * config.roi_positive_ratio)
if fg_ids.shape[0] > fg_roi_count:
keep_fg_ids = np.random.choice(fg_ids, fg_roi_count, replace=false)
else:
keep_fg_ids = fg_ids
# bg
remaining = config.train_rois_per_image - keep_fg_ids.shape[0]
if bg_ids.shape[0] > remaining:
keep_bg_ids = np.random.choice(bg_ids, remaining, replace=false)
else:
keep_bg_ids = bg_ids
# combine indices of rois to keep
keep = np.concatenate([keep_fg_ids, keep_bg_ids])
# need more?
remaining = config.train_rois_per_image - keep.shape[0]
if remaining > 0:
# looks like we don't have enough samples to maintain the desired
# balance. reduce requirements and fill in the rest. this is
# likely different from the mask rcnn paper. # there is a small chance we have neither fg nor bg samples.
if keep.shape[0] == 0:
# pick bg regions with easier iou threshold
bg_ids = np.where(rpn_roi_iou_max < 0.5)[0]
assert bg_ids.shape[0] >= remaining
keep_bg_ids = np.random.choice(bg_ids, remaining, replace=false)
assert keep_bg_ids.shape[0] == remaining
keep = np.concatenate([keep, keep_bg_ids])
else:
# fill the rest with repeated bg rois.
keep_extra_ids = np.random.choice(
keep_bg_ids, remaining, replace=true)
keep = np.concatenate([keep, keep_extra_ids])
assert keep.shape[0] == config.train_rois_per_image, \
"keep doesn't match roi batch size {}, {}".format(
keep.shape[0], config.train_rois_per_image) # reset the gt boxes assigned to bg rois.
rpn_roi_gt_boxes[keep_bg_ids, :] = 0
rpn_roi_gt_class_ids[keep_bg_ids] = 0 # for each kept roi, assign a class_id, and for fg rois also add bbox refinement.
rois = rpn_rois[keep]
roi_gt_boxes = rpn_roi_gt_boxes[keep]
roi_gt_class_ids = rpn_roi_gt_class_ids[keep]
roi_gt_assignment = rpn_roi_iou_argmax[keep] # class-aware bbox deltas. [y, x, log(h), log(w)]
bboxes = np.zeros((config.train_rois_per_image,
config.num_classes, 4), dtype=np.float32)
pos_ids = np.where(roi_gt_class_ids > 0)[0]
bboxes[pos_ids, roi_gt_class_ids[pos_ids]] = utils.box_refinement(
rois[pos_ids], roi_gt_boxes[pos_ids, :4])
# normalize bbox refinements
bboxes /= config.bbox_std_dev # generate class-specific target masks
masks = np.zeros((config.train_rois_per_image, config.mask_shape[0], config.mask_shape[1], config.num_classes),
dtype=np.float32)
for i in pos_ids:
class_id = roi_gt_class_ids[i]
assert class_id > 0, "class id must be greater than 0"
gt_id = roi_gt_assignment[i]
class_mask = gt_masks[:, :, gt_id] if config.use_mini_mask:
# create a mask placeholder, the size of the image
placeholder = np.zeros(config.image_shape[:2], dtype=bool)
# gt box
gt_y1, gt_x1, gt_y2, gt_x2 = gt_boxes[gt_id]
gt_w = gt_x2 - gt_x1
gt_h = gt_y2 - gt_y1
# resize mini mask to size of gt box
placeholder[gt_y1:gt_y2, gt_x1:gt_x2] = \
np.round(utils.resize(class_mask, (gt_h, gt_w))).astype(bool)
# place the mini batch in the placeholder
class_mask = placeholder # pick part of the mask and resize it
y1, x1, y2, x2 = rois[i].astype(np.int32)
m = class_mask[y1:y2, x1:x2]
mask = utils.resize(m, config.mask_shape)
masks[i, :, :, class_id] = mask return rois, roi_gt_class_ids, bboxes, masks def build_rpn_targets(image_shape, anchors, gt_class_ids, gt_boxes, config):
"""given the anchors and gt boxes, compute overlaps and identify positive
anchors and deltas to refine them to match their corresponding gt boxes. anchors: [num_anchors, (y1, x1, y2, x2)]
gt_class_ids: [num_gt_boxes] integer class ids.
gt_boxes: [num_gt_boxes, (y1, x1, y2, x2)] returns:
rpn_match: [n] (int32) matches between anchors and gt boxes.
1 = positive anchor, -1 = negative anchor, 0 = neutral
rpn_bbox: [n, (dy, dx, log(dh), log(dw))] anchor bbox deltas.
"""
# rpn match: 1 = positive anchor, -1 = negative anchor, 0 = neutral
rpn_match = np.zeros([anchors.shape[0]], dtype=np.int32)
# rpn bounding boxes: [max anchors per image, (dy, dx, log(dh), log(dw))]
rpn_bbox = np.zeros((config.rpn_train_anchors_per_image, 4)) # handle coco crowds
# a crowd box in coco is a bounding box around several instances. exclude
# them from training. a crowd box is given a negative class id.
crowd_ix = np.where(gt_class_ids < 0)[0]
if crowd_ix.shape[0] > 0:
# filter out crowds from ground truth class ids and boxes
non_crowd_ix = np.where(gt_class_ids > 0)[0]
crowd_boxes = gt_boxes[crowd_ix]
gt_class_ids = gt_class_ids[non_crowd_ix]
gt_boxes = gt_boxes[non_crowd_ix]
# compute overlaps with crowd boxes [anchors, crowds]
crowd_overlaps = utils.compute_overlaps(anchors, crowd_boxes)
crowd_iou_max = np.amax(crowd_overlaps, axis=1)
no_crowd_bool = (crowd_iou_max < 0.001)
else:
# all anchors don't intersect a crowd
no_crowd_bool = np.ones([anchors.shape[0]], dtype=bool) # compute overlaps [num_anchors, num_gt_boxes]
overlaps = utils.compute_overlaps(anchors, gt_boxes) # match anchors to gt boxes
# if an anchor overlaps a gt box with iou >= 0.7 then it's positive.
# if an anchor overlaps a gt box with iou < 0.3 then it's negative.
# neutral anchors are those that don't match the conditions above,
# and they don't influence the loss function.
# however, don't keep any gt box unmatched (rare, but happens). instead,
# match it to the closest anchor (even if its max iou is < 0.3).
#
# 1. set negative anchors first. they get overwritten below if a gt box is
# matched to them. skip boxes in crowd areas.
anchor_iou_argmax = np.argmax(overlaps, axis=1)
anchor_iou_max = overlaps[np.arange(overlaps.shape[0]), anchor_iou_argmax]
rpn_match[(anchor_iou_max < 0.3) & (no_crowd_bool)] = -1
# 2. set an anchor for each gt box (regardless of iou value).
# if multiple anchors have the same iou match all of them
gt_iou_argmax = np.argwhere(overlaps == np.max(overlaps, axis=0))[:,0]
rpn_match[gt_iou_argmax] = 1
# 3. set anchors with high overlap as positive.
rpn_match[anchor_iou_max >= 0.7] = 1 # subsample to balance positive and negative anchors
# don't let positives be more than half the anchors
ids = np.where(rpn_match == 1)[0]
extra = len(ids) - (config.rpn_train_anchors_per_image // 2)
if extra > 0:
# reset the extra ones to neutral
ids = np.random.choice(ids, extra, replace=false)
rpn_match[ids] = 0
# same for negative proposals
ids = np.where(rpn_match == -1)[0]
extra = len(ids) - (config.rpn_train_anchors_per_image -
np.sum(rpn_match == 1))
if extra > 0:
# rest the extra ones to neutral
ids = np.random.choice(ids, extra, replace=false)
rpn_match[ids] = 0 # for positive anchors, compute shift and scale needed to transform them
# to match the corresponding gt boxes.
ids = np.where(rpn_match == 1)[0]
ix = 0 # index into rpn_bbox
# todo: use box_refinement() rather than duplicating the code here
for i, a in zip(ids, anchors[ids]):
# closest gt box (it might have iou < 0.7)
gt = gt_boxes[anchor_iou_argmax[i]] # convert coordinates to center plus width/height.
# gt box
gt_h = gt[2] - gt[0]
gt_w = gt[3] - gt[1]
gt_center_y = gt[0] 0.5 * gt_h
gt_center_x = gt[1] 0.5 * gt_w
# anchor
a_h = a[2] - a[0]
a_w = a[3] - a[1]
a_center_y = a[0] 0.5 * a_h
a_center_x = a[1] 0.5 * a_w # compute the bbox refinement that the rpn should predict.
rpn_bbox[ix] = [
(gt_center_y - a_center_y) / a_h,
(gt_center_x - a_center_x) / a_w,
np.log(gt_h / a_h),
np.log(gt_w / a_w),
]
# normalize
rpn_bbox[ix] /= config.rpn_bbox_std_dev
ix = 1 return rpn_match, rpn_bbox def generate_random_rois(image_shape, count, gt_class_ids, gt_boxes):
"""generates roi proposals similar to what a region proposal network
would generate. image_shape: [height, width, depth]
count: number of rois to generate
gt_class_ids: [n] integer ground truth class ids
gt_boxes: [n, (y1, x1, y2, x2)] ground truth boxes in pixels. returns: [count, (y1, x1, y2, x2)] roi boxes in pixels.
"""
# placeholder
rois = np.zeros((count, 4), dtype=np.int32) # generate random rois around gt boxes (90% of count)
rois_per_box = int(0.9 * count / gt_boxes.shape[0])
for i in range(gt_boxes.shape[0]):
gt_y1, gt_x1, gt_y2, gt_x2 = gt_boxes[i]
h = gt_y2 - gt_y1
w = gt_x2 - gt_x1
# random boundaries
r_y1 = max(gt_y1 - h, 0)
r_y2 = min(gt_y2 h, image_shape[0])
r_x1 = max(gt_x1 - w, 0)
r_x2 = min(gt_x2 w, image_shape[1]) # to avoid generating boxes with zero area, we generate double what
# we need and filter out the extra. if we get fewer valid boxes
# than we need, we loop and try again.
while true:
y1y2 = np.random.randint(r_y1, r_y2, (rois_per_box * 2, 2))
x1x2 = np.random.randint(r_x1, r_x2, (rois_per_box * 2, 2))
# filter out zero area boxes
threshold = 1
y1y2 = y1y2[np.abs(y1y2[:, 0] - y1y2[:, 1]) >=
threshold][:rois_per_box]
x1x2 = x1x2[np.abs(x1x2[:, 0] - x1x2[:, 1]) >=
threshold][:rois_per_box]
if y1y2.shape[0] == rois_per_box and x1x2.shape[0] == rois_per_box:
break # sort on axis 1 to ensure x1 <= x2 and y1 <= y2 and then reshape
# into x1, y1, x2, y2 order
x1, x2 = np.split(np.sort(x1x2, axis=1), 2, axis=1)
y1, y2 = np.split(np.sort(y1y2, axis=1), 2, axis=1)
box_rois = np.hstack([y1, x1, y2, x2])
rois[rois_per_box * i:rois_per_box * (i 1)] = box_rois # generate random rois anywhere in the image (10% of count)
remaining_count = count - (rois_per_box * gt_boxes.shape[0])
# to avoid generating boxes with zero area, we generate double what
# we need and filter out the extra. if we get fewer valid boxes
# than we need, we loop and try again.
while true:
y1y2 = np.random.randint(0, image_shape[0], (remaining_count * 2, 2))
x1x2 = np.random.randint(0, image_shape[1], (remaining_count * 2, 2))
# filter out zero area boxes
threshold = 1
y1y2 = y1y2[np.abs(y1y2[:, 0] - y1y2[:, 1]) >=
threshold][:remaining_count]
x1x2 = x1x2[np.abs(x1x2[:, 0] - x1x2[:, 1]) >=
threshold][:remaining_count]
if y1y2.shape[0] == remaining_count and x1x2.shape[0] == remaining_count:
break # sort on axis 1 to ensure x1 <= x2 and y1 <= y2 and then reshape
# into x1, y1, x2, y2 order
x1, x2 = np.split(np.sort(x1x2, axis=1), 2, axis=1)
y1, y2 = np.split(np.sort(y1y2, axis=1), 2, axis=1)
global_rois = np.hstack([y1, x1, y2, x2])
rois[-remaining_count:] = global_rois
return rois def data_generator(dataset, config, shuffle=true, augment=false, augmentation=none,
random_rois=0, batch_size=1, detection_targets=false,
no_augmentation_sources=none):
"""a generator that returns images and corresponding target class ids,
bounding box deltas, and masks. dataset: the dataset object to pick data from
config: the model config object
shuffle: if true, shuffles the samples before every epoch
augment: (deprecated. use augmentation instead). if true, apply random
image augmentation. currently, only horizontal flipping is offered.
augmentation: optional. an imgaug (https://github.com/aleju/imgaug) augmentation.
for example, passing imgaug.augmenters.fliplr(0.5) flips images
right/left 50% of the time.
random_rois: if > 0 then generate proposals to be used to train the
network classifier and mask heads. useful if training
the mask rcnn part without the rpn.
batch_size: how many images to return in each call
detection_targets: if true, generate detection targets (class ids, bbox
deltas, and masks). typically for debugging or visualizations because
in trainig detection targets are generated by detectiontargetlayer.
no_augmentation_sources: optional. list of sources to exclude for
augmentation. a source is string that identifies a dataset and is
defined in the dataset class. returns a python generator. upon calling next() on it, the
generator returns two lists, inputs and outputs. the contents
of the lists differs depending on the received arguments:
inputs list:
- images: [batch, h, w, c]
- image_meta: [batch, (meta data)] image details. see compose_image_meta()
- rpn_match: [batch, n] integer (1=positive anchor, -1=negative, 0=neutral)
- rpn_bbox: [batch, n, (dy, dx, log(dh), log(dw))] anchor bbox deltas.
- gt_class_ids: [batch, max_gt_instances] integer class ids
- gt_boxes: [batch, max_gt_instances, (y1, x1, y2, x2)]
- gt_masks: [batch, height, width, max_gt_instances]. the height and width
are those of the image unless use_mini_mask is true, in which
case they are defined in mini_mask_shape. outputs list: usually empty in regular training. but if detection_targets
is true then the outputs list contains target class_ids, bbox deltas,
and masks.
"""
b = 0 # batch item index
image_index = -1
image_ids = np.copy(dataset.image_ids)
error_count = 0
no_augmentation_sources = no_augmentation_sources or [] # anchors
# [anchor_count, (y1, x1, y2, x2)]
backbone_shapes = compute_backbone_shapes(config, config.image_shape)
anchors = utils.generate_pyramid_anchors(config.rpn_anchor_scales,
config.rpn_anchor_ratios,
backbone_shapes,
config.backbone_strides,
config.rpn_anchor_stride) # keras requires a generator to run indefinitely.
while true:
try:
# increment index to pick next image. shuffle if at the start of an epoch.
image_index = (image_index 1) % len(image_ids)
if shuffle and image_index == 0:
np.random.shuffle(image_ids) # get gt bounding boxes and masks for image.
image_id = image_ids[image_index] # if the image source is not to be augmented pass none as augmentation
if dataset.image_info[image_id]['source'] in no_augmentation_sources:
image, image_meta, gt_class_ids, gt_boxes, gt_masks = \
load_image_gt(dataset, config, image_id, augment=augment,
augmentation=none,
use_mini_mask=config.use_mini_mask)
else:
image, image_meta, gt_class_ids, gt_boxes, gt_masks = \
load_image_gt(dataset, config, image_id, augment=augment,
augmentation=augmentation,
use_mini_mask=config.use_mini_mask) # skip images that have no instances. this can happen in cases
# where we train on a subset of classes and the image doesn't
# have any of the classes we care about.
if not np.any(gt_class_ids > 0):
continue # rpn targets
rpn_match, rpn_bbox = build_rpn_targets(image.shape, anchors,
gt_class_ids, gt_boxes, config) # mask r-cnn targets
if random_rois:
rpn_rois = generate_random_rois(
image.shape, random_rois, gt_class_ids, gt_boxes)
if detection_targets:
rois, mrcnn_class_ids, mrcnn_bbox, mrcnn_mask =\
build_detection_targets(
rpn_rois, gt_class_ids, gt_boxes, gt_masks, config) # init batch arrays
if b == 0:
batch_image_meta = np.zeros(
(batch_size,) image_meta.shape, dtype=image_meta.dtype)
batch_rpn_match = np.zeros(
[batch_size, anchors.shape[0], 1], dtype=rpn_match.dtype)
batch_rpn_bbox = np.zeros(
[batch_size, config.rpn_train_anchors_per_image, 4], dtype=rpn_bbox.dtype)
batch_images = np.zeros(
(batch_size,) image.shape, dtype=np.float32)
batch_gt_class_ids = np.zeros(
(batch_size, config.max_gt_instances), dtype=np.int32)
batch_gt_boxes = np.zeros(
(batch_size, config.max_gt_instances, 4), dtype=np.int32)
batch_gt_masks = np.zeros(
(batch_size, gt_masks.shape[0], gt_masks.shape[1],
config.max_gt_instances), dtype=gt_masks.dtype)
if random_rois:
batch_rpn_rois = np.zeros(
(batch_size, rpn_rois.shape[0], 4), dtype=rpn_rois.dtype)
if detection_targets:
batch_rois = np.zeros(
(batch_size,) rois.shape, dtype=rois.dtype)
batch_mrcnn_class_ids = np.zeros(
(batch_size,) mrcnn_class_ids.shape, dtype=mrcnn_class_ids.dtype)
batch_mrcnn_bbox = np.zeros(
(batch_size,) mrcnn_bbox.shape, dtype=mrcnn_bbox.dtype)
batch_mrcnn_mask = np.zeros(
(batch_size,) mrcnn_mask.shape, dtype=mrcnn_mask.dtype) # if more instances than fits in the array, sub-sample from them.
if gt_boxes.shape[0] > config.max_gt_instances:
ids = np.random.choice(
np.arange(gt_boxes.shape[0]), config.max_gt_instances, replace=false)
gt_class_ids = gt_class_ids[ids]
gt_boxes = gt_boxes[ids]
gt_masks = gt_masks[:, :, ids] # add to batch
batch_image_meta[b] = image_meta
batch_rpn_match[b] = rpn_match[:, np.newaxis]
batch_rpn_bbox[b] = rpn_bbox
batch_images[b] = mold_image(image.astype(np.float32), config)
batch_gt_class_ids[b, :gt_class_ids.shape[0]] = gt_class_ids
batch_gt_boxes[b, :gt_boxes.shape[0]] = gt_boxes
batch_gt_masks[b, :, :, :gt_masks.shape[-1]] = gt_masks
if random_rois:
batch_rpn_rois[b] = rpn_rois
if detection_targets:
batch_rois[b] = rois
batch_mrcnn_class_ids[b] = mrcnn_class_ids
batch_mrcnn_bbox[b] = mrcnn_bbox
batch_mrcnn_mask[b] = mrcnn_mask
b = 1 # batch full?
if b >= batch_size:
inputs = [batch_images, batch_image_meta, batch_rpn_match, batch_rpn_bbox,
batch_gt_class_ids, batch_gt_boxes, batch_gt_masks]
outputs = [] if random_rois:
inputs.extend([batch_rpn_rois])
if detection_targets:
inputs.extend([batch_rois])
# keras requires that output and targets have the same number of dimensions
batch_mrcnn_class_ids = np.expand_dims(
batch_mrcnn_class_ids, -1)
outputs.extend(
[batch_mrcnn_class_ids, batch_mrcnn_bbox, batch_mrcnn_mask]) yield inputs, outputs # start a new batch
b = 0
except (generatorexit, keyboardinterrupt):
raise
except:
# log it and skip the image
logging.exception("error processing image {}".format(
dataset.image_info[image_id]))
error_count = 1
if error_count > 5:
raise ############################################################
# maskrcnn class
############################################################ class maskrcnn():
"""encapsulates the mask rcnn model functionality. the actual keras model is in the keras_model property.
""" def __init__(self, mode, config, model_dir):
"""
mode: either "training" or "inference"
config: a sub-class of the config class
model_dir: directory to save training logs and trained weights
"""
assert mode in ['training', 'inference']
self.mode = mode
self.config = config
self.model_dir = model_dir
self.set_log_dir()
self.keras_model = self.build(mode=mode, config=config) def build(self, mode, config):
"""build mask r-cnn architecture.
input_shape: the shape of the input image.
mode: either "training" or "inference". the inputs and
outputs of the model differ accordingly.
"""
assert mode in ['training', 'inference'] # image size must be dividable by 2 multiple times
h, w = config.image_shape[:2]
if h / 2**6 != int(h / 2**6) or w / 2**6 != int(w / 2**6):
raise exception("image size must be dividable by 2 at least 6 times "
"to avoid fractions when downscaling and upscaling."
"for example, use 256, 320, 384, 448, 512, ... etc. ") # inputs
input_image = kl.input(
shape=[none, none, config.image_shape[2]], name="input_image")
input_image_meta = kl.input(shape=[config.image_meta_size],
name="input_image_meta")
if mode == "training":
# rpn gt
input_rpn_match = kl.input(
shape=[none, 1], name="input_rpn_match", dtype=tf.int32)
input_rpn_bbox = kl.input(
shape=[none, 4], name="input_rpn_bbox", dtype=tf.float32) # detection gt (class ids, bounding boxes, and masks)
# 1. gt class ids (zero padded)
input_gt_class_ids = kl.input(
shape=[none], name="input_gt_class_ids", dtype=tf.int32)
# 2. gt boxes in pixels (zero padded)
# [batch, max_gt_instances, (y1, x1, y2, x2)] in image coordinates
input_gt_boxes = kl.input(
shape=[none, 4], name="input_gt_boxes", dtype=tf.float32)
# normalize coordinates
gt_boxes = kl.lambda(lambda x: norm_boxes_graph(
x, k.shape(input_image)[1:3]))(input_gt_boxes)
# 3. gt masks (zero padded)
# [batch, height, width, max_gt_instances]
if config.use_mini_mask:
input_gt_masks = kl.input(
shape=[config.mini_mask_shape[0],
config.mini_mask_shape[1], none],
name="input_gt_masks", dtype=bool)
else:
input_gt_masks = kl.input(
shape=[config.image_shape[0], config.image_shape[1], none],
name="input_gt_masks", dtype=bool)
elif mode == "inference":
# anchors in normalized coordinates
input_anchors = kl.input(shape=[none, 4], name="input_anchors") # build the shared convolutional layers.
# bottom-up layers
# returns a list of the last layers of each stage, 5 in total.
# don't create the thead (stage 5), so we pick the 4th item in the list.
if callable(config.backbone):
_, c2, c3, c4, c5 = config.backbone(input_image, stage5=true,
train_bn=config.train_bn)
else:
_, c2, c3, c4, c5 = resnet_graph(input_image, config.backbone,
stage5=true, train_bn=config.train_bn)
# top-down layers
# todo: add assert to varify feature map sizes match what's in config
p5 = kl.conv2d(config.top_down_pyramid_size, (1, 1), name='fpn_c5p5')(c5)
p4 = kl.add(name="fpn_p4add")([
kl.upsampling2d(size=(2, 2), name="fpn_p5upsampled")(p5),
kl.conv2d(config.top_down_pyramid_size, (1, 1), name='fpn_c4p4')(c4)])
p3 = kl.add(name="fpn_p3add")([
kl.upsampling2d(size=(2, 2), name="fpn_p4upsampled")(p4),
kl.conv2d(config.top_down_pyramid_size, (1, 1), name='fpn_c3p3')(c3)])
p2 = kl.add(name="fpn_p2add")([
kl.upsampling2d(size=(2, 2), name="fpn_p3upsampled")(p3),
kl.conv2d(config.top_down_pyramid_size, (1, 1), name='fpn_c2p2')(c2)])
# attach 3x3 conv to all p layers to get the final feature maps.
p2 = kl.conv2d(config.top_down_pyramid_size, (3, 3), padding="same", name="fpn_p2")(p2)
p3 = kl.conv2d(config.top_down_pyramid_size, (3, 3), padding="same", name="fpn_p3")(p3)
p4 = kl.conv2d(config.top_down_pyramid_size, (3, 3), padding="same", name="fpn_p4")(p4)
p5 = kl.conv2d(config.top_down_pyramid_size, (3, 3), padding="same", name="fpn_p5")(p5)
# p6 is used for the 5th anchor scale in rpn. generated by
# subsampling from p5 with stride of 2.
p6 = kl.maxpooling2d(pool_size=(1, 1), strides=2, name="fpn_p6")(p5) # note that p6 is used in rpn, but not in the classifier heads.
rpn_feature_maps = [p2, p3, p4, p5, p6]
mrcnn_feature_maps = [p2, p3, p4, p5] # anchors
if mode == "training":
anchors = self.get_anchors(config.image_shape)
# duplicate across the batch dimension because keras requires it
# todo: can this be optimized to avoid duplicating the anchors?
anchors = np.broadcast_to(anchors, (config.batch_size,) anchors.shape)
# a hack to get around keras's bad support for constants
anchors = kl.lambda(lambda x: tf.variable(anchors), name="anchors")(input_image)
else:
anchors = input_anchors # rpn model
rpn = build_rpn_model(config.rpn_anchor_stride,
len(config.rpn_anchor_ratios), config.top_down_pyramid_size)
# loop through pyramid layers
layer_outputs = [] # list of lists
for p in rpn_feature_maps:
layer_outputs.append(rpn([p]))
# concatenate layer outputs
# convert from list of lists of level outputs to list of lists
# of outputs across levels.
# e.g. [[a1, b1, c1], [a2, b2, c2]] => [[a1, a2], [b1, b2], [c1, c2]]
output_names = ["rpn_class_logits", "rpn_class", "rpn_bbox"]
outputs = list(zip(*layer_outputs))
outputs = [kl.concatenate(axis=1, name=n)(list(o))
for o, n in zip(outputs, output_names)] rpn_class_logits, rpn_class, rpn_bbox = outputs # generate proposals
# proposals are [batch, n, (y1, x1, y2, x2)] in normalized coordinates
# and zero padded.
proposal_count = config.post_nms_rois_training if mode == "training"\
else config.post_nms_rois_inference
rpn_rois = proposallayer(
proposal_count=proposal_count,
nms_threshold=config.rpn_nms_threshold,
name="roi",
config=config)([rpn_class, rpn_bbox, anchors]) if mode == "training":
# class id mask to mark class ids supported by the dataset the image
# came from.
active_class_ids = kl.lambda(
lambda x: parse_image_meta_graph(x)["active_class_ids"]
)(input_image_meta) if not config.use_rpn_rois:
# ignore predicted rois and use rois provided as an input.
input_rois = kl.input(shape=[config.post_nms_rois_training, 4],
name="input_roi", dtype=np.int32)
# normalize coordinates
target_rois = kl.lambda(lambda x: norm_boxes_graph(
x, k.shape(input_image)[1:3]))(input_rois)
else:
target_rois = rpn_rois # generate detection targets
# subsamples proposals and generates target outputs for training
# note that proposal class ids, gt_boxes, and gt_masks are zero
# padded. equally, returned rois and targets are zero padded.
rois, target_class_ids, target_bbox, target_mask =\
detectiontargetlayer(config, name="proposal_targets")([
target_rois, input_gt_class_ids, gt_boxes, input_gt_masks]) # network heads
# todo: verify that this handles zero padded rois
mrcnn_class_logits, mrcnn_class, mrcnn_bbox, _ =\
fpn_classifier_graph(rois, mrcnn_feature_maps, input_image_meta,
config.pool_size, config.num_classes,
train_bn=config.train_bn,
fc_layers_size=config.fpn_classif_fc_layers_size) mrcnn_mask = build_fpn_mask_graph(rois, mrcnn_feature_maps,
input_image_meta,
config.mask_pool_size,
config.num_classes,
train_bn=config.train_bn) # todo: clean up (use tf.identify if necessary)
output_rois = kl.lambda(lambda x: x * 1, name="output_rois")(rois) # losses
rpn_class_loss = kl.lambda(lambda x: rpn_class_loss_graph(*x), name="rpn_class_loss")(
[input_rpn_match, rpn_class_logits])
rpn_bbox_loss = kl.lambda(lambda x: rpn_bbox_loss_graph(config, *x), name="rpn_bbox_loss")(
[input_rpn_bbox, input_rpn_match, rpn_bbox])
class_loss = kl.lambda(lambda x: mrcnn_class_loss_graph(*x), name="mrcnn_class_loss")(
[target_class_ids, mrcnn_class_logits, active_class_ids])
bbox_loss = kl.lambda(lambda x: mrcnn_bbox_loss_graph(*x), name="mrcnn_bbox_loss")(
[target_bbox, target_class_ids, mrcnn_bbox])
mask_loss = kl.lambda(lambda x: mrcnn_mask_loss_graph(*x), name="mrcnn_mask_loss")(
[target_mask, target_class_ids, mrcnn_mask]) # model
inputs = [input_image, input_image_meta,
input_rpn_match, input_rpn_bbox, input_gt_class_ids, input_gt_boxes, input_gt_masks]
if not config.use_rpn_rois:
inputs.append(input_rois)
outputs = [rpn_class_logits, rpn_class, rpn_bbox,
mrcnn_class_logits, mrcnn_class, mrcnn_bbox, mrcnn_mask,
rpn_rois, output_rois,
rpn_class_loss, rpn_bbox_loss, class_loss, bbox_loss, mask_loss]
model = km.model(inputs, outputs, name='mask_rcnn')
else:
# network heads
# proposal classifier and bbox regressor heads
mrcnn_class_logits, mrcnn_class, mrcnn_bbox, feature_maps =\
fpn_classifier_graph(rpn_rois, mrcnn_feature_maps, input_image_meta,
config.pool_size, config.num_classes,
train_bn=config.train_bn,
fc_layers_size=config.fpn_classif_fc_layers_size) # detections
# output is [batch, num_detections, (y1, x1, y2, x2, class_id, score)] in
# normalized coordinates
detections = detectionlayer(config, name="mrcnn_detection")(
[rpn_rois, mrcnn_class, mrcnn_bbox, input_image_meta, feature_maps]) # create masks for detections
detection_boxes = kl.lambda(lambda x: x[..., :4])(detections)
mrcnn_mask = build_fpn_mask_graph(detection_boxes, mrcnn_feature_maps,
input_image_meta,
config.mask_pool_size,
config.num_classes,
train_bn=config.train_bn) model = km.model([input_image, input_image_meta, input_anchors],
[detections, mrcnn_class, mrcnn_bbox,
mrcnn_mask, rpn_rois, rpn_class, rpn_bbox],
name='mask_rcnn') # add multi-gpu support.
if config.gpu_count > 1:
from mrcnn.parallel_model import parallelmodel
model = parallelmodel(model, config.gpu_count) return model def find_last(self):
"""finds the last checkpoint file of the last trained model in the
model directory.
returns:
the path of the last checkpoint file
"""
# get directory names. each directory corresponds to a model
dir_names = next(os.walk(self.model_dir))[1]
key = self.config.name.lower()
dir_names = filter(lambda f: f.startswith(key), dir_names)
dir_names = sorted(dir_names)
if not dir_names:
import errno
raise filenotfounderror(
errno.enoent,
"could not find model directory under {}".format(self.model_dir))
# pick last directory
dir_name = os.path.join(self.model_dir, dir_names[-1])
# find the last checkpoint
checkpoints = next(os.walk(dir_name))[2]
checkpoints = filter(lambda f: f.startswith("mask_rcnn"), checkpoints)
checkpoints = sorted(checkpoints)
if not checkpoints:
import errno
raise filenotfounderror(
errno.enoent, "could not find weight files in {}".format(dir_name))
checkpoint = os.path.join(dir_name, checkpoints[-1])
return checkpoint def load_weights(self, filepath, by_name=false, exclude=none):
"""modified version of the corresponding keras function with
the addition of multi-gpu support and the ability to exclude
some layers from loading.
exclude: list of layer names to exclude
"""
import h5py
# conditional import to support versions of keras before 2.2
# todo: remove in about 6 months (end of 2018)
try:
from keras.engine import saving
except importerror:
# keras before 2.2 used the 'topology' namespace.
from keras.engine import topology as saving if exclude:
by_name = true if h5py is none:
raise importerror('`load_weights` requires h5py.')
f = h5py.file(filepath, mode='r')
if 'layer_names' not in f.attrs and 'model_weights' in f:
f = f['model_weights'] # in multi-gpu training, we wrap the model. get layers
# of the inner model because they have the weights.
keras_model = self.keras_model
layers = keras_model.inner_model.layers if hasattr(keras_model, "inner_model")\
else keras_model.layers # exclude some layers
if exclude:
layers = filter(lambda l: l.name not in exclude, layers) if by_name:
saving.load_weights_from_hdf5_group_by_name(f, layers)
else:
saving.load_weights_from_hdf5_group(f, layers)
if hasattr(f, 'close'):
f.close() # update the log directory
self.set_log_dir(filepath) def get_imagenet_weights(self):
"""downloads imagenet trained weights from keras.
returns path to weights file.
"""
from keras.utils.data_utils import get_file
tf_weights_path_no_top = 'https://github.com/fchollet/deep-learning-models/'\
'releases/download/v0.2/'\
'resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5'
weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
tf_weights_path_no_top,
cache_subdir='models',
md5_hash='a268eb855778b3df3c7506639542a6af')
return weights_path def compile(self, learning_rate, momentum):
"""gets the model ready for training. adds losses, regularization, and
metrics. then calls the keras compile() function.
"""
# optimizer object
optimizer = keras.optimizers.sgd(
lr=learning_rate, momentum=momentum,
clipnorm=self.config.gradient_clip_norm)
# add losses
# first, clear previously set losses to avoid duplication
self.keras_model._losses = []
self.keras_model._per_input_losses = {}
loss_names = [
"rpn_class_loss", "rpn_bbox_loss",
"mrcnn_class_loss", "mrcnn_bbox_loss", "mrcnn_mask_loss"]
for name in loss_names:
layer = self.keras_model.get_layer(name)
if layer.output in self.keras_model.losses:
continue
loss = (
tf.reduce_mean(layer.output, keepdims=true)
* self.config.loss_weights.get(name, 1.))
self.keras_model.add_loss(loss) # add l2 regularization
# skip gamma and beta weights of batch normalization layers.
reg_losses = [
keras.regularizers.l2(self.config.weight_decay)(w) / tf.cast(tf.size(w), tf.float32)
for w in self.keras_model.trainable_weights
if 'gamma' not in w.name and 'beta' not in w.name]
self.keras_model.add_loss(tf.add_n(reg_losses)) # compile
self.keras_model.compile(
optimizer=optimizer,
loss=[none] * len(self.keras_model.outputs)) # add metrics for losses
for name in loss_names:
if name in self.keras_model.metrics_names:
continue
layer = self.keras_model.get_layer(name)
self.keras_model.metrics_names.append(name)
loss = (
tf.reduce_mean(layer.output, keepdims=true)
* self.config.loss_weights.get(name, 1.))
self.keras_model.metrics_tensors.append(loss) def set_trainable(self, layer_regex, keras_model=none, indent=0, verbose=1):
"""sets model layers as trainable if their names match
the given regular expression.
"""
# print message on the first call (but not on recursive calls)
if verbose > 0 and keras_model is none:
log("selecting layers to train") keras_model = keras_model or self.keras_model # in multi-gpu training, we wrap the model. get layers
# of the inner model because they have the weights.
layers = keras_model.inner_model.layers if hasattr(keras_model, "inner_model")\
else keras_model.layers for layer in layers:
# is the layer a model?
if layer.__class__.__name__ == 'model':
print("in model: ", layer.name)
self.set_trainable(
layer_regex, keras_model=layer, indent=indent 4)
continue if not layer.weights:
continue
# is it trainable?
trainable = bool(re.fullmatch(layer_regex, layer.name))
# update layer. if layer is a container, update inner layer.
if layer.__class__.__name__ == 'timedistributed':
layer.layer.trainable = trainable
else:
layer.trainable = trainable
# print trainable layer names
if trainable and verbose > 0:
log("{}{:20} ({})".format(" " * indent, layer.name,
layer.__class__.__name__)) def set_log_dir(self, model_path=none):
"""sets the model log directory and epoch counter. model_path: if none, or a format different from what this code uses
then set a new log directory and start epochs from 0. otherwise,
extract the log directory and the epoch counter from the file
name.
"""
# set date and epoch counter as if starting a new model
self.epoch = 0
now = datetime.datetime.now() # if we have a model path with date and epochs use them
if model_path:
# continue from we left of. get epoch and date from the file name
# a sample model path might look like:
# \path\to\logs\coco20171029t2315\mask_rcnn_coco_0001.h5 (windows)
# /path/to/logs/coco20171029t2315/mask_rcnn_coco_0001.h5 (linux)
regex = r".*[/\\][\w-] (\d{4})(\d{2})(\d{2})t(\d{2})(\d{2})[/\\]mask\_rcnn\_[\w-] (\d{4})\.h5"
m = re.match(regex, model_path)
if m:
now = datetime.datetime(int(m.group(1)), int(m.group(2)), int(m.group(3)),
int(m.group(4)), int(m.group(5)))
# epoch number in file is 1-based, and in keras code it's 0-based.
# so, adjust for that then increment by one to start from the next epoch
self.epoch = int(m.group(6)) - 1 1
print('re-starting from epoch %d' % self.epoch) # directory for training logs
self.log_dir = os.path.join(self.model_dir, "{}{:%y%m%dt%h%m}".format(
self.config.name.lower(), now)) # path to save after each epoch. include placeholders that get filled by keras.
self.checkpoint_path = os.path.join(self.log_dir, "mask_rcnn_{}_*epoch*.h5".format(
self.config.name.lower()))
self.checkpoint_path = self.checkpoint_path.replace(
"*epoch*", "{epoch:04d}") def train(self, train_dataset, val_dataset, learning_rate, epochs, layers,
augmentation=none, custom_callbacks=none, no_augmentation_sources=none):
"""train the model.
train_dataset, val_dataset: training and validation dataset objects.
learning_rate: the learning rate to train with
epochs: number of training epochs. note that previous training epochs
are considered to be done alreay, so this actually determines
the epochs to train in total rather than in this particaular
call.
layers: allows selecting wich layers to train. it can be:
- a regular expression to match layer names to train
- one of these predefined values:
heads: the rpn, classifier and mask heads of the network
all: all the layers
3 : train resnet stage 3 and up
4 : train resnet stage 4 and up
5 : train resnet stage 5 and up
augmentation: optional. an imgaug (https://github.com/aleju/imgaug)
augmentation. for example, passing imgaug.augmenters.fliplr(0.5)
flips images right/left 50% of the time. you can pass complex
augmentations as well. this augmentation applies 50% of the
time, and when it does it flips images right/left half the time
and adds a gaussian blur with a random sigma in range 0 to 5. augmentation = imgaug.augmenters.sometimes(0.5, [
imgaug.augmenters.fliplr(0.5),
imgaug.augmenters.gaussianblur(sigma=(0.0, 5.0))
])
custom_callbacks: optional. add custom callbacks to be called
with the keras fit_generator method. must be list of type keras.callbacks.
no_augmentation_sources: optional. list of sources to exclude for
augmentation. a source is string that identifies a dataset and is
defined in the dataset class.
"""
assert self.mode == "training", "create model in training mode." # pre-defined layer regular expressions
layer_regex = {
# all layers but the backbone
"heads": r"(mrcnn\_.*)|(rpn\_.*)|(fpn\_.*)",
# from a specific resnet stage and up
"3 ": r"(res3.*)|(bn3.*)|(res4.*)|(bn4.*)|(res5.*)|(bn5.*)|(mrcnn\_.*)|(rpn\_.*)|(fpn\_.*)",
"4 ": r"(res4.*)|(bn4.*)|(res5.*)|(bn5.*)|(mrcnn\_.*)|(rpn\_.*)|(fpn\_.*)",
"5 ": r"(res5.*)|(bn5.*)|(mrcnn\_.*)|(rpn\_.*)|(fpn\_.*)",
# all layers
"all": ".*",
}
if layers in layer_regex.keys():
layers = layer_regex[layers] # data generators
train_generator = data_generator(train_dataset, self.config, shuffle=true,
augmentation=augmentation,
batch_size=self.config.batch_size,
no_augmentation_sources=no_augmentation_sources)
val_generator = data_generator(val_dataset, self.config, shuffle=true,
batch_size=self.config.batch_size) # create log_dir if it does not exist
if not os.path.exists(self.log_dir):
os.makedirs(self.log_dir) # callbacks
callbacks = [
keras.callbacks.tensorboard(log_dir=self.log_dir,
histogram_freq=0, write_graph=true, write_images=false),
keras.callbacks.modelcheckpoint(self.checkpoint_path,
verbose=0, save_weights_only=true),
] # add custom callbacks to the list
if custom_callbacks:
callbacks = custom_callbacks # train
log("\nstarting at epoch {}. lr={}\n".format(self.epoch, learning_rate))
log("checkpoint path: {}".format(self.checkpoint_path))
self.set_trainable(layers)
self.compile(learning_rate, self.config.learning_momentum) # work-around for windows: keras fails on windows when using
# multiprocessing workers. see discussion here:
# https://github.com/matterport/mask_rcnn/issues/13#issuecomment-353124009
if os.name is 'nt':
workers = 0
else:
workers = multiprocessing.cpu_count() self.keras_model.fit_generator(
train_generator,
initial_epoch=self.epoch,
epochs=epochs,
steps_per_epoch=self.config.steps_per_epoch,
callbacks=callbacks,
validation_data=val_generator,
validation_steps=self.config.validation_steps,
max_queue_size=100,
workers=workers,
use_multiprocessing=true,
)
self.epoch = max(self.epoch, epochs) def mold_inputs(self, images):
"""takes a list of images and modifies them to the format expected
as an input to the neural network.
images: list of image matrices [height,width,depth]. images can have
different sizes. returns 3 numpy matrices:
molded_images: [n, h, w, 3]. images resized and normalized.
image_metas: [n, length of meta data]. details about each image.
windows: [n, (y1, x1, y2, x2)]. the portion of the image that has the
original image (padding excluded).
"""
molded_images = []
image_metas = []
windows = []
for image in images:
# resize image
# todo: move resizing to mold_image()
molded_image, window, scale, padding, crop = utils.resize_image(
image,
min_dim=self.config.image_min_dim,
min_scale=self.config.image_min_scale,
max_dim=self.config.image_max_dim,
mode=self.config.image_resize_mode)
molded_image = mold_image(molded_image, self.config)
# build image_meta
image_meta = compose_image_meta(
0, image.shape, molded_image.shape, window, scale,
np.zeros([self.config.num_classes], dtype=np.int32))
# append
molded_images.append(molded_image)
windows.append(window)
image_metas.append(image_meta)
# pack into arrays
molded_images = np.stack(molded_images)
image_metas = np.stack(image_metas)
windows = np.stack(windows)
return molded_images, image_metas, windows def unmold_detections(self, detections, mrcnn_mask, original_image_shape,
image_shape, window):
"""reformats the detections of one image from the format of the neural
network output to a format suitable for use in the rest of the
application. detections: [n, (y1, x1, y2, x2, class_id, score)] in normalized coordinates
mrcnn_mask: [n, height, width, num_classes]
original_image_shape: [h, w, c] original image shape before resizing
image_shape: [h, w, c] shape of the image after resizing and padding
window: [y1, x1, y2, x2] pixel coordinates of box in the image where the real
image is excluding the padding. returns:
boxes: [n, (y1, x1, y2, x2)] bounding boxes in pixels
class_ids: [n] integer class ids for each bounding box
scores: [n] float probability scores of the class_id
masks: [height, width, num_instances] instance masks
"""
# how many detections do we have?
# detections array is padded with zeros. find the first class_id == 0.
zero_ix = np.where(detections[:, 4] == 0)[0]
n = zero_ix[0] if zero_ix.shape[0] > 0 else detections.shape[0] # extract boxes, class_ids, scores, and class-specific masks
boxes = detections[:n, :4]
class_ids = detections[:n, 4].astype(np.int32)
scores = detections[:n, 5]
features = detections[:n, 6:]
masks = mrcnn_mask[np.arange(n), :, :, class_ids] # translate normalized coordinates in the resized image to pixel
# coordinates in the original image before resizing
window = utils.norm_boxes(window, image_shape[:2])
wy1, wx1, wy2, wx2 = window
shift = np.array([wy1, wx1, wy1, wx1])
wh = wy2 - wy1 # window height
ww = wx2 - wx1 # window width
scale = np.array([wh, ww, wh, ww])
# convert boxes to normalized coordinates on the window
boxes = np.divide(boxes - shift, scale)
# convert boxes to pixel coordinates on the original image
boxes = utils.denorm_boxes(boxes, original_image_shape[:2]) # filter out detections with zero area. happens in early training when
# network weights are still random
exclude_ix = np.where(
(boxes[:, 2] - boxes[:, 0]) * (boxes[:, 3] - boxes[:, 1]) <= 0)[0]
if exclude_ix.shape[0] > 0:
boxes = np.delete(boxes, exclude_ix, axis=0)
class_ids = np.delete(class_ids, exclude_ix, axis=0)
scores = np.delete(scores, exclude_ix, axis=0)
masks = np.delete(masks, exclude_ix, axis=0)
n = class_ids.shape[0] # resize masks to original image size and set boundary threshold.
full_masks = []
for i in range(n):
# convert neural network mask to full size mask
full_mask = utils.unmold_mask(masks[i], boxes[i], original_image_shape)
full_masks.append(full_mask)
full_masks = np.stack(full_masks, axis=-1)\
if full_masks else np.empty(original_image_shape[:2] (0,)) return boxes, class_ids, scores, full_masks, features def detect(self, images, verbose=0):
"""runs the detection pipeline. images: list of images, potentially of different sizes. returns a list of dicts, one dict per image. the dict contains:
rois: [n, (y1, x1, y2, x2)] detection bounding boxes
class_ids: [n] int class ids
scores: [n] float probability scores for the class ids
masks: [h, w, n] instance binary masks
"""
assert self.mode == "inference", "create model in inference mode."
assert len(
images) == self.config.batch_size, "len(images) must be equal to batch_size" if verbose:
log("processing {} images".format(len(images)))
for image in images:
log("image", image) # mold inputs to format expected by the neural network
molded_images, image_metas, windows = self.mold_inputs(images) # validate image sizes
# all images in a batch must be of the same size
image_shape = molded_images[0].shape
for g in molded_images[1:]:
assert g.shape == image_shape,\
"after resizing, all images must have the same size. check image_resize_mode and image sizes." # anchors
anchors = self.get_anchors(image_shape)
# duplicate across the batch dimension because keras requires it
# todo: can this be optimized to avoid duplicating the anchors?
anchors = np.broadcast_to(anchors, (self.config.batch_size,) anchors.shape) if verbose:
log("molded_images", molded_images)
log("image_metas", image_metas)
log("anchors", anchors)
# run object detection
detections, _, _, mrcnn_mask, _, _, _ =\
self.keras_model.predict([molded_images, image_metas, anchors], verbose=0)
# process detections
results = []
for i, image in enumerate(images):
final_rois, final_class_ids, final_scores, final_masks, features =\
self.unmold_detections(detections[i], mrcnn_mask[i],
image.shape, molded_images[i].shape,
windows[i])
results.append({
"rois": final_rois,
"class_ids": final_class_ids,
"scores": final_scores,
"masks": final_masks,
"features": features,
})
return results def detect_molded(self, molded_images, image_metas, verbose=0):
"""runs the detection pipeline, but expect inputs that are
molded already. used mostly for debugging and inspecting
the model. molded_images: list of images loaded using load_image_gt()
image_metas: image meta data, also returned by load_image_gt() returns a list of dicts, one dict per image. the dict contains:
rois: [n, (y1, x1, y2, x2)] detection bounding boxes
class_ids: [n] int class ids
scores: [n] float probability scores for the class ids
masks: [h, w, n] instance binary masks
"""
assert self.mode == "inference", "create model in inference mode."
assert len(molded_images) == self.config.batch_size,\
"number of images must be equal to batch_size" if verbose:
log("processing {} images".format(len(molded_images)))
for image in molded_images:
log("image", image) # validate image sizes
# all images in a batch must be of the same size
image_shape = molded_images[0].shape
for g in molded_images[1:]:
assert g.shape == image_shape, "images must have the same size" # anchors
anchors = self.get_anchors(image_shape)
# duplicate across the batch dimension because keras requires it
# todo: can this be optimized to avoid duplicating the anchors?
anchors = np.broadcast_to(anchors, (self.config.batch_size,) anchors.shape) if verbose:
log("molded_images", molded_images)
log("image_metas", image_metas)
log("anchors", anchors)
# run object detection
detections, _, _, mrcnn_mask, _, _, _ =\
self.keras_model.predict([molded_images, image_metas, anchors], verbose=0)
# process detections
results = []
for i, image in enumerate(molded_images):
window = [0, 0, image.shape[0], image.shape[1]]
final_rois, final_class_ids, final_scores, final_masks =\
self.unmold_detections(detections[i], mrcnn_mask[i],
image.shape, molded_images[i].shape,
window)
results.append({
"rois": final_rois,
"class_ids": final_class_ids,
"scores": final_scores,
"masks": final_masks,
})
return results def get_anchors(self, image_shape):
"""returns anchor pyramid for the given image size."""
backbone_shapes = compute_backbone_shapes(self.config, image_shape)
# cache anchors and reuse if image shape is the same
if not hasattr(self, "_anchor_cache"):
self._anchor_cache = {}
if not tuple(image_shape) in self._anchor_cache:
# generate anchors
a = utils.generate_pyramid_anchors(
self.config.rpn_anchor_scales,
self.config.rpn_anchor_ratios,
backbone_shapes,
self.config.backbone_strides,
self.config.rpn_anchor_stride)
# keep a copy of the latest anchors in pixel coordinates because
# it's used in inspect_model notebooks.
# todo: remove this after the notebook are refactored to not use it
self.anchors = a
# normalize coordinates
self._anchor_cache[tuple(image_shape)] = utils.norm_boxes(a, image_shape[:2])
return self._anchor_cache[tuple(image_shape)] def ancestor(self, tensor, name, checked=none):
"""finds the ancestor of a tf tensor in the computation graph.
tensor: tensorflow symbolic tensor.
name: name of ancestor tensor to find
checked: for internal use. a list of tensors that were already
searched to avoid loops in traversing the graph.
"""
checked = checked if checked is not none else []
# put a limit on how deep we go to avoid very long loops
if len(checked) > 500:
return none
# convert name to a regex and allow matching a number prefix
# because keras adds them automatically
if isinstance(name, str):
name = re.compile(name.replace("/", r"(\_\d )*/")) parents = tensor.op.inputs
for p in parents:
if p in checked:
continue
if bool(re.fullmatch(name, p.name)):
return p
checked.append(p)
a = self.ancestor(p, name, checked)
if a is not none:
return a
return none def find_trainable_layer(self, layer):
"""if a layer is encapsulated by another layer, this function
digs through the encapsulation and returns the layer that holds
the weights.
"""
if layer.__class__.__name__ == 'timedistributed':
return self.find_trainable_layer(layer.layer)
return layer def get_trainable_layers(self):
"""returns a list of layers that have weights."""
layers = []
# loop through all layers
for l in self.keras_model.layers:
# if layer is a wrapper, find inner trainable layer
l = self.find_trainable_layer(l)
# include layer if it has weights
if l.get_weights():
layers.append(l)
return layers def run_graph(self, images, outputs, image_metas=none):
"""runs a sub-set of the computation graph that computes the given
outputs. image_metas: if provided, the images are assumed to be already
molded (i.e. resized, padded, and normalized) outputs: list of tuples (name, tensor) to compute. the tensors are
symbolic tensorflow tensors and the names are for easy tracking. returns an ordered dict of results. keys are the names received in the
input and values are numpy arrays.
"""
model = self.keras_model # organize desired outputs into an ordered dict
outputs = ordereddict(outputs)
for o in outputs.values():
assert o is not none # build a keras function to run parts of the computation graph
inputs = model.inputs
if model.uses_learning_phase and not isinstance(k.learning_phase(), int):
inputs = [k.learning_phase()]
kf = k.function(model.inputs, list(outputs.values())) # prepare inputs
if image_metas is none:
molded_images, image_metas, _ = self.mold_inputs(images)
else:
molded_images = images
image_shape = molded_images[0].shape
# anchors
anchors = self.get_anchors(image_shape)
# duplicate across the batch dimension because keras requires it
# todo: can this be optimized to avoid duplicating the anchors?
anchors = np.broadcast_to(anchors, (self.config.batch_size,) anchors.shape)
model_in = [molded_images, image_metas, anchors] # run inference
if model.uses_learning_phase and not isinstance(k.learning_phase(), int):
model_in.append(0.)
outputs_np = kf(model_in) # pack the generated numpy arrays into a a dict and log the results.
outputs_np = ordereddict([(k, v)
for k, v in zip(outputs.keys(), outputs_np)])
for k, v in outputs_np.items():
log(k, v)
return outputs_np ############################################################
# data formatting
############################################################ def compose_image_meta(image_id, original_image_shape, image_shape,
window, scale, active_class_ids):
"""takes attributes of an image and puts them in one 1d array. image_id: an int id of the image. useful for debugging.
original_image_shape: [h, w, c] before resizing or padding.
image_shape: [h, w, c] after resizing and padding
window: (y1, x1, y2, x2) in pixels. the area of the image where the real
image is (excluding the padding)
scale: the scaling factor applied to the original image (float32)
active_class_ids: list of class_ids available in the dataset from which
the image came. useful if training on images from multiple datasets
where not all classes are present in all datasets.
"""
meta = np.array(
[image_id] # size=1
list(original_image_shape) # size=3
list(image_shape) # size=3
list(window) # size=4 (y1, x1, y2, x2) in image cooredinates
[scale] # size=1
list(active_class_ids) # size=num_classes
)
return meta def parse_image_meta(meta):
"""parses an array that contains image attributes to its components.
see compose_image_meta() for more details. meta: [batch, meta length] where meta length depends on num_classes returns a dict of the parsed values.
"""
image_id = meta[:, 0]
original_image_shape = meta[:, 1:4]
image_shape = meta[:, 4:7]
window = meta[:, 7:11] # (y1, x1, y2, x2) window of image in in pixels
scale = meta[:, 11]
active_class_ids = meta[:, 12:]
return {
"image_id": image_id.astype(np.int32),
"original_image_shape": original_image_shape.astype(np.int32),
"image_shape": image_shape.astype(np.int32),
"window": window.astype(np.int32),
"scale": scale.astype(np.float32),
"active_class_ids": active_class_ids.astype(np.int32),
} def parse_image_meta_graph(meta):
"""parses a tensor that contains image attributes to its components.
see compose_image_meta() for more details. meta: [batch, meta length] where meta length depends on num_classes returns a dict of the parsed tensors.
"""
image_id = meta[:, 0]
original_image_shape = meta[:, 1:4]
image_shape = meta[:, 4:7]
window = meta[:, 7:11] # (y1, x1, y2, x2) window of image in in pixels
scale = meta[:, 11]
active_class_ids = meta[:, 12:]
return {
"image_id": image_id,
"original_image_shape": original_image_shape,
"image_shape": image_shape,
"window": window,
"scale": scale,
"active_class_ids": active_class_ids,
} def mold_image(images, config):
"""expects an rgb image (or array of images) and subtracts
the mean pixel and converts it to float. expects image
colors in rgb order.
"""
return images.astype(np.float32) - config.mean_pixel def unmold_image(normalized_images, config):
"""takes a image normalized with mold() and returns the original."""
return (normalized_images config.mean_pixel).astype(np.uint8) ############################################################
# miscellenous graph functions
############################################################ def trim_zeros_graph(boxes, name='trim_zeros'):
"""often boxes are represented with matrices of shape [n, 4] and
are padded with zeros. this removes zero boxes. boxes: [n, 4] matrix of boxes.
non_zeros: [n] a 1d boolean mask identifying the rows to keep
"""
non_zeros = tf.cast(tf.reduce_sum(tf.abs(boxes), axis=1), tf.bool)
boxes = tf.boolean_mask(boxes, non_zeros, name=name)
return boxes, non_zeros def batch_pack_graph(x, counts, num_rows):
"""picks different number of values from each row
in x depending on the values in counts.
"""
outputs = []
for i in range(num_rows):
outputs.append(x[i, :counts[i]])
return tf.concat(outputs, axis=0) def norm_boxes_graph(boxes, shape):
"""converts boxes from pixel coordinates to normalized coordinates.
boxes: [..., (y1, x1, y2, x2)] in pixel coordinates
shape: [..., (height, width)] in pixels note: in pixel coordinates (y2, x2) is outside the box. but in normalized
coordinates it's inside the box. returns:
[..., (y1, x1, y2, x2)] in normalized coordinates
"""
h, w = tf.split(tf.cast(shape, tf.float32), 2)
scale = tf.concat([h, w, h, w], axis=-1) - tf.constant(1.0)
shift = tf.constant([0., 0., 1., 1.])
return tf.divide(boxes - shift, scale) def denorm_boxes_graph(boxes, shape):
"""converts boxes from normalized coordinates to pixel coordinates.
boxes: [..., (y1, x1, y2, x2)] in normalized coordinates
shape: [..., (height, width)] in pixels note: in pixel coordinates (y2, x2) is outside the box. but in normalized
coordinates it's inside the box. returns:
[..., (y1, x1, y2, x2)] in pixel coordinates
"""
h, w = tf.split(tf.cast(shape, tf.float32), 2)
scale = tf.concat([h, w, h, w], axis=-1) - tf.constant(1.0)
shift = tf.constant([0., 0., 1., 1.])
return tf.cast(tf.round(tf.multiply(boxes, scale) shift), tf.int32)
model.py
复制上述代码，替换 /path/to/mask_rcnn-master/mask_rcnn-master/mrcnn/model.py 文件中的全部内容，请注意保留原 model.py 文件！
在新的 model.py 文件中，第2485行找到 detect() 函数，在函数注释后添加如下代码，提示函数调用：
print('function detect() is running...')
在第2531行 for 循环结束后，添加如下代码，每个 region 的 feature map：
print(results)
print(len(results[0]['features']))
在 anaconda prompt 中，重新加载 jupyter notebook，运行 demo.ipynb 文件，运行结果如下：
凯发真人娱乐的版权声明：本文为博主原创文章，欢迎转载，转载请注明作者及原文出处！
![[opencv实战]13 opencv中使用mask r-cnn进行对象检测和实例分割](/file/thumb/4.jpg/280-180.jpg)