DynaSLAM/src/python/

""" Mask R-CNN The main Mask R-CNN model implemenetation. Copyright (c) 2017 Matterport, Inc. Licensed under the MIT License (see LICENSE for details) Written by Waleed Abdulla """ import os import sys import glob import random import math import datetime import itertools import json import re import logging from collections import OrderedDict import numpy as np import scipy.misc import tensorflow as tf import keras import keras.backend as K import keras.layers as KL import keras.initializers as KI import keras.engine as KE import keras.models as KM 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} min: {:10.5f} max: {:10.5f}".format( str(array.shape), array.min() if array.size else "", array.max() if array.size else "")) # print(text) class BatchNorm(KL.BatchNormalization): """Batch Normalization class. Subclasses the Keras BN class and hardcodes training=False so the BN layer doesn't update during training. Batch normalization has a negative effect on training if batches are small so we disable it here. """ def call(self, inputs, training=None): return super(self.__class__, self).call(inputs, training=False) ############################################################ # 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): """The identity_block is the block that has no conv layer at shortcut # Arguments input_tensor: input tensor kernel_size: defualt 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 """ 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(axis=3, name=bn_name_base + '2a')(x) 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(axis=3, name=bn_name_base + '2b')(x) x = KL.Activation('relu')(x) x = KL.Conv2D(nb_filter3, (1, 1), name=conv_name_base + '2c', use_bias=use_bias)(x) x = BatchNorm(axis=3, name=bn_name_base + '2c')(x) 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): """conv_block is the block that has a conv layer at shortcut # Arguments input_tensor: input tensor kernel_size: defualt 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 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(axis=3, name=bn_name_base + '2a')(x) 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(axis=3, name=bn_name_base + '2b')(x) x = KL.Activation('relu')(x) x = KL.Conv2D(nb_filter3, (1, 1), name=conv_name_base + '2c', use_bias=use_bias)(x) x = BatchNorm(axis=3, name=bn_name_base + '2c')(x) shortcut = KL.Conv2D(nb_filter3, (1, 1), strides=strides, name=conv_name_base + '1', use_bias=use_bias)(input_tensor) shortcut = BatchNorm(axis=3, name=bn_name_base + '1')(shortcut) 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): 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(axis=3, name='bn_conv1')(x) 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)) x = identity_block(x, 3, [64, 64, 256], stage=2, block='b') C2 = x = identity_block(x, 3, [64, 64, 256], stage=2, block='c') # Stage 3 x = conv_block(x, 3, [128, 128, 512], stage=3, block='a') x = identity_block(x, 3, [128, 128, 512], stage=3, block='b') x = identity_block(x, 3, [128, 128, 512], stage=3, block='c') C3 = x = identity_block(x, 3, [128, 128, 512], stage=3, block='d') # Stage 4 x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a') 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)) C4 = x # Stage 5 if stage5: x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a') x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b') C5 = x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c') 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, 4] where each row is y1, x1, y2, x2 deltas: [N, 4] where each row is [dy, dx, log(dh), log(dw)] """ # 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, 4] each row is y1, x1, y2, x2 window: [4] in the form y1, x1, y2, x2 """ # Split corners 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.maximu