Faster-RCNN_TF代码解读15：roi_data_layer/minibatch.py

# --------------------------------------------------------
# Fast R-CNN
# Copyright (c) 2015 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Ross Girshick
# --------------------------------------------------------

"""Compute minibatch blobs for training a Fast R-CNN network."""

import numpy as np
import numpy.random as npr
import cv2
from fast_rcnn.config import cfg
from utils.blob import prep_im_for_blob, im_list_to_blob
#roidb为一个列表，列表中为该minibatch的信息，n个dict
def get_minibatch(roidb, num_classes):
"""Given a roidb, construct a minibatch sampled from it."""
#minibatch的图像个数
num_images = len(roidb)
# Sample random scales to use for each image in this batch
#cfg.TRAIN.SCALES为(0.25, 0.5, 1.0, 2.0, 3.0)
#建立一个最低为0,最高为5的（最低最高取不到）的（2,）大小的array
random_scale_inds = npr.randint(0, high=len(cfg.TRAIN.SCALES),
size=num_images)
assert(cfg.TRAIN.BATCH_SIZE % num_images == 0), \
'num_images ({}) must divide BATCH_SIZE ({})'. \
format(num_images, cfg.TRAIN.BATCH_SIZE)
#cfg.TRAIN.BATCH_SIZE为128 ，rois_per_image为64
rois_per_image = cfg.TRAIN.BATCH_SIZE / num_images
#cfg.TRAIN.FG_FRACTION为0.25,fg_rois_per_image为16
fg_rois_per_image = np.round(cfg.TRAIN.FG_FRACTION * rois_per_image)

# Get the input image blob, formatted for caffe
#得到用于训练的blob(array)（对原始图像减去均值，缩放，下边和右边区域可能为0）和图像缩放比例im_scales(list)
im_blob, im_scales = _get_image_blob(roidb, random_scale_inds)
#存入blobs字典
blobs = {'data': im_blob}
#False
if cfg.TRAIN.HAS_RPN:
assert len(im_scales) == 1, "Single batch only"
assert len(roidb) == 1, "Single batch only"
# gt boxes: (x1, y1, x2, y2, cls)
#组合 gt 信息
gt_inds = np.where(roidb[0]['gt_classes'] != 0)[0]
gt_boxes = np.empty((len(gt_inds), 5), dtype=np.float32)
gt_boxes[:, 0:4] = roidb[0]['boxes'][gt_inds, :] * im_scales[0]
gt_boxes[:, 4] = roidb[0]['gt_classes'][gt_inds]
blobs['gt_boxes'] = gt_boxes
#im_blob.shape[1]为高，im_blob.shape[2]为高,im_scales[0]为缩放比例
blobs['im_info'] = np.array(
[[im_blob.shape[1], im_blob.shape[2], im_scales[0]]],
dtype=np.float32)
else: # not using RPN
# Now, build the region of interest and label blobs
rois_blob = np.zeros((0, 5), dtype=np.float32)
labels_blob = np.zeros((0), dtype=np.float32)
bbox_targets_blob = np.zeros((0, 4 * num_classes), dtype=np.float32)
bbox_inside_blob = np.zeros(bbox_targets_blob.shape, dtype=np.float32)
# all_overlaps = []
for im_i in xrange(num_images):
labels, overlaps, im_rois, bbox_targets, bbox_inside_weights \
= _sample_rois(roidb[im_i], fg_rois_per_image, rois_per_image,
num_classes)

# Add to RoIs blob
rois = _project_im_rois(im_rois, im_scales[im_i])
batch_ind = im_i * np.ones((rois.shape[0], 1))
rois_blob_this_image = np.hstack((batch_ind, rois))
rois_blob = np.vstack((rois_blob, rois_blob_this_image))

# Add to labels, bbox targets, and bbox loss blobs
labels_blob = np.hstack((labels_blob, labels))
bbox_targets_blob = np.vstack((bbox_targets_blob, bbox_targets))
bbox_inside_blob = np.vstack((bbox_inside_blob, bbox_inside_weights))
# all_overlaps = np.hstack((all_overlaps, overlaps))

# For debug visualizations
# _vis_minibatch(im_blob, rois_blob, labels_blob, all_overlaps)

blobs['rois'] = rois_blob
blobs['labels'] = labels_blob

if cfg.TRAIN.BBOX_REG:
blobs['bbox_targets'] = bbox_targets_blob
blobs['bbox_inside_weights'] = bbox_inside_blob
blobs['bbox_outside_weights'] = \
np.array(bbox_inside_blob > 0).astype(np.float32)

return blobs

def _sample_rois(roidb, fg_rois_per_image, rois_per_image, num_classes):
"""Generate a random sample of RoIs comprising foreground and background
examples.
"""
# label = class RoI has max overlap with
labels = roidb['max_classes']
overlaps = roidb['max_overlaps']
rois = roidb['boxes']

# Select foreground RoIs as those with >= FG_THRESH overlap
fg_inds = np.where(overlaps >= cfg.TRAIN.FG_THRESH)[0]
# Guard against the case when an image has fewer than fg_rois_per_image
# foreground RoIs
fg_rois_per_this_image = int(np.minimum(fg_rois_per_image, fg_inds.size))
# Sample foreground regions without replacement
if fg_inds.size > 0:
fg_inds = npr.choice(
fg_inds, size=fg_rois_per_this_image, replace=False)

# Select background RoIs as those within [BG_THRESH_LO, BG_THRESH_HI)
bg_inds = np.where((overlaps < cfg.TRAIN.BG_THRESH_HI) &
(overlaps >= cfg.TRAIN.BG_THRESH_LO))[0]
# Compute number of background RoIs to take from this image (guarding
# against there being fewer than desired)
bg_rois_per_this_image = rois_per_image - fg_rois_per_this_image
bg_rois_per_this_image = np.minimum(bg_rois_per_this_image,
bg_inds.size)
# Sample foreground regions without replacement
if bg_inds.size > 0:
bg_inds = npr.choice(
bg_inds, size=bg_rois_per_this_image, replace=False)

# The indices that we're selecting (both fg and bg)
keep_inds = np.append(fg_inds, bg_inds)
# Select sampled values from various arrays:
labels = labels[keep_inds]
# Clamp labels for the background RoIs to 0
labels[fg_rois_per_this_image:] = 0
overlaps = overlaps[keep_inds]
rois = rois[keep_inds]

bbox_targets, bbox_inside_weights = _get_bbox_regression_labels(
roidb['bbox_targets'][keep_inds, :], num_classes)

return labels, overlaps, rois, bbox_targets, bbox_inside_weights

def _get_image_blob(roidb, scale_inds):
"""Builds an input blob from the images in the roidb at the specified
scales.
"""
#一次传的图片数，为每一个roidb为一个dict
num_images = len(roidb)
processed_ims = []
im_scales = []
for i in xrange(num_images):
im = cv2.imread(roidb[i]['image'])
if roidb[i]['flipped']:
#水平反转图片有'flipped'标签，但是'image'标签里存的是正常图片
im = im[:, ::-1, :]
# cfg.TRAIN.SCALES为(0.25, 0.5, 1.0, 2.0, 3.0)
#scale_inds为建立的一个最低为0,最高为5的（最低最高取不到）的（2,）大小的array
#即target_size为从(0.25, 0.5, 1.0, 2.0, 3.0)随机取出的一个值
target_size = cfg.TRAIN.SCALES[scale_inds[i]]
#cfg.PIXEL_MEANS 为 np.array([[[102.9801, 115.9465, 122.7717]]])
#cfg.TRAIN.MAX_SIZE为1000
#对图像进行缩放，返回缩放后的image以及缩放比例
im, im_scale = prep_im_for_blob(im, cfg.PIXEL_MEANS, target_size,
cfg.TRAIN.MAX_SIZE)
#以此存入im_scales和processed_ims列表
#其中im信息为ndarray，im_scale为int
im_scales.append(im_scale)
processed_ims.append(im)

# Create a blob to hold the input images
#processed_ims为缩放后的image信息
#返回blob，该blob存的是减去均值且缩放后的im信息，该blob可能右边与下边值为0
blob = im_list_to_blob(processed_ims)

return blob, im_scales

def _project_im_rois(im_rois, im_scale_factor):
"""Project image RoIs into the rescaled training image."""
rois = im_rois * im_scale_factor
return rois

def _get_bbox_regression_labels(bbox_target_data, num_classes):
"""Bounding-box regression targets are stored in a compact form in the
roidb.

This function expands those targets into the 4-of-4*K representation used
by the network (i.e. only one class has non-zero targets). The loss weights
are similarly expanded.

Returns:
bbox_target_data (ndarray): N x 4K blob of regression targets
bbox_inside_weights (ndarray): N x 4K blob of loss weights
"""
clss = np.array(bbox_target_data[:, 0], dtype=np.uint16, copy=True)
bbox_targets = np.zeros((clss.size, 4 * num_classes), dtype=np.float32)
bbox_inside_weights = np.zeros(bbox_targets.shape, dtype=np.float32)
inds = np.where(clss > 0)[0]
for ind in inds:
cls = clss[ind]
start = 4 * cls
end = start + 4
bbox_targets[ind, start:end] = bbox_target_data[ind, 1:]
bbox_inside_weights[ind, start:end] = cfg.TRAIN.BBOX_INSIDE_WEIGHTS
return bbox_targets, bbox_inside_weights

def _vis_minibatch(im_blob, rois_blob, labels_blob, overlaps):
"""Visualize a mini-batch for debugging."""
import matplotlib.pyplot as plt
for i in xrange(rois_blob.shape[0]):
rois = rois_blob[i, :]
im_ind = rois[0]
roi = rois[1:]
im = im_blob[im_ind, :, :, :].transpose((1, 2, 0)).copy()
im += cfg.PIXEL_MEANS
im = im[:, :, (2, 1, 0)]
im = im.astype(np.uint8)
cls = labels_blob[i]
plt.imshow(im)
print 'class: ', cls, ' overlap: ', overlaps[i]
plt.gca().add_patch(
plt.Rectangle((roi[0], roi[1]), roi[2] - roi[0],
roi[3] - roi[1], fill=False,
edgecolor='r', linewidth=3)
)
plt.show()