faster rcnn源码解读(六)之minibatch
2016-07-18 21:57
561 查看
faster rcnn用python版本的https://github.com/rbgirshick/py-faster-rcnn
minibatch源码:https://github.com/rbgirshick/py-faster-rcnn/blob/master/lib/roi_data_layer/minibatch.py
源码:
# --------------------------------------------------------
# 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
def get_minibatch(roidb, num_classes):
"""Given a roidb, construct a minibatch sampled from it."""
num_images = len(roidb)
# Sample random scales to use for each image in this batch
random_scale_inds = npr.randint(0, high=len(cfg.TRAIN.SCALES),
size=num_images)#随机索引组成的numpy,大小是roidb的长度
assert(cfg.TRAIN.BATCH_SIZE % num_images == 0), \
'num_images ({}) must divide BATCH_SIZE ({})'. \
format(num_images, cfg.TRAIN.BATCH_SIZE)
rois_per_image = cfg.TRAIN.BATCH_SIZE / num_images
fg_rois_per_image = np.round(cfg.TRAIN.FG_FRACTION * rois_per_image)
# Get the input image blob, formatted for caffe
im_blob, im_scales = _get_image_blob(roidb, random_scale_inds)
blobs = {'data': im_blob}
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)
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
blobs['im_info'] = np.array(
[[im_blob.shape[2], im_blob.shape[3], 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 = 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.
"""
num_images = len(roidb)
processed_ims = []
im_scales = []
for i in xrange(num_images):
im = cv2.imread(roidb[i]['image'])
if roidb[i]['flipped']:
im = im[:, ::-1, :]
target_size = cfg.TRAIN.SCALES[scale_inds[i]]
im, im_scale = prep_im_for_blob(im, cfg.PIXEL_MEANS, target_size,
cfg.TRAIN.MAX_SIZE)prep_im_for_blob: util的blob.py中;用于将图片平均后缩放。#im_scales: 每张图片的缩放率
solver.step(1)-》reshape-》forward-》_get_next_minbatch-》_get_next_minbatch_inds-》(前面在layers里,现在进入minibatch组建真正的blob)get_minibatch
4.1 cfg.TRAIN.SCALES: 图片被缩放的target_size列表
4.2 random_scale_inds:列表的随机索引组成的numpy,大小是roidb的长度
4.3 cfg.PIXEL_MEANS: 原始图片会集体减去该值达到mean
4.4 im_scales: 每张图片的缩放率
缩放率的求法: im_scales = target_size/min(width, height);
if im_scales*max(width, height) > cfg.TRAIN.MAX_SIZE
im_scales = cfg.TRAIN.MAX_SIZE * max(width, height)
4.5 prep_im_for_blob: util的blob.py中;用于将图片平均后缩放。
4.6 im_list_to_blob(ims): 将以list形式存放的图片数据处理成(batch elem, channel, height, width)的im_blob形式,height,width用的是此次计算所有图片的最大值
4.7 blob是一个字典:data,一个batch的处理过的所有图片数据,即上面的im_blob;
im_info, [im_blob.shape[2], im_blob.shape[3], im_scales[0]]
gt_boxes, 是前四列是box的值,第五列是box的类别。
box=原box*im_scales
blob与name_to_top对应,方便把blob数据放进top
!!!minibatch.py中34行的代码表明,batchsize即cfg.TRAIN.IMS_PER_BATCH只能是1
minibatch源码:https://github.com/rbgirshick/py-faster-rcnn/blob/master/lib/roi_data_layer/minibatch.py
源码:
# --------------------------------------------------------
# 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
def get_minibatch(roidb, num_classes):
"""Given a roidb, construct a minibatch sampled from it."""
num_images = len(roidb)
# Sample random scales to use for each image in this batch
random_scale_inds = npr.randint(0, high=len(cfg.TRAIN.SCALES),
size=num_images)#随机索引组成的numpy,大小是roidb的长度
assert(cfg.TRAIN.BATCH_SIZE % num_images == 0), \
'num_images ({}) must divide BATCH_SIZE ({})'. \
format(num_images, cfg.TRAIN.BATCH_SIZE)
rois_per_image = cfg.TRAIN.BATCH_SIZE / num_images
fg_rois_per_image = np.round(cfg.TRAIN.FG_FRACTION * rois_per_image)
# Get the input image blob, formatted for caffe
im_blob, im_scales = _get_image_blob(roidb, random_scale_inds)
blobs = {'data': im_blob}
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)
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
blobs['im_info'] = np.array(
[[im_blob.shape[2], im_blob.shape[3], 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 = 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.
"""
num_images = len(roidb)
processed_ims = []
im_scales = []
for i in xrange(num_images):
im = cv2.imread(roidb[i]['image'])
if roidb[i]['flipped']:
im = im[:, ::-1, :]
target_size = cfg.TRAIN.SCALES[scale_inds[i]]
im, im_scale = prep_im_for_blob(im, cfg.PIXEL_MEANS, target_size,
cfg.TRAIN.MAX_SIZE)prep_im_for_blob: util的blob.py中;用于将图片平均后缩放。#im_scales: 每张图片的缩放率
# cfg.PIXEL_MEANS: 原始图片会集体减去该值达到mean im_scales.append(im_scale) processed_ims.append(im) # Create a blob to hold the input images blob = im_list_to_blob(processed_ims)#将以list形式存放的图片数据处理成(batch elem, channel, height, width)的im_blob形式,height,width用的是此次计算所有图片的最大值 return blob, im_scales#blob是一个字典,与name_to_top对应,方便把blob数据放进top 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 = bbox_target_data[:, 0] 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()
solver.step(1)-》reshape-》forward-》_get_next_minbatch-》_get_next_minbatch_inds-》(前面在layers里,现在进入minibatch组建真正的blob)get_minibatch
4.1 cfg.TRAIN.SCALES: 图片被缩放的target_size列表
4.2 random_scale_inds:列表的随机索引组成的numpy,大小是roidb的长度
4.3 cfg.PIXEL_MEANS: 原始图片会集体减去该值达到mean
4.4 im_scales: 每张图片的缩放率
缩放率的求法: im_scales = target_size/min(width, height);
if im_scales*max(width, height) > cfg.TRAIN.MAX_SIZE
im_scales = cfg.TRAIN.MAX_SIZE * max(width, height)
4.5 prep_im_for_blob: util的blob.py中;用于将图片平均后缩放。
4.6 im_list_to_blob(ims): 将以list形式存放的图片数据处理成(batch elem, channel, height, width)的im_blob形式,height,width用的是此次计算所有图片的最大值
4.7 blob是一个字典:data,一个batch的处理过的所有图片数据,即上面的im_blob;
im_info, [im_blob.shape[2], im_blob.shape[3], im_scales[0]]
gt_boxes, 是前四列是box的值,第五列是box的类别。
box=原box*im_scales
blob与name_to_top对应,方便把blob数据放进top
!!!minibatch.py中34行的代码表明,batchsize即cfg.TRAIN.IMS_PER_BATCH只能是1
相关文章推荐
- 伪类&伪元素
- Python的多版本如何处理--请使用pyenv
- 实现string的构造函数,析构函数,拷贝构造函数
- js表单克隆
- HTML5地理位置Geolocation以及百度地图应用
- Linux bash shell中变量的设置和使用
- 22.协议
- 优秀开源前端框架
- HDU 1596 find the safest road
- MongoDB学习笔记(索引)
- 关于LCA(Tarjan+ST)
- 会话管理之Session
- 利用Eclipse集成开发环境进行ROS开发
- 【Arduino官方教程】数字处理示例(五):按键状态变化检测
- discuz 可以使用多种缓存
- Python之检查URL
- window python 操作mysql、redis
- 深入阅读gulp源码小结
- gdb core的使用
- java-----hashCode和equals的区别