生活随笔
收集整理的這篇文章主要介紹了
faster rcnn源码解读（六）之minibatch
小編覺得挺不錯的,現在分享給大家,幫大家做個參考.
轉載自：faster rcnn源碼解讀（六）之minibatch - 野孩子的專欄 - 博客頻道 - CSDN.NET
http://blog.csdn.net/u010668907/article/details/51945917
faster rcnn用python版本的https://github.com/rbgirshick/py-faster-rcnn
minibatch源碼：https://github.com/rbgirshick/py-faster-rcnn/blob/master/lib/roi_data_layer/minibatch.py
源碼：
[python]?view plaincopy print?
?? ?? ?? ?? ?? ?? ?? ?? ?? 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):?? ?????? ????num_images?=?len(roidb)?? ?????? ????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)?? ????rois_per_image?=?cfg.TRAIN.BATCH_SIZE?/?num_images?? ????fg_rois_per_image?=?np.round(cfg.TRAIN.FG_FRACTION?*?rois_per_image)?? ?? ?????? ????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_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:??? ?????????? ????????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)?? ?????????? ????????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)?? ?? ?????????????? ????????????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))?? ?? ?????????????? ????????????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))?? ?????????????? ?? ?????????? ?????????? ?? ????????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):?? ????? ? ?? ?????? ????labels?=?roidb['max_classes']?? ????overlaps?=?roidb['max_overlaps']?? ????rois?=?roidb['boxes']?? ?? ?????? ????fg_inds?=?np.where(overlaps?>=?cfg.TRAIN.FG_THRESH)[0]?? ?????? ?????? ????fg_rois_per_this_image?=?np.minimum(fg_rois_per_image,?fg_inds.size)?? ?????? ????if?fg_inds.size?>?0:?? ????????fg_inds?=?npr.choice(?? ????????????????fg_inds,?size=fg_rois_per_this_image,?replace=False)?? ?? ?????? ????bg_inds?=?np.where((overlaps?<?cfg.TRAIN.BG_THRESH_HI)?&?? ???????????????????????(overlaps?>=?cfg.TRAIN.BG_THRESH_LO))[0]?? ?????? ?????? ????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)?? ?????? ????if?bg_inds.size?>?0:?? ????????bg_inds?=?npr.choice(?? ????????????????bg_inds,?size=bg_rois_per_this_image,?replace=False)?? ?? ?????? ????keep_inds?=?np.append(fg_inds,?bg_inds)?? ?????? ????labels?=?labels[keep_inds]?? ?????? ????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):?? ????? ? ?? ????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；用于將圖片平均后縮放。??
[python]?view plaincopy print?
?????????? ????????im_scales.append(im_scale)?? ????????processed_ims.append(im)?? ?? ?????? ????blob?=?im_list_to_blob(processed_ims)?? ?? ????return?blob,?im_scales?? ?? def?_project_im_rois(im_rois,?im_scale_factor):?? ?????? ????rois?=?im_rois?*?im_scale_factor?? ????return?rois?? ?? def?_get_bbox_regression_labels(bbox_target_data,?num_classes):?? ????? ? ? ? ? ? ? ? ? ? ?? ????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):?? ?????? ????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,現在進入minibatch組建真正的blob)get_minibatch
4.1 cfg.TRAIN.SCALES： 圖片被縮放的target_size列表
??4.2 random_scale_inds：列表的隨機索引組成的numpy，大小是roidb的長度
??4.3 cfg.PIXEL_MEANS： 原始圖片會集體減去該值達到mean
??4.4 im_scales： 每張圖片的縮放率
????縮放率的求法：?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；用于將圖片平均后縮放。
?4.6 im_list_to_blob(ims):?將以list形式存放的圖片數據處理成(batch elem, channel, height, width)的im_blob形式，height，width用的是此次計算所有圖片的最大值
4.7 blob是一個字典：data，一個batch的處理過的所有圖片數據，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的類別。
??????????????????????????????box=原box*im_scales
??blob與name_to_top對應，方便把blob數據放進top
！！！minibatch.py中34行的代碼表明，batchsize即cfg.TRAIN.IMS_PER_BATCH只能是1
總結
以上是生活随笔為你收集整理的faster rcnn源码解读（六）之minibatch的全部內容，希望文章能夠幫你解決所遇到的問題。
如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。
