用fast rcnn训练自己的数据集时遇到的问题索引问题

 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)
    
     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)  修改为  fg_rois_per_image = int(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)
    
  
    
     # 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_loss_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_loss \
    
         = _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_loss_blob = np.vstack((bbox_loss_blob, bbox_loss))
    
     # all_overlaps = np.hstack((all_overlaps, overlaps))
    
  
    
     # For debug visualizations
    
     # _vis_minibatch(im_blob, rois_blob, labels_blob, all_overlaps)
    
  
    
     blobs = {'data': im_blob,
    
          'rois': rois_blob,
    
          'labels': labels_blob}
    
  
    
     if cfg.TRAIN.BBOX_REG:
    
     blobs['bbox_targets'] = bbox_targets_blob
    
     blobs['bbox_loss_weights'] = bbox_loss_blob
    
  
    
     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_loss_weights = \
    
         _get_bbox_regression_labels(roidb['bbox_targets'][keep_inds, :],
    
                                     num_classes)
    
  
    
     return labels, overlaps, rois, bbox_targets, bbox_loss_weights
    
    
    
    

二是，minibatch.py中，_get_bbox_regression_labels(bbox_target_data, num_class)函数中，bbox_targets[ind, start:end] = bbox_target_data[ind, 1:]一直报错。原因也是索引不是整型。通过输出变量，发现 start 不是整型。找到其定义的地方： start = 4 * cls，其结果不是整型。再往前看，cls = clss[ind]不是整型，因此在定义start的时候，定义其为整型。

 """Bounding-box regression targets are stored in a compact form in the

 roidb.

 by the network (i.e. only one class has non-zero targets). The loss weights

 are similarly expanded.

 bbox_target_data (ndarray): N x 4K blob of regression targets

 bbox_loss_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_loss_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    修改为   start = int( 4 * cls )

 end = start + 4

 bbox_targets[ind, start:end] = bbox_target_data[ind, 1:]

 bbox_loss_weights[ind, start:end] = [1., 1., 1., 1.]

 return bbox_targets, bbox_loss_weights

AI写代码AI写代码