fixed int conversion issue in faster rcnn

experiments/cfgs/faster_rcnn_end2end.yml

@@ -8,4 +8,4 @@ TRAIN:
   PROPOSAL_METHOD: gt
   BG_THRESH_LO: 0.0
 TEST:
-  HAS_RPN: True
+  HAS_RPN: True

lib/roi_data_layer/layer.py

@@ -20,7 +20,7 @@
 class RoIDataLayer(caffe.Layer):
     """Fast R-CNN data layer used for training."""
 
-    def _shuffle_roidb_inds(self, gpu_id):
+    def _shuffle_roidb_inds(self, gpu_id=0):
         self.gpu_id = gpu_id
         """Randomly permute the training roidb."""
         if cfg.TRAIN.ASPECT_GROUPING:
@@ -64,7 +64,7 @@ def _get_next_minibatch(self):
             minibatch_db = [self._roidb[i] for i in db_inds]
             return get_minibatch(minibatch_db, self._num_classes)
 
-    def set_roidb(self, roidb, gpu_id):
+    def set_roidb(self, roidb, gpu_id=0):
         """Set the roidb to be used by this layer during training."""
         self._roidb = roidb
         self._shuffle_roidb_inds(gpu_id)
@@ -125,6 +125,7 @@ def setup(self, bottom, top):
                 # bbox_targets blob: R bounding-box regression targets with 4
                 # targets per class
                 num_reg_class = 2 if cfg.TRAIN.AGNOSTIC else self._num_classes
+
                 top[idx].reshape(1, num_reg_class * 4, 1, 1)
                 self._name_to_top_map['bbox_targets'] = idx
                 idx += 1
@@ -167,7 +168,7 @@ def reshape(self, bottom, top):
 
 class BlobFetcher(Process):
     """Experimental class for prefetching blobs in a separate process."""
-    def __init__(self, queue, roidb, num_classes, gpu_id):
+    def __init__(self, queue, roidb, num_classes, gpu_id=0):
         super(BlobFetcher, self).__init__()
         self._queue = queue
         self._roidb = roidb

lib/rpn/proposal_target_layer.py

@@ -12,7 +12,6 @@
 from fast_rcnn.config import cfg
 from fast_rcnn.bbox_transform import bbox_transform
 from utils.cython_bbox import bbox_overlaps
-
 DEBUG = False
 
 class ProposalTargetLayer(caffe.Layer):
@@ -141,8 +140,8 @@ def _get_bbox_regression_labels(bbox_target_data, num_classes):
     else:
         for ind in inds:
             cls = clss[ind]
-            start = 4 * cls
-            end = start + 4
+            start = int(4 * cls)
+            end = int(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
@@ -179,7 +178,7 @@ def _sample_rois(all_rois, gt_boxes, fg_rois_per_image, rois_per_image, num_clas
     fg_inds = np.where(max_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 = min(fg_rois_per_image, fg_inds.size)
+    fg_rois_per_this_image = int(min(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)
@@ -190,7 +189,7 @@ def _sample_rois(all_rois, gt_boxes, fg_rois_per_image, rois_per_image, num_clas
     # 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 = min(bg_rois_per_this_image, bg_inds.size)
+    bg_rois_per_this_image = int(min(bg_rois_per_this_image, bg_inds.size))
     # Sample background regions without replacement
     if bg_inds.size > 0:
         bg_inds = npr.choice(bg_inds, size=bg_rois_per_this_image, replace=False)