add rpn_target_assign api test (#13013)

* Add unit test for rpn_target_assign API.

Author: jerrywgz

paddle/fluid/API.spec

@@ -301,7 +301,7 @@ paddle.fluid.layers.target_assign ArgSpec(args=['input', 'matched_indices', 'neg
 paddle.fluid.layers.detection_output ArgSpec(args=['loc', 'scores', 'prior_box', 'prior_box_var', 'background_label', 'nms_threshold', 'nms_top_k', 'keep_top_k', 'score_threshold', 'nms_eta'], varargs=None, keywords=None, defaults=(0, 0.3, 400, 200, 0.01, 1.0))
 paddle.fluid.layers.ssd_loss ArgSpec(args=['location', 'confidence', 'gt_box', 'gt_label', 'prior_box', 'prior_box_var', 'background_label', 'overlap_threshold', 'neg_pos_ratio', 'neg_overlap', 'loc_loss_weight', 'conf_loss_weight', 'match_type', 'mining_type', 'normalize', 'sample_size'], varargs=None, keywords=None, defaults=(None, 0, 0.5, 3.0, 0.5, 1.0, 1.0, 'per_prediction', 'max_negative', True, None))
 paddle.fluid.layers.detection_map ArgSpec(args=['detect_res', 'label', 'class_num', 'background_label', 'overlap_threshold', 'evaluate_difficult', 'has_state', 'input_states', 'out_states', 'ap_version'], varargs=None, keywords=None, defaults=(0, 0.3, True, None, None, None, 'integral'))
-paddle.fluid.layers.rpn_target_assign ArgSpec(args=['loc', 'scores', 'anchor_box', 'gt_box', 'rpn_batch_size_per_im', 'fg_fraction', 'rpn_positive_overlap', 'rpn_negative_overlap'], varargs=None, keywords=None, defaults=(256, 0.25, 0.7, 0.3))
+paddle.fluid.layers.rpn_target_assign ArgSpec(args=['loc', 'scores', 'anchor_box', 'anchor_var', 'gt_box', 'rpn_batch_size_per_im', 'fg_fraction', 'rpn_positive_overlap', 'rpn_negative_overlap'], varargs=None, keywords=None, defaults=(256, 0.25, 0.7, 0.3))
 paddle.fluid.layers.anchor_generator ArgSpec(args=['input', 'anchor_sizes', 'aspect_ratios', 'variance', 'stride', 'offset', 'name'], varargs=None, keywords=None, defaults=(None, None, [0.1, 0.1, 0.2, 0.2], None, 0.5, None))
 paddle.fluid.layers.generate_proposal_labels ArgSpec(args=['rpn_rois', 'gt_classes', 'gt_boxes', 'im_scales', 'batch_size_per_im', 'fg_fraction', 'fg_thresh', 'bg_thresh_hi', 'bg_thresh_lo', 'bbox_reg_weights', 'class_nums'], varargs=None, keywords=None, defaults=(256, 0.25, 0.25, 0.5, 0.0, [0.1, 0.1, 0.2, 0.2], None))
 paddle.fluid.layers.generate_proposals ArgSpec(args=['scores', 'bbox_deltas', 'im_info', 'anchors', 'variances', 'pre_nms_top_n', 'post_nms_top_n', 'nms_thresh', 'min_size', 'eta', 'name'], varargs=None, keywords=None, defaults=(6000, 1000, 0.5, 0.1, 1.0, None))

python/paddle/fluid/layers/detection.py

@@ -58,6 +58,7 @@
 def rpn_target_assign(loc,
                       scores,
                       anchor_box,
+                      anchor_var,
                       gt_box,
                       rpn_batch_size_per_im=256,
                       fg_fraction=0.25,
@@ -96,6 +97,8 @@ class number, M is number of bounding boxes. For each category
             if the input is image feature map, they are close to the origin
             of the coordinate system. [xmax, ymax] is the right bottom
             coordinate of the anchor box.
+        anchor_var(Variable): A 2-D Tensor with shape [M,4] holds expanded 
+            variances of anchors.
         gt_box (Variable): The ground-truth boudding boxes (bboxes) are a 2D
             LoDTensor with shape [Ng, 4], Ng is the total number of ground-truth
             bboxes of mini-batch input.
@@ -145,30 +148,29 @@ class number, M is number of bounding boxes. For each category
     # 1. Compute the regression target bboxes
     target_bbox = box_coder(
         prior_box=anchor_box,
+        prior_box_var=anchor_var,
         target_box=gt_box,
         code_type='encode_center_size',
         box_normalized=False)
-
     # 2. Compute overlaps between the prior boxes and the gt boxes overlaps
     iou = iou_similarity(x=gt_box, y=anchor_box)
-
     # 3. Assign target label to anchors
     loc_index = helper.create_tmp_variable(dtype=anchor_box.dtype)
     score_index = helper.create_tmp_variable(dtype=anchor_box.dtype)
     target_label = helper.create_tmp_variable(dtype=anchor_box.dtype)
     helper.append_op(
         type="rpn_target_assign",
-        inputs={'Overlap': iou, },
+        inputs={'DistMat': iou},
         outputs={
             'LocationIndex': loc_index,
             'ScoreIndex': score_index,
-            'TargetLabel': target_label,
+            'TargetLabel': target_label
         },
         attrs={
             'rpn_batch_size_per_im': rpn_batch_size_per_im,
             'rpn_positive_overlap': rpn_positive_overlap,
             'rpn_negative_overlap': rpn_negative_overlap,
-            'fg_fraction': fg_fraction,
+            'fg_fraction': fg_fraction
         })
 
     # 4. Reshape and gather the target entry
@@ -181,7 +183,7 @@ class number, M is number of bounding boxes. For each category
     predicted_location = nn.gather(loc, loc_index)
     target_label = nn.gather(target_label, score_index)
     target_bbox = nn.gather(target_bbox, loc_index)
-    return predicted_scores, predicted_loc, target_label, target_bbox
+    return predicted_scores, predicted_location, target_label, target_bbox
 
 
 def detection_output(loc,

python/paddle/fluid/tests/test_detection.py

@@ -250,6 +250,59 @@ def test_detection_map(self):
         print(str(program))
 
 
+class TestRpnTargetAssign(unittest.TestCase):
+    def test_rpn_target_assign(self):
+        program = Program()
+        with program_guard(program):
+            loc_shape = [10, 50, 4]
+            score_shape = [10, 50, 2]
+            anchor_shape = [50, 4]
+
+            loc = layers.data(
+                name='loc',
+                shape=loc_shape,
+                append_batch_size=False,
+                dtype='float32')
+            scores = layers.data(
+                name='scores',
+                shape=score_shape,
+                append_batch_size=False,
+                dtype='float32')
+            anchor_box = layers.data(
+                name='anchor_box',
+                shape=anchor_shape,
+                append_batch_size=False,
+                dtype='float32')
+            anchor_var = layers.data(
+                name='anchor_var',
+                shape=anchor_shape,
+                append_batch_size=False,
+                dtype='float32')
+            gt_box = layers.data(
+                name='gt_box', shape=[4], lod_level=1, dtype='float32')
+
+            predicted_scores, predicted_location, target_label, target_bbox = layers.rpn_target_assign(
+                loc=loc,
+                scores=scores,
+                anchor_box=anchor_box,
+                anchor_var=anchor_var,
+                gt_box=gt_box,
+                rpn_batch_size_per_im=256,
+                fg_fraction=0.25,
+                rpn_positive_overlap=0.7,
+                rpn_negative_overlap=0.3)
+
+            self.assertIsNotNone(predicted_scores)
+            self.assertIsNotNone(predicted_location)
+            self.assertIsNotNone(target_label)
+            self.assertIsNotNone(target_bbox)
+            assert predicted_scores.shape[1] == 2
+            assert predicted_location.shape[1] == 4
+            assert predicted_location.shape[1] == target_bbox.shape[1]
+
+        print(str(program))
+
+
 class TestGenerateProposals(unittest.TestCase):
     def test_generate_proposals(self):
         data_shape = [20, 64, 64]