Debug changes

retinanet/model.py

@@ -259,8 +259,6 @@ def forward(self, inputs):
             transformed_anchors = self.regressBoxes(anchors, regression)
             transformed_anchors = self.clipBoxes(transformed_anchors, img_batch)
 
-            finalResult = [[], [], []]
-
             finalScores = torch.Tensor([])
             finalAnchorBoxesIndexes = torch.Tensor([]).long()
             finalAnchorBoxesCoordinates = torch.Tensor([])
@@ -282,10 +280,6 @@ def forward(self, inputs):
                 anchorBoxes = anchorBoxes[scores_over_thresh]
                 anchors_nms_idx = nms(anchorBoxes, scores, 0.5)
 
-                finalResult[0].extend(scores[anchors_nms_idx])
-                finalResult[1].extend(torch.tensor([i] * anchors_nms_idx.shape[0]))
-                finalResult[2].extend(anchorBoxes[anchors_nms_idx])
-
                 finalScores = torch.cat((finalScores, scores[anchors_nms_idx]))
                 finalAnchorBoxesIndexesValue = torch.tensor([i] * anchors_nms_idx.shape[0])
                 if torch.cuda.is_available():

visualize_single_image.py

@@ -52,6 +52,8 @@ def detect_image(image_path, model_path, class_list):
     for img_name in os.listdir(image_path):
 
         image = cv2.imread(os.path.join(image_path, img_name))
+        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+
         if image is None:
             continue
         image_orig = image.copy()
@@ -96,7 +98,7 @@ def detect_image(image_path, model_path, class_list):
 
             st = time.time()
             print(image.shape, image_orig.shape, scale)
-            scores, classification, transformed_anchors = model(image.cuda().float())
+            scores, classification, transformed_anchors = model(image.float())
             print('Elapsed time: {}'.format(time.time() - st))
             idxs = np.where(scores.cpu() > 0.5)
 
@@ -109,7 +111,7 @@ def detect_image(image_path, model_path, class_list):
                 y2 = int(bbox[3] / scale)
                 label_name = labels[int(classification[idxs[0][j]])]
                 print(bbox, classification.shape)
-                score = scores[j]
+                score = scores[idxs[0][j]]
                 caption = '{} {:.3f}'.format(label_name, score)
                 # draw_caption(img, (x1, y1, x2, y2), label_name)
                 draw_caption(image_orig, (x1, y1, x2, y2), caption)