np.pad (open-mmlab#1116)

mmpose/core/evaluation/top_down_eval.py

@@ -366,34 +366,10 @@ def post_dark_udp(coords, batch_heatmaps, kernel=3):
             cv2.GaussianBlur(heatmap, (kernel, kernel), 0, heatmap)
     np.clip(batch_heatmaps, 0.001, 50, batch_heatmaps)
     np.log(batch_heatmaps, batch_heatmaps)
-    batch_heatmaps = np.transpose(batch_heatmaps,
-                                  (2, 3, 0, 1)).reshape(H, W, -1)
-
-    # cv2.copyMakeBorder will report an error when input dimension exceeds 512
-    batch_heatmaps_channel = batch_heatmaps.shape[2]
-    if batch_heatmaps_channel > 512:
-        total_group_number = int(np.ceil(batch_heatmaps_channel / 512))
-        splited_batch_heatmaps = []
-        for group_idx in range(total_group_number):
-            splited_batch_heatmap = batch_heatmaps[
-                ..., group_idx *
-                512:min(batch_heatmaps_channel, (group_idx + 1) * 512)]
-            batch_heatmap_pad = cv2.copyMakeBorder(
-                splited_batch_heatmap,
-                1,
-                1,
-                1,
-                1,
-                borderType=cv2.BORDER_REFLECT)
-            splited_batch_heatmaps.append(batch_heatmap_pad)
-        batch_heatmaps_pad = np.concatenate(splited_batch_heatmaps, axis=2)
-    else:
-        batch_heatmaps_pad = cv2.copyMakeBorder(
-            batch_heatmaps, 1, 1, 1, 1, borderType=cv2.BORDER_REFLECT)
 
-    batch_heatmaps_pad = np.transpose(
-        batch_heatmaps_pad.reshape(H + 2, W + 2, B, K),
-        (2, 3, 0, 1)).flatten()
+    batch_heatmaps_pad = np.pad(
+        batch_heatmaps, ((0, 0), (0, 0), (1, 1), (1, 1)),
+        mode='edge').flatten()
 
     index = coords[..., 0] + 1 + (coords[..., 1] + 1) * (W + 2)
     index += (W + 2) * (H + 2) * np.arange(0, B * K).reshape(-1, K)