diff --git a/mmdet3d/datasets/nuscenes_dataset.py b/mmdet3d/datasets/nuscenes_dataset.py
index 6811a2b4f7..a7d4b06375 100644
--- a/mmdet3d/datasets/nuscenes_dataset.py
+++ b/mmdet3d/datasets/nuscenes_dataset.py
@@ -98,6 +98,14 @@ class NuScenesDataset(Custom3DDataset):
         'vehicle.parked',
         'vehicle.stopped',
     ]
+    # https://github.com/nutonomy/nuscenes-devkit/blob/57889ff20678577025326cfc24e57424a829be0a/python-sdk/nuscenes/eval/detection/evaluate.py#L222 # noqa
+    ErrNameMapping = {
+        'trans_err': 'mATE',
+        'scale_err': 'mASE',
+        'orient_err': 'mAOE',
+        'vel_err': 'mAVE',
+        'attr_err': 'mAAE'
+    }
     CLASSES = ('car', 'truck', 'trailer', 'bus', 'construction_vehicle',
                'bicycle', 'motorcycle', 'pedestrian', 'traffic_cone',
                'barrier')
@@ -404,6 +412,10 @@ def _evaluate_single(self,
             for k, v in metrics['label_tp_errors'][name].items():
                 val = float('{:.4f}'.format(v))
                 detail['{}/{}_{}'.format(metric_prefix, name, k)] = val
+            for k, v in metrics['tp_errors'].items():
+                val = float('{:.4f}'.format(v))
+                detail['{}/{}'.format(metric_prefix,
+                                      self.ErrNameMapping[k])] = val
 
         detail['{}/NDS'.format(metric_prefix)] = metrics['nd_score']
         detail['{}/mAP'.format(metric_prefix)] = metrics['mean_ap']
diff --git a/mmdet3d/datasets/nuscenes_mono_dataset.py b/mmdet3d/datasets/nuscenes_mono_dataset.py
index 32431e2915..37d1aff037 100644
--- a/mmdet3d/datasets/nuscenes_mono_dataset.py
+++ b/mmdet3d/datasets/nuscenes_mono_dataset.py
@@ -58,6 +58,14 @@ class NuScenesMonoDataset(CocoDataset):
         'barrier': '',
         'traffic_cone': '',
     }
+    # https://github.com/nutonomy/nuscenes-devkit/blob/57889ff20678577025326cfc24e57424a829be0a/python-sdk/nuscenes/eval/detection/evaluate.py#L222 # noqa
+    ErrNameMapping = {
+        'trans_err': 'mATE',
+        'scale_err': 'mASE',
+        'orient_err': 'mAOE',
+        'vel_err': 'mAVE',
+        'attr_err': 'mAAE'
+    }
 
     def __init__(self,
                  data_root,
@@ -423,6 +431,10 @@ def _evaluate_single(self,
             for k, v in metrics['label_tp_errors'][name].items():
                 val = float('{:.4f}'.format(v))
                 detail['{}/{}_{}'.format(metric_prefix, name, k)] = val
+            for k, v in metrics['tp_errors'].items():
+                val = float('{:.4f}'.format(v))
+                detail['{}/{}'.format(metric_prefix,
+                                      self.ErrNameMapping[k])] = val
 
         detail['{}/NDS'.format(metric_prefix)] = metrics['nd_score']
         detail['{}/mAP'.format(metric_prefix)] = metrics['mean_ap']