update

Author: zytx121

configs/_base_/models/retinanet_r50_fpn.py

@@ -71,15 +71,17 @@
     type='DetTTAModel',
     tta_cfg=dict(nms=dict(type='nms', iou_threshold=0.5), max_per_img=100))
 
+img_scales = [(1333, 800), (666, 400), (2000, 1200)]
 tta_pipeline = [
     dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
     dict(
         type='TestTimeAug',
-        transforms=[[dict(type='Resize', scale=(1333, 800), keep_ratio=True)],
-                    [
-                        dict(type='RandomFlip', prob=1.),
-                        dict(type='RandomFlip', prob=0.)
-                    ],
+        transforms=[[
+            dict(type='Resize', scale=s, keep_ratio=True) for s in img_scales
+        ], [
+            dict(type='RandomFlip', prob=1.),
+            dict(type='RandomFlip', prob=0.)
+        ],
                     [
                         dict(
                             type='PackDetInputs',

configs/centernet/centernet_r18-dcnv2_8xb16-crop512-140e_coco.py

@@ -147,7 +147,9 @@
         type='TestTimeAug',
         transforms=[
             [
-                # ``RandomFlip`` must be placed before ``RandomCenterCropPad``
+                # ``RandomFlip`` must be placed before ``RandomCenterCropPad``,
+                # otherwise bounding box coordinates after flipping cannot be
+                # recovered correctly.
                 dict(type='RandomFlip', prob=1.),
                 dict(type='RandomFlip', prob=0.)
             ],

configs/rtmdet/rtmdet_l_8xb32-300e_coco.py

@@ -187,21 +187,27 @@
     type='DetTTAModel',
     tta_cfg=dict(nms=dict(type='nms', iou_threshold=0.6), max_per_img=100))
 
+img_scales = [(640, 640), (320, 320), (960, 960)]
 tta_pipeline = [
     dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
     dict(
         type='TestTimeAug',
         transforms=[
-            [dict(type='Resize', scale=(640, 640), keep_ratio=True)],
             [
-                # ``RandomFlip`` must be placed before ``Pad``
+                dict(type='Resize', scale=s, keep_ratio=True)
+                for s in img_scales
+            ],
+            [
+                # ``RandomFlip`` must be placed before ``Pad``, otherwise
+                # bounding box coordinates after flipping cannot be
+                # recovered correctly.
                 dict(type='RandomFlip', prob=1.),
                 dict(type='RandomFlip', prob=0.)
             ],
             [
                 dict(
                     type='Pad',
-                    size=(640, 640),
+                    size=(960, 960),
                     pad_val=dict(img=(114, 114, 114))),
             ],
             [

configs/yolox/yolox_s_8xb8-300e_coco.py

@@ -240,14 +240,20 @@
     type='DetTTAModel',
     tta_cfg=dict(nms=dict(type='nms', iou_threshold=0.65), max_per_img=100))
 
+img_scales = [(640, 640), (320, 320), (960, 960)]
 tta_pipeline = [
     dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
     dict(
         type='TestTimeAug',
         transforms=[
-            [dict(type='Resize', scale=img_scale, keep_ratio=True)],
             [
-                # ``RandomFlip`` must be placed before ``Pad``
+                dict(type='Resize', scale=s, keep_ratio=True)
+                for s in img_scales
+            ],
+            [
+                # ``RandomFlip`` must be placed before ``Pad``, otherwise
+                # bounding box coordinates after flipping cannot be
+                # recovered correctly.
                 dict(type='RandomFlip', prob=1.),
                 dict(type='RandomFlip', prob=0.)
             ],