modify transform op of yolo and solo configs (#2260)

dygraph/configs/fcos/fcos_r50_fpn_multiscale_2x_coco.yml

@@ -10,17 +10,13 @@ weights: output/fcos_r50_fpn_multiscale_2x_coco/model_final
 
 TrainReader:
   sample_transforms:
-  - DecodeOp: {}
-  - RandomFlipOp: {prob: 0.5}
-  - NormalizeImageOp: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
-  - ResizeImage:
-      target_size: [640, 672, 704, 736, 768, 800]
-      max_size: 1333
-      interp: 1
-      use_cv2: true
-  - PermuteOp: {}
+  - Decode: {}
+  - RandomFlip: {prob: 0.5}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - RandomResize: {target_size: [[640, 1333], [672, 1333], [704, 1333], [736, 1333], [768, 1333], [800, 1333]], keep_ratio: true, interp: 1}
+  - Permute: {}
   batch_transforms:
-  - PadBatchOp: {pad_to_stride: 128}
+  - PadBatch: {pad_to_stride: 128}
   - Gt2FCOSTarget:
       object_sizes_boundary: [64, 128, 256, 512]
       center_sampling_radius: 1.5

dygraph/configs/ppyolo/ppyolo_mbv3_large_coco.yml

@@ -13,24 +13,24 @@ TrainReader:
   inputs_def:
     num_max_boxes: 90
   sample_transforms:
-    - DecodeOp: {}
-    - MixupOp: {alpha: 1.5, beta: 1.5}
-    - RandomDistortOp: {}
-    - RandomExpandOp: {fill_value: [123.675, 116.28, 103.53]}
-    - RandomCropOp: {}
-    - RandomFlipOp: {}
+    - Decode: {}
+    - Mixup: {alpha: 1.5, beta: 1.5}
+    - RandomDistort: {}
+    - RandomExpand: {fill_value: [123.675, 116.28, 103.53]}
+    - RandomCrop: {}
+    - RandomFlip: {}
   batch_transforms:
-    - BatchRandomResizeOp:
+    - BatchRandomResize:
         target_size: [224, 256, 288, 320, 352, 384, 416, 448, 480, 512]
         random_size: True
         random_interp: True
         keep_ratio: False
-    - NormalizeBoxOp: {}
-    - PadBoxOp: {num_max_boxes: 90}
-    - BboxXYXY2XYWHOp: {}
-    - NormalizeImageOp: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
-    - PermuteOp: {}
-    - Gt2YoloTargetOp:
+    - NormalizeBox: {}
+    - PadBox: {num_max_boxes: 90}
+    - BboxXYXY2XYWH: {}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+    - Gt2YoloTarget:
         anchor_masks: [[3, 4, 5], [0, 1, 2]]
         anchors: [[11, 18], [34, 47], [51, 126], [115, 71], [120, 195], [254, 235]]
         downsample_ratios: [32, 16]
@@ -42,10 +42,10 @@ TrainReader:
 
 EvalReader:
   sample_transforms:
-    - DecodeOp: {}
-    - ResizeOp: {target_size: [320, 320], keep_ratio: False, interp: 2}
-    - NormalizeImageOp: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
-    - PermuteOp: {}
+    - Decode: {}
+    - Resize: {target_size: [320, 320], keep_ratio: False, interp: 2}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
   batch_size: 8
   drop_empty: false
 
@@ -53,10 +53,10 @@ TestReader:
   inputs_def:
     image_shape: [3, 320, 320]
   sample_transforms:
-    - DecodeOp: {}
-    - ResizeOp: {target_size: [320, 320], keep_ratio: False, interp: 2}
-    - NormalizeImageOp: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
-    - PermuteOp: {}
+    - Decode: {}
+    - Resize: {target_size: [320, 320], keep_ratio: False, interp: 2}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
   batch_size: 1
 
 epoch: 270

dygraph/configs/ppyolo/ppyolo_mbv3_small_coco.yml

@@ -13,24 +13,24 @@ TrainReader:
   inputs_def:
     num_max_boxes: 90
   sample_transforms:
-    - DecodeOp: {}
-    - MixupOp: {alpha: 1.5, beta: 1.5}
-    - RandomDistortOp: {}
-    - RandomExpandOp: {fill_value: [123.675, 116.28, 103.53]}
-    - RandomCropOp: {}
-    - RandomFlipOp: {}
+    - Decode: {}
+    - Mixup: {alpha: 1.5, beta: 1.5}
+    - RandomDistort: {}
+    - RandomExpand: {fill_value: [123.675, 116.28, 103.53]}
+    - RandomCrop: {}
+    - RandomFlip: {}
   batch_transforms:
-    - BatchRandomResizeOp:
+    - BatchRandomResize:
         target_size: [224, 256, 288, 320, 352, 384, 416, 448, 480, 512]
         random_size: True
         random_interp: True
         keep_ratio: False
-    - NormalizeBoxOp: {}
-    - PadBoxOp: {num_max_boxes: 90}
-    - BboxXYXY2XYWHOp: {}
-    - NormalizeImageOp: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
-    - PermuteOp: {}
-    - Gt2YoloTargetOp:
+    - NormalizeBox: {}
+    - PadBox: {num_max_boxes: 90}
+    - BboxXYXY2XYWH: {}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+    - Gt2YoloTarget:
         anchor_masks: [[3, 4, 5], [0, 1, 2]]
         anchors: [[11, 18], [34, 47], [51, 126], [115, 71], [120, 195], [254, 235]]
         downsample_ratios: [32, 16]
@@ -42,10 +42,10 @@ TrainReader:
 
 EvalReader:
   sample_transforms:
-    - DecodeOp: {}
-    - ResizeOp: {target_size: [320, 320], keep_ratio: False, interp: 2}
-    - NormalizeImageOp: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
-    - PermuteOp: {}
+    - Decode: {}
+    - Resize: {target_size: [320, 320], keep_ratio: False, interp: 2}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
   batch_size: 8
   drop_empty: false
 
@@ -53,10 +53,10 @@ TestReader:
   inputs_def:
     image_shape: [3, 320, 320]
   sample_transforms:
-    - DecodeOp: {}
-    - ResizeOp: {target_size: [320, 320], keep_ratio: False, interp: 2}
-    - NormalizeImageOp: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
-    - PermuteOp: {}
+    - Decode: {}
+    - Resize: {target_size: [320, 320], keep_ratio: False, interp: 2}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
   batch_size: 1
 
 epoch: 270

dygraph/configs/ppyolo/ppyolo_r18vd_coco.yml

@@ -11,27 +11,27 @@ weights: output/ppyolo_r18vd_coco/model_final
 
 TrainReader:
   sample_transforms:
-    - DecodeOp: {}
-    - MixupOp: {alpha: 1.5, beta: 1.5}
-    - RandomDistortOp: {}
-    - RandomExpandOp: {fill_value: [123.675, 116.28, 103.53]}
-    - RandomCropOp: {}
-    - RandomFlipOp: {}
+    - Decode: {}
+    - Mixup: {alpha: 1.5, beta: 1.5}
+    - RandomDistort: {}
+    - RandomExpand: {fill_value: [123.675, 116.28, 103.53]}
+    - RandomCrop: {}
+    - RandomFlip: {}
   batch_transforms:
-    - BatchRandomResizeOp:
+    - BatchRandomResize:
         target_size: [320, 352, 384, 416, 448, 480, 512, 544, 576, 608]
         random_size: True
         random_interp: True
         keep_ratio: False
-    - NormalizeBoxOp: {}
-    - PadBoxOp: {num_max_boxes: 50}
-    - BboxXYXY2XYWHOp: {}
-    - NormalizeImageOp:
+    - NormalizeBox: {}
+    - PadBox: {num_max_boxes: 50}
+    - BboxXYXY2XYWH: {}
+    - NormalizeImage:
         mean: [0.485, 0.456, 0.406]
         std: [0.229, 0.224, 0.225]
         is_scale: True
-    - PermuteOp: {}
-    - Gt2YoloTargetOp:
+    - Permute: {}
+    - Gt2YoloTarget:
         anchor_masks: [[3, 4, 5], [0, 1, 2]]
         anchors: [[10, 14], [23, 27], [37, 58], [81, 82], [135, 169], [344, 319]]
         downsample_ratios: [32, 16]
@@ -42,10 +42,10 @@ TrainReader:
 
 EvalReader:
   sample_transforms:
-    - DecodeOp: {}
-    - ResizeOp: {target_size: [512, 512], keep_ratio: False, interp: 2}
-    - NormalizeImageOp: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
-    - PermuteOp: {}
+    - Decode: {}
+    - Resize: {target_size: [512, 512], keep_ratio: False, interp: 2}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
   batch_size: 8
   drop_empty: false
 
@@ -53,10 +53,10 @@ TestReader:
   inputs_def:
     image_shape: [3, 512, 512]
   sample_transforms:
-    - DecodeOp: {}
-    - ResizeOp: {target_size: [512, 512], keep_ratio: False, interp: 2}
-    - NormalizeImageOp: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
-    - PermuteOp: {}
+    - Decode: {}
+    - Resize: {target_size: [512, 512], keep_ratio: False, interp: 2}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
   batch_size: 1
 
 epoch: 270

dygraph/configs/solov2/solov2_r50_fpn_3x_coco.yml

@@ -20,17 +20,17 @@ LearningRate:
 
 TrainReader:
   sample_transforms:
-  - DecodeOp: {}
+  - Decode: {}
   - Poly2Mask: {}
-  - RandomResizeOp: {interp: 1,
+  - RandomResize: {interp: 1,
                      target_size: [[640, 1333], [672, 1333], [704, 1333], [736, 1333], [768, 1333], [800, 1333]],
                      keep_ratio: True}
-  - RandomFlipOp: {}
-  - NormalizeImageOp: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
-  - PermuteOp: {}
+  - RandomFlip: {}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
   batch_transforms:
-  - PadBatchOp: {pad_to_stride: 32}
-  - Gt2Solov2TargetOp: {num_grids: [40, 36, 24, 16, 12],
+  - PadBatch: {pad_to_stride: 32}
+  - Gt2Solov2Target: {num_grids: [40, 36, 24, 16, 12],
                         scale_ranges: [[1, 96], [48, 192], [96, 384], [192, 768], [384, 2048]],
                         coord_sigma: 0.2}
   batch_size: 2

dygraph/configs/yolov3/yolov3_mobilenet_v1_270e_voc.yml

@@ -13,24 +13,24 @@ TrainReader:
   inputs_def:
     num_max_boxes: 50
   sample_transforms:
-    - DecodeOp: {}
-    - MixupOp: {alpha: 1.5, beta: 1.5}
-    - RandomDistortOp: {}
-    - RandomExpandOp: {fill_value: [123.675, 116.28, 103.53]}
-    - RandomCropOp: {}
-    - RandomFlipOp: {}
+    - Decode: {}
+    - Mixup: {alpha: 1.5, beta: 1.5}
+    - RandomDistort: {}
+    - RandomExpand: {fill_value: [123.675, 116.28, 103.53]}
+    - RandomCrop: {}
+    - RandomFlip: {}
   batch_transforms:
-    - BatchRandomResizeOp:
+    - BatchRandomResize:
         target_size: [320, 352, 384, 416, 448, 480, 512, 544, 576, 608]
         random_size: True
         random_interp: True
         keep_ratio: False
-    - NormalizeBoxOp: {}
-    - PadBoxOp: {num_max_boxes: 50}
-    - BboxXYXY2XYWHOp: {}
-    - NormalizeImageOp: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
-    - PermuteOp: {}
-    - Gt2YoloTargetOp:
+    - NormalizeBox: {}
+    - PadBox: {num_max_boxes: 50}
+    - BboxXYXY2XYWH: {}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+    - Gt2YoloTarget:
         anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
         anchors: [[10, 13], [16, 30], [33, 23], [30, 61], [62, 45], [59, 119], [116, 90], [156, 198], [373, 326]]
         downsample_ratios: [32, 16, 8]

dygraph/configs/yolov3/yolov3_mobilenet_v1_roadsign.yml

@@ -19,24 +19,24 @@ TrainReader:
   inputs_def:
     num_max_boxes: 50
   sample_transforms:
-    - DecodeOp: {}
-    - MixupOp: {alpha: 1.5, beta: 1.5}
-    - RandomDistortOp: {}
-    - RandomExpandOp: {fill_value: [123.675, 116.28, 103.53]}
-    - RandomCropOp: {}
-    - RandomFlipOp: {}
+    - Decode: {}
+    - Mixup: {alpha: 1.5, beta: 1.5}
+    - RandomDistort: {}
+    - RandomExpand: {fill_value: [123.675, 116.28, 103.53]}
+    - RandomCrop: {}
+    - RandomFlip: {}
   batch_transforms:
-    - BatchRandomResizeOp:
+    - BatchRandomResize:
         target_size: [320, 352, 384, 416, 448, 480, 512, 544, 576, 608]
         random_size: True
         random_interp: True
         keep_ratio: False
-    - NormalizeBoxOp: {}
-    - PadBoxOp: {num_max_boxes: 50}
-    - BboxXYXY2XYWHOp: {}
-    - NormalizeImageOp: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
-    - PermuteOp: {}
-    - Gt2YoloTargetOp:
+    - NormalizeBox: {}
+    - PadBox: {num_max_boxes: 50}
+    - BboxXYXY2XYWH: {}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+    - Gt2YoloTarget:
         anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
         anchors: [[10, 13], [16, 30], [33, 23], [30, 61], [62, 45], [59, 119], [116, 90], [156, 198], [373, 326]]
         downsample_ratios: [32, 16, 8]

dygraph/configs/yolov3/yolov3_mobilenet_v3_large_270e_voc.yml

@@ -13,24 +13,24 @@ TrainReader:
   inputs_def:
     num_max_boxes: 50
   sample_transforms:
-    - DecodeOp: {}
-    - MixupOp: {alpha: 1.5, beta: 1.5}
-    - RandomDistortOp: {}
-    - RandomExpandOp: {fill_value: [123.675, 116.28, 103.53]}
-    - RandomCropOp: {}
-    - RandomFlipOp: {}
+    - Decode: {}
+    - Mixup: {alpha: 1.5, beta: 1.5}
+    - RandomDistort: {}
+    - RandomExpand: {fill_value: [123.675, 116.28, 103.53]}
+    - RandomCrop: {}
+    - RandomFlip: {}
   batch_transforms:
-    - BatchRandomResizeOp:
+    - BatchRandomResize:
         target_size: [320, 352, 384, 416, 448, 480, 512, 544, 576, 608]
         random_size: True
         random_interp: True
         keep_ratio: False
-    - NormalizeBoxOp: {}
-    - PadBoxOp: {num_max_boxes: 50}
-    - BboxXYXY2XYWHOp: {}
-    - NormalizeImageOp: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
-    - PermuteOp: {}
-    - Gt2YoloTargetOp:
+    - NormalizeBox: {}
+    - PadBox: {num_max_boxes: 50}
+    - BboxXYXY2XYWH: {}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+    - Gt2YoloTarget:
         anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
         anchors: [[10, 13], [16, 30], [33, 23], [30, 61], [62, 45], [59, 119], [116, 90], [156, 198], [373, 326]]
         downsample_ratios: [32, 16, 8]