fix cutout issue & pad doc

mindspore/ccsrc/minddata/dataset/api/vision.cc

@@ -901,8 +901,14 @@ std::shared_ptr<TensorOp> RandomAffineOperation::Build() {
   if (translate_range_.size() == 2) {
     translate_range_.resize(4);
   }
+  std::vector<uint8_t> fill_value = {fill_value_[0], fill_value_[0], fill_value_[0]};
+  if (fill_value_.size() == 3) {
+    fill_value[1] = fill_value_[1];
+    fill_value[2] = fill_value_[2];
+  }
+
   auto tensor_op = std::make_shared<RandomAffineOp>(degrees_, translate_range_, scale_range_, shear_ranges_,
-                                                    interpolation_, fill_value_);
+                                                    interpolation_, fill_value);
   return tensor_op;
 }
 

mindspore/ccsrc/minddata/dataset/include/vision.h

@@ -198,14 +198,14 @@ std::shared_ptr<NormalizePadOperation> NormalizePad(const std::vector<float> &me
 /// \brief Function to create a Pad TensorOp
 /// \notes Pads the image according to padding parameters
 /// \param[in] padding A vector representing the number of pixels to pad the image
-///    If vector has one value, it pads all sides of the image with that value
+///    If vector has one value, it pads all sides of the image with that value.
 ///    If vector has two values, it pads left and right with the first and
-///    top and bottom with the second value
+///    top and bottom with the second value.
 ///    If vector has four values, it pads left, top, right, and bottom with
-///    those values respectively
+///    those values respectively.
 /// \param[in] fill_value A vector representing the pixel intensity of the borders if the padding_mode is
-///    BorderType.kConstant. If 3 values are provided,
-///    it is used to fill R, G, B channels respectively
+///    BorderType.kConstant. If 1 value is provided, it is used for all RGB channels. If 3 values are provided,
+///    it is used to fill R, G, B channels respectively.
 /// \param[in] padding_mode The method of padding (default=BorderType.kConstant)
 ///    Can be any of
 ///    [BorderType.kConstant, BorderType.kEdge, BorderType.kReflect, BorderType.kSymmetric]
@@ -230,8 +230,9 @@ std::shared_ptr<PadOperation> Pad(std::vector<int32_t> padding, std::vector<uint
 ///    if size is 2, (min_shear_x, max_shear_x, 0, 0)
 ///    if size is 4, (min_shear_x, max_shear_x, min_shear_y, max_shear_y)
 /// \param[in] interpolation An enum for the mode of interpolation
-/// \param[in] fill_value A uint8_t vector of size 3, representing the pixel intensity of the borders, it is used to
-///    fill R, G, B channels respectively.
+/// \param[in] fill_value A vector representing the value to fill the area outside the transform
+///    in the output image. If 1 value is provided, it is used for all RGB channels.
+///    If 3 values are provided, it is used to fill R, G, B channels respectively.
 /// \return Shared pointer to the current TensorOperation.
 std::shared_ptr<RandomAffineOperation> RandomAffine(
   const std::vector<float_t> &degrees, const std::vector<float_t> &translate_range = {0.0, 0.0, 0.0, 0.0},
@@ -272,8 +273,9 @@ std::shared_ptr<RandomColorAdjustOperation> RandomColorAdjust(std::vector<float>
 ///     it pads the left, top, right and bottom respectively.
 /// \param[in] pad_if_needed A boolean whether to pad the image if either side is smaller than
 ///     the given output size.
-/// \param[in] fill_value A vector representing the pixel intensity of the borders, it is used to
-///     fill R, G, B channels respectively.
+/// \param[in] fill_value A vector representing the pixel intensity of the borders if the padding_mode is
+///     BorderType.kConstant. If 1 value is provided, it is used for all RGB channels.
+///     If 3 values are provided, it is used to fill R, G, B channels respectively.
 /// \return Shared pointer to the current TensorOperation.
 std::shared_ptr<RandomCropOperation> RandomCrop(std::vector<int32_t> size, std::vector<int32_t> padding = {0, 0, 0, 0},
                                                 bool pad_if_needed = false, std::vector<uint8_t> fill_value = {0, 0, 0},
@@ -305,8 +307,9 @@ std::shared_ptr<RandomCropDecodeResizeOperation> RandomCropDecodeResize(
 ///     it pads the left, top, right and bottom respectively.
 /// \param[in] pad_if_needed A boolean whether to pad the image if either side is smaller than
 ///     the given output size.
-/// \param[in] fill_value A vector representing the pixel intensity of the borders, it is used to
-///     fill R, G, B channels respectively.
+/// \param[in] fill_value A vector representing the pixel intensity of the borders if the padding_mode is
+///     BorderType.kConstant. If 1 value is provided, it is used for all RGB channels.
+///     If 3 values are provided, it is used to fill R, G, B channels respectively.
 /// \param[in] padding_mode The method of padding (default=BorderType::kConstant).It can be any of
 ///     [BorderType::kConstant, BorderType::kEdge, BorderType::kReflect, BorderType::kSymmetric].
 /// \return Shared pointer to the current TensorOperation.
@@ -389,7 +392,9 @@ std::shared_ptr<RandomResizedCropWithBBoxOperation> RandomResizedCropWithBBox(
 /// \param[in] resample An enum for the mode of interpolation
 /// \param[in] expand A boolean representing whether the image is expanded after rotation
 /// \param[in] center A float vector of size 2, representing the x and y center of rotation.
-/// \param[in] fill_value A uint8_t vector of size 3, representing the rgb value of the fill color
+/// \param[in] fill_value A vector representing the value to fill the area outside the transform
+///    in the output image. If 1 value is provided, it is used for all RGB channels.
+///    If 3 values are provided, it is used to fill R, G, B channels respectively.
 /// \return Shared pointer to the current TensorOp
 std::shared_ptr<RandomRotationOperation> RandomRotation(
   std::vector<float> degrees, InterpolationMode resample = InterpolationMode::kNearestNeighbour, bool expand = false,

mindspore/ccsrc/minddata/dataset/kernels/image/image_utils.cc

@@ -949,7 +949,7 @@ Status Erase(const std::shared_ptr<Tensor> &input, std::shared_ptr<Tensor> *outp
       RETURN_STATUS_UNEXPECTED("CutOut: load image failed.");
     }
     if (input_cv->Rank() != 3 || num_channels != 3) {
-      RETURN_STATUS_UNEXPECTED("CutOut: image shape is not <H,W,C> or <H,W>.");
+      RETURN_STATUS_UNEXPECTED("CutOut: image shape is not <H,W,C>.");
     }
     cv::Mat input_img = input_cv->mat();
     int32_t image_h = input_cv->shape()[0];

mindspore/dataset/vision/c_transforms.py

@@ -438,8 +438,8 @@ class Pad(ImageTensorOperation):
     Args:
         padding (Union[int, sequence]): The number of pixels to pad the image.
             If a single number is provided, it pads all borders with this value.
-            If a tuple or list of 2 values are provided, it pads the (left and top)
-            with the first value and (right and bottom) with the second value.
+            If a tuple or list of 2 values are provided, it pads left and right
+            with the first value and top and bottom with the second value.
             If 4 values are provided as a list or tuple,
             it pads the left, top, right and bottom respectively.
         fill_value (Union[int, tuple], optional): The pixel intensity of the borders, only valid for
@@ -674,8 +674,8 @@ class RandomCrop(ImageTensorOperation):
         padding (Union[int, sequence], optional): The number of pixels to pad the image (default=None).
             If padding is not None, pad image firstly with padding values.
             If a single number is provided, pad all borders with this value.
-            If a tuple or list of 2 values are provided, pad the (left and top)
-            with the first value and (right and bottom) with the second value.
+            If a tuple or list of 2 values are provided, it pads left and right
+            with the first value and top and bottom with the second value.
             If 4 values are provided as a list or tuple,
             pad the left, top, right and bottom respectively.
         pad_if_needed (bool, optional): Pad the image if either side is smaller than
@@ -790,8 +790,8 @@ class RandomCropWithBBox(ImageTensorOperation):
         padding (Union[int, sequence], optional): The number of pixels to pad the image (default=None).
             If padding is not None, first pad image with padding values.
             If a single number is provided, pad all borders with this value.
-            If a tuple or list of 2 values are provided, pad the (left and top)
-            with the first value and (right and bottom) with the second value.
+            If a tuple or list of 2 values are provided, it pads left and right
+            with the first value and top and bottom with the second value.
             If 4 values are provided as a list or tuple, pad the left, top, right and bottom respectively.
         pad_if_needed (bool, optional): Pad the image if either side is smaller than
             the given output size (default=False).