Fix dvpp input validation and Aipp config generation issue

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

@@ -32,6 +32,7 @@
 #endif
 #ifdef ENABLE_ACL
 #include "minddata/dataset/core/ascend_resource.h"
+#include "minddata/dataset/kernels/image/dvpp/utils/CommonDataType.h"
 #include "minddata/dataset/kernels/ir/vision/ascend_vision_ir.h"
 #endif
 
@@ -42,6 +43,15 @@ using json = nlohmann::json;
 struct Execute::ExtraInfo {
   std::multimap<std::string, std::vector<uint32_t>> aipp_cfg_;
   bool init_with_shared_ptr_ = true;  // Initial execute object with shared_ptr as default
+#ifdef ENABLE_ACL
+  std::multimap<std::string, std::string> op2para_map_ = {{vision::kDvppCropJpegOperation, "size"},
+                                                          {vision::kDvppDecodeResizeOperation, "size"},
+                                                          {vision::kDvppDecodeResizeCropOperation, "crop_size"},
+                                                          {vision::kDvppDecodeResizeCropOperation, "resize_size"},
+                                                          {vision::kDvppNormalizeOperation, "mean"},
+                                                          {vision::kDvppNormalizeOperation, "std"},
+                                                          {vision::kDvppResizeJpegOperation, "size"}};
+#endif
 };
 
 // FIXME - Temporarily overload Execute to support both TensorOperation and TensorTransform
@@ -221,6 +231,7 @@ Status Execute::operator()(const mindspore::MSTensor &input, mindspore::MSTensor
   // Parse TensorTransform transforms_ into TensorOperation ops_
   if (info_->init_with_shared_ptr_) {
     RETURN_IF_NOT_OK(ParseTransforms_());
+    info_->init_with_shared_ptr_ = false;
   }
   CHECK_FAIL_RETURN_UNEXPECTED(!ops_.empty(), "Input TensorOperation should be provided");
 
@@ -285,11 +296,13 @@ Status Execute::operator()(const mindspore::MSTensor &input, mindspore::MSTensor
       device_input = std::move(device_output);
     }
     CHECK_FAIL_RETURN_UNEXPECTED(device_input->HasDeviceData(), "Apply transform failed, output tensor has no data");
-    std::shared_ptr<mindspore::dataset::Tensor> host_output;
+
     // TODO(lizhenglong) waiting for computing department development, hence we pop data onto host temporarily.
-    RETURN_IF_NOT_OK(device_resource_->Pop(device_input, &host_output));
-    *output = mindspore::MSTensor(std::make_shared<DETensor>(host_output));
-    // *output = mindspore::MSTensor(std::make_shared<DETensor>(device_input, true)); Use in the future
+    // std::shared_ptr<mindspore::dataset::Tensor> host_output;
+    // RETURN_IF_NOT_OK(device_resource_->Pop(device_input, &host_output));
+    // *output = mindspore::MSTensor(std::make_shared<DETensor>(host_output));
+
+    *output = mindspore::MSTensor(std::make_shared<DETensor>(device_input, true));
 #endif
   }
   return Status::OK();
@@ -306,6 +319,7 @@ Status Execute::operator()(const std::vector<MSTensor> &input_tensor_list, std::
   // Parse TensorTransform transforms_ into TensorOperation ops_
   if (info_->init_with_shared_ptr_) {
     RETURN_IF_NOT_OK(ParseTransforms_());
+    info_->init_with_shared_ptr_ = false;
   }
   CHECK_FAIL_RETURN_UNEXPECTED(!ops_.empty(), "Input TensorOperation should be provided");
 
@@ -386,6 +400,7 @@ Status Execute::operator()(const std::vector<MSTensor> &input_tensor_list, std::
 
 std::vector<uint32_t> AippSizeFilter(const std::vector<uint32_t> &resize_para, const std::vector<uint32_t> &crop_para) {
   std::vector<uint32_t> aipp_size;
+
   // Special condition where (no Crop and no Resize) or (no Crop and resize with fixed ratio) will lead to dynamic input
   if ((resize_para.size() == 0 || resize_para.size() == 1) && crop_para.size() == 0) {
     aipp_size = {0, 0};
@@ -408,6 +423,11 @@ std::vector<uint32_t> AippSizeFilter(const std::vector<uint32_t> &resize_para, c
           : crop_para;
     }
   }
+
+#ifdef ENABLE_ACL
+  aipp_size[0] = DVPP_ALIGN_UP(aipp_size[0], VPC_HEIGHT_ALIGN);  // H
+  aipp_size[1] = DVPP_ALIGN_UP(aipp_size[1], VPC_WIDTH_ALIGN);   // W
+#endif
   return aipp_size;
 }
 
@@ -489,6 +509,7 @@ std::string Execute::AippCfgGenerator() {
 #ifdef ENABLE_ACL
   if (info_->init_with_shared_ptr_) {
     ParseTransforms_();
+    info_->init_with_shared_ptr_ = false;
   }
   std::vector<uint32_t> paras;  // Record the parameters value of each Ascend operators
   for (int32_t i = 0; i < ops_.size(); i++) {
@@ -501,15 +522,9 @@ std::string Execute::AippCfgGenerator() {
 
     // Define map between operator name and parameter name
     ops_[i]->to_json(&ir_info);
-    std::multimap<std::string, std::string> op_list = {{vision::kDvppCropJpegOperation, "size"},
-                                                       {vision::kDvppDecodeResizeOperation, "size"},
-                                                       {vision::kDvppDecodeResizeCropOperation, "crop_size"},
-                                                       {vision::kDvppDecodeResizeCropOperation, "resize_size"},
-                                                       {vision::kDvppNormalizeOperation, "mean"},
-                                                       {vision::kDvppNormalizeOperation, "std"},
-                                                       {vision::kDvppResizeJpegOperation, "size"}};
+
     // Collect the information of operators
-    for (auto pos = op_list.equal_range(ops_[i]->Name()); pos.first != pos.second; ++pos.first) {
+    for (auto pos = info_->op2para_map_.equal_range(ops_[i]->Name()); pos.first != pos.second; ++pos.first) {
       auto paras_key_word = pos.first->second;
       paras = ir_info[paras_key_word].get<std::vector<uint32_t>>();
       info_->aipp_cfg_.insert(std::make_pair(ops_[i]->Name(), paras));
@@ -578,6 +593,11 @@ std::string Execute::AippCfgGenerator() {
     }
     outfile << "}";
     outfile.close();
+  } else {  // For case GPU or CPU
+    outfile << "aipp_op {" << std::endl << "}";
+    outfile.close();
+    MS_LOG(WARNING) << "Your runtime environment is not Ascend310, this config file will lead to undefined behavior on "
+                       "computing result. Please check that.";
   }
 #endif
   return config_location;
@@ -608,8 +628,9 @@ Status Execute::ParseTransforms_() {
 }
 
 Status Execute::validate_device_() {
-  if (device_type_ != MapTargetDevice::kCpu && device_type_ != MapTargetDevice::kAscend310) {
-    std::string err_msg = "Your input device is not supported. (Option: CPU or Ascend310)";
+  if (device_type_ != MapTargetDevice::kCpu && device_type_ != MapTargetDevice::kAscend310 &&
+      device_type_ != MapTargetDevice::kGpu) {
+    std::string err_msg = "Your input device is not supported. (Option: CPU or GPU or Ascend310)";
     MS_LOG(ERROR) << err_msg;
     RETURN_STATUS_UNEXPECTED(err_msg);
   }

mindspore/ccsrc/minddata/dataset/core/ascend_resource.cc

@@ -18,6 +18,7 @@
 #include "include/api/types.h"
 #include "minddata/dataset/include/type_id.h"
 #include "minddata/dataset/core/ascend_resource.h"
+#include "minddata/dataset/kernels/image/image_utils.h"
 
 namespace mindspore {
 namespace dataset {
@@ -59,6 +60,10 @@ Status AscendResource::Sink(const mindspore::MSTensor &host_input, std::shared_p
                                                 MSTypeToDEType(static_cast<TypeId>(host_input.DataType())),
                                                 (const uchar *)(host_input.Data().get()), &de_input);
   RETURN_IF_NOT_OK(rc);
+  if (!IsNonEmptyJPEG(de_input)) {
+    RETURN_STATUS_UNEXPECTED("Dvpp operators can only support processing JPEG image");
+  }
+
   APP_ERROR ret = processor_->H2D_Sink(de_input, *device_input);
   if (ret != APP_ERR_OK) {
     ascend_resource_->Release();

mindspore/ccsrc/minddata/dataset/core/de_tensor.cc

@@ -87,8 +87,8 @@ const std::vector<int64_t> &DETensor::Shape() const { return shape_; }
 std::shared_ptr<const void> DETensor::Data() const {
 #ifndef ENABLE_ANDROID
   if (is_device_) {
-    MS_LOG(ERROR) << "Data() always return the data on the host.";
-    return nullptr;
+    ASSERT_NULL(device_tensor_impl_);
+    return std::shared_ptr<const void>(device_tensor_impl_->GetHostBuffer(), [](const void *) {});
   }
 #endif
   return std::shared_ptr<const void>(tensor_impl_->GetBuffer(), [](const void *) {});

mindspore/ccsrc/minddata/dataset/core/device_tensor.cc

@@ -16,6 +16,9 @@
 
 #include "minddata/dataset/core/global_context.h"
 #include "minddata/dataset/core/device_tensor.h"
+#ifdef ENABLE_ACL
+#include "minddata/dataset/kernels/image/dvpp/utils/MDAclProcess.h"
+#endif
 #include "minddata/dataset/util/status.h"
 
 namespace mindspore {
@@ -25,6 +28,7 @@ DeviceTensor::DeviceTensor(const TensorShape &shape, const DataType &type) : Ten
   std::shared_ptr<MemoryPool> global_pool = GlobalContext::Instance()->mem_pool();
   data_allocator_ = std::make_unique<Allocator<unsigned char>>(global_pool);
   device_data_type_ = type;
+  host_data_tensor_ = nullptr;
 }
 
 Status DeviceTensor::CreateEmpty(const TensorShape &shape, const DataType &type, std::shared_ptr<DeviceTensor> *out) {
@@ -80,6 +84,20 @@ Status DeviceTensor::CreateFromDeviceMemory(const TensorShape &shape, const Data
   return Status::OK();
 }
 
+const unsigned char *DeviceTensor::GetHostBuffer() {
+#ifdef ENABLE_ACL
+  Status rc = DataPop_(&host_data_tensor_);
+  if (!rc.IsOk()) {
+    MS_LOG(ERROR) << "Pop device data onto host fail, a nullptr will be returned";
+    return nullptr;
+  }
+#endif
+  if (!host_data_tensor_) {
+    return nullptr;
+  }
+  return host_data_tensor_->GetBuffer();
+}
+
 uint8_t *DeviceTensor::GetDeviceBuffer() { return device_data_; }
 
 uint8_t *DeviceTensor::GetDeviceMutableBuffer() { return device_data_; }
@@ -109,5 +127,42 @@ Status DeviceTensor::SetSize_(const uint32_t &new_size) {
   size_ = new_size;
   return Status::OK();
 }
+
+#ifdef ENABLE_ACL
+Status DeviceTensor::DataPop_(std::shared_ptr<Tensor> *host_tensor) {
+  void *resHostBuf = nullptr;
+  APP_ERROR ret = aclrtMallocHost(&resHostBuf, this->DeviceDataSize());
+  if (ret != APP_ERR_OK) {
+    MS_LOG(ERROR) << "Failed to allocate memory from host ret = " << ret;
+    return Status(StatusCode::kMDNoSpace);
+  }
+  std::shared_ptr<void> outBuf(resHostBuf, aclrtFreeHost);
+  auto processedInfo_ = outBuf;
+  // Memcpy the output data from device to host
+  ret = aclrtMemcpy(outBuf.get(), this->DeviceDataSize(), this->GetDeviceBuffer(), this->DeviceDataSize(),
+                    ACL_MEMCPY_DEVICE_TO_HOST);
+  if (ret != APP_ERR_OK) {
+    MS_LOG(ERROR) << "Failed to copy memory from device to host, ret = " << ret;
+    return Status(StatusCode::kMDOutOfMemory);
+  }
+  auto data = std::static_pointer_cast<unsigned char>(processedInfo_);
+  unsigned char *ret_ptr = data.get();
+
+  mindspore::dataset::dsize_t dvppDataSize = this->DeviceDataSize();
+  const mindspore::dataset::TensorShape dvpp_shape({dvppDataSize, 1, 1});
+  uint32_t _output_width_ = this->GetYuvStrideShape()[0];
+  uint32_t _output_widthStride_ = this->GetYuvStrideShape()[1];
+  uint32_t _output_height_ = this->GetYuvStrideShape()[2];
+  uint32_t _output_heightStride_ = this->GetYuvStrideShape()[3];
+  const mindspore::dataset::DataType dvpp_data_type(mindspore::dataset::DataType::DE_UINT8);
+  mindspore::dataset::Tensor::CreateFromMemory(dvpp_shape, dvpp_data_type, ret_ptr, host_tensor);
+  (*host_tensor)->SetYuvShape(_output_width_, _output_widthStride_, _output_height_, _output_heightStride_);
+  if (!(*host_tensor)->HasData()) {
+    return Status(StatusCode::kMCDeviceError);
+  }
+  MS_LOG(INFO) << "Successfully pop DeviceTensor data onto host";
+  return Status::OK();
+}
+#endif
 }  // namespace dataset
 }  // namespace mindspore

mindspore/ccsrc/minddata/dataset/core/device_tensor.h

@@ -43,6 +43,8 @@ class DeviceTensor : public Tensor {
                                        const uint32_t &dataSize, const std::vector<uint32_t> &attributes,
                                        std::shared_ptr<DeviceTensor> *out);
 
+  const unsigned char *GetHostBuffer();
+
   uint8_t *GetDeviceBuffer();
 
   uint8_t *GetDeviceMutableBuffer();
@@ -61,6 +63,10 @@ class DeviceTensor : public Tensor {
   Status SetYuvStrideShape_(const uint32_t &width, const uint32_t &widthStride, const uint32_t &height,
                             const uint32_t &heightStride);
 
+#ifdef ENABLE_ACL
+  Status DataPop_(std::shared_ptr<Tensor> *host_tensor);
+#endif
+
   std::vector<uint32_t> YUV_shape_;  // YUV_shape_ = {width, widthStride, height, heightStride}
 
   uint8_t *device_data_;
@@ -68,6 +74,9 @@ class DeviceTensor : public Tensor {
   uint32_t size_;
 
   DataType device_data_type_;
+
+  // We use this Tensor to store device_data when DeviceTensor pop onto host
+  std::shared_ptr<Tensor> host_data_tensor_;
 };
 
 }  // namespace dataset

tests/st/cpp/dataset/test_de.cc

@@ -67,7 +67,8 @@ TEST_F(TestDE, TestDvpp) {
 #ifdef ENABLE_ACL
   // Read images from target directory
   std::shared_ptr<mindspore::dataset::Tensor> de_tensor;
-  mindspore::dataset::Tensor::CreateFromFile("./data/dataset/apple.jpg", &de_tensor);
+  Status rc = mindspore::dataset::Tensor::CreateFromFile("./data/dataset/apple.jpg", &de_tensor);
+  ASSERT_TRUE(rc.IsOk());
   auto image = MSTensor(std::make_shared<mindspore::dataset::DETensor>(de_tensor));
 
   // Define dvpp transform
@@ -77,13 +78,13 @@ TEST_F(TestDE, TestDvpp) {
   mindspore::dataset::Execute Transform(decode_resize_crop, MapTargetDevice::kAscend310);
 
   // Apply transform on images
-  Status rc = Transform(image, &image);
+  rc = Transform(image, &image);
   std::string aipp_cfg = Transform.AippCfgGenerator();
   ASSERT_EQ(aipp_cfg, "./aipp.cfg");
 
   // Check image info
   ASSERT_TRUE(rc.IsOk());
-  ASSERT_EQ(image.Shape().size(), 3);
+  ASSERT_EQ(image.Shape().size(), 2);
   int32_t real_h = 0;
   int32_t real_w = 0;
   int32_t remainder = crop_paras[crop_paras.size() - 1] % 16;
@@ -94,15 +95,21 @@ TEST_F(TestDE, TestDvpp) {
     real_h = (crop_paras[0] % 2 == 0) ? crop_paras[0] : crop_paras[0] + 1;
     real_w = (remainder == 0) ? crop_paras[1] : crop_paras[1] + 16 - remainder;
   }
-  /* TODO Use in the future after compute college finish their job
+
   ASSERT_EQ(image.Shape()[0], real_h);  // For image in YUV format, each pixel takes 1.5 byte
   ASSERT_EQ(image.Shape()[1], real_w);
   ASSERT_EQ(image.DataSize(), real_h * real_w * 1.5);
-   */
+
+  ASSERT_TRUE(image.Data().get() != nullptr);
+  ASSERT_EQ(image.DataType(), mindspore::DataType::kNumberTypeUInt8);
+  ASSERT_EQ(image.IsDevice(), true);
+
+  /* This is the criterion for previous method(Without pop)
   ASSERT_EQ(image.Shape()[0], 1.5 * real_h * real_w);  // For image in YUV format, each pixel takes 1.5 byte
   ASSERT_EQ(image.Shape()[1], 1);
   ASSERT_EQ(image.Shape()[2], 1);
   ASSERT_EQ(image.DataSize(), real_h * real_w * 1.5);
+  */
 #endif
 }
 
@@ -110,7 +117,8 @@ TEST_F(TestDE, TestDvppSinkMode) {
 #ifdef ENABLE_ACL
   // Read images from target directory
   std::shared_ptr<mindspore::dataset::Tensor> de_tensor;
-  mindspore::dataset::Tensor::CreateFromFile("./data/dataset/apple.jpg", &de_tensor);
+  Status rc = mindspore::dataset::Tensor::CreateFromFile("./data/dataset/apple.jpg", &de_tensor);
+  ASSERT_TRUE(rc.IsOk());
   auto image = MSTensor(std::make_shared<mindspore::dataset::DETensor>(de_tensor));
 
   // Define dvpp transform
@@ -123,11 +131,11 @@ TEST_F(TestDE, TestDvppSinkMode) {
   mindspore::dataset::Execute Transform(trans_list, MapTargetDevice::kAscend310);
 
   // Apply transform on images
-  Status rc = Transform(image, &image);
+  rc = Transform(image, &image);
 
   // Check image info
   ASSERT_TRUE(rc.IsOk());
-  ASSERT_EQ(image.Shape().size(), 3);
+  ASSERT_EQ(image.Shape().size(), 2);
   int32_t real_h = 0;
   int32_t real_w = 0;
   int32_t remainder = crop_paras[crop_paras.size() - 1] % 16;
@@ -138,10 +146,13 @@ TEST_F(TestDE, TestDvppSinkMode) {
     real_h = (crop_paras[0] % 2 == 0) ? crop_paras[0] : crop_paras[0] + 1;
     real_w = (remainder == 0) ? crop_paras[1] : crop_paras[1] + 16 - remainder;
   }
-  ASSERT_EQ(image.Shape()[0], 1.5 * real_h * real_w);  // For image in YUV format, each pixel takes 1.5 byte
-  ASSERT_EQ(image.Shape()[1], 1);
-  ASSERT_EQ(image.Shape()[2], 1);
+  ASSERT_EQ(image.Shape()[0], real_h);  // For image in YUV format, each pixel takes 1.5 byte
+  ASSERT_EQ(image.Shape()[1], real_w);
   ASSERT_EQ(image.DataSize(), real_h * real_w * 1.5);
+
+  ASSERT_TRUE(image.Data().get() != nullptr);
+  ASSERT_EQ(image.DataType(), mindspore::DataType::kNumberTypeUInt8);
+  ASSERT_EQ(image.IsDevice(), true);
   Transform.DeviceMemoryRelease();
 #endif
 }
@@ -149,7 +160,8 @@ TEST_F(TestDE, TestDvppSinkMode) {
 TEST_F(TestDE, TestDvppDecodeResizeCropNormalize) {
 #ifdef ENABLE_ACL
   std::shared_ptr<mindspore::dataset::Tensor> de_tensor;
-  mindspore::dataset::Tensor::CreateFromFile("./data/dataset/apple.jpg", &de_tensor);
+  Status rc = mindspore::dataset::Tensor::CreateFromFile("./data/dataset/apple.jpg", &de_tensor);
+  ASSERT_TRUE(rc.IsOk());
   auto image = MSTensor(std::make_shared<mindspore::dataset::DETensor>(de_tensor));
 
   // Define dvpp transform
@@ -170,11 +182,11 @@ TEST_F(TestDE, TestDvppDecodeResizeCropNormalize) {
   ASSERT_EQ(aipp_cfg, "./aipp.cfg");
 
   // Apply transform on images
-  Status rc = Transform(image, &image);
+  rc = Transform(image, &image);
 
   // Check image info
   ASSERT_TRUE(rc.IsOk());
-  ASSERT_EQ(image.Shape().size(), 3);
+  ASSERT_EQ(image.Shape().size(), 2);
   int32_t real_h = 0;
   int32_t real_w = 0;
   int32_t remainder = crop_paras[crop_paras.size() - 1] % 16;
@@ -185,10 +197,14 @@ TEST_F(TestDE, TestDvppDecodeResizeCropNormalize) {
     real_h = (crop_paras[0] % 2 == 0) ? crop_paras[0] : crop_paras[0] + 1;
     real_w = (remainder == 0) ? crop_paras[1] : crop_paras[1] + 16 - remainder;
   }
-  ASSERT_EQ(image.Shape()[0], 1.5 * real_h * real_w);  // For image in YUV format, each pixel takes 1.5 byte
-  ASSERT_EQ(image.Shape()[1], 1);
-  ASSERT_EQ(image.Shape()[2], 1);
+
+  ASSERT_EQ(image.Shape()[0], real_h);  // For image in YUV format, each pixel takes 1.5 byte
+  ASSERT_EQ(image.Shape()[1], real_w);
   ASSERT_EQ(image.DataSize(), real_h * real_w * 1.5);
+
+  ASSERT_TRUE(image.Data().get() != nullptr);
+  ASSERT_EQ(image.DataType(), mindspore::DataType::kNumberTypeUInt8);
+  ASSERT_EQ(image.IsDevice(), true);
   Transform.DeviceMemoryRelease();
 #endif
 }