Compute Library
 19.08
CLConvertFullyConnectedWeightsKernel Class Reference

Interface to convert the 2D Fully Connected weights from NCHW to NHWC or vice versa. More...

#include <CLConvertFullyConnectedWeightsKernel.h>

Collaboration diagram for CLConvertFullyConnectedWeightsKernel:
[legend]

Public Member Functions

 CLConvertFullyConnectedWeightsKernel ()
 Default constructor. More...
 
 CLConvertFullyConnectedWeightsKernel (const CLConvertFullyConnectedWeightsKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
CLConvertFullyConnectedWeightsKerneloperator= (const CLConvertFullyConnectedWeightsKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
 CLConvertFullyConnectedWeightsKernel (CLConvertFullyConnectedWeightsKernel &&)=default
 Allow instances of this class to be moved. More...
 
CLConvertFullyConnectedWeightsKerneloperator= (CLConvertFullyConnectedWeightsKernel &&)=default
 Allow instances of this class to be moved. More...
 
 ~CLConvertFullyConnectedWeightsKernel ()=default
 Default destructor. More...
 
void configure (const ICLTensor *input, ICLTensor *output, const TensorShape &original_input_shape, DataLayout data_layout)
 Set the input and output tensor. More...
 
void run (const Window &window, cl::CommandQueue &queue) override
 Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue. More...
 
- Public Member Functions inherited from ICLKernel
 ICLKernel ()
 Constructor. More...
 
cl::Kernel & kernel ()
 Returns a reference to the OpenCL kernel of this object. More...
 
template<typename T >
void add_1D_array_argument (unsigned int &idx, const ICLArray< T > *array, const Strides &strides, unsigned int num_dimensions, const Window &window)
 Add the passed 1D array's parameters to the object's kernel's arguments starting from the index idx. More...
 
void add_1D_tensor_argument (unsigned int &idx, const ICLTensor *tensor, const Window &window)
 Add the passed 1D tensor's parameters to the object's kernel's arguments starting from the index idx. More...
 
void add_1D_tensor_argument_if (bool cond, unsigned int &idx, const ICLTensor *tensor, const Window &window)
 Add the passed 1D tensor's parameters to the object's kernel's arguments starting from the index idx if the condition is true. More...
 
void add_2D_tensor_argument (unsigned int &idx, const ICLTensor *tensor, const Window &window)
 Add the passed 2D tensor's parameters to the object's kernel's arguments starting from the index idx. More...
 
void add_2D_tensor_argument_if (bool cond, unsigned int &idx, const ICLTensor *tensor, const Window &window)
 Add the passed 2D tensor's parameters to the object's kernel's arguments starting from the index idx if the condition is true. More...
 
void add_3D_tensor_argument (unsigned int &idx, const ICLTensor *tensor, const Window &window)
 Add the passed 3D tensor's parameters to the object's kernel's arguments starting from the index idx. More...
 
void add_4D_tensor_argument (unsigned int &idx, const ICLTensor *tensor, const Window &window)
 Add the passed 4D tensor's parameters to the object's kernel's arguments starting from the index idx. More...
 
template<typename T >
void add_argument (unsigned int &idx, T value)
 Add the passed parameters to the object's kernel's arguments starting from the index idx. More...
 
void set_lws_hint (const cl::NDRange &lws_hint)
 Set the Local-Workgroup-Size hint. More...
 
cl::NDRange lws_hint () const
 Return the Local-Workgroup-Size hint. More...
 
const std::string & config_id () const
 Get the configuration ID. More...
 
void set_target (GPUTarget target)
 Set the targeted GPU architecture. More...
 
void set_target (cl::Device &device)
 Set the targeted GPU architecture according to the CL device. More...
 
GPUTarget get_target () const
 Get the targeted GPU architecture. More...
 
size_t get_max_workgroup_size ()
 Get the maximum workgroup size for the device the CLKernelLibrary uses. More...
 
template<typename T , unsigned int dimension_size>
void add_array_argument (unsigned &idx, const ICLArray< T > *array, const Strides &strides, unsigned int num_dimensions, const Window &window)
 Add the passed array's parameters to the object's kernel's arguments starting from the index idx. More...
 
template<unsigned int dimension_size>
void add_tensor_argument (unsigned &idx, const ICLTensor *tensor, const Window &window)
 
- Public Member Functions inherited from IKernel
 IKernel ()
 Constructor. More...
 
virtual ~IKernel ()=default
 Destructor. More...
 
virtual bool is_parallelisable () const
 Indicates whether or not the kernel is parallelisable. More...
 
virtual BorderSize border_size () const
 The size of the border for that kernel. More...
 
const Windowwindow () const
 The maximum window the kernel can be executed on. More...
 

Static Public Member Functions

static Status validate (const ITensorInfo *input, const ITensorInfo *output, const TensorShape &original_input_shape, DataLayout data_layout)
 Static function to check if given info will lead to a valid configuration of CLConvertFullyConnectedWeightsKernel. More...
 
- Static Public Member Functions inherited from ICLKernel
static constexpr unsigned int num_arguments_per_1D_array ()
 Returns the number of arguments enqueued per 1D array object. More...
 
static constexpr unsigned int num_arguments_per_1D_tensor ()
 Returns the number of arguments enqueued per 1D tensor object. More...
 
static constexpr unsigned int num_arguments_per_2D_tensor ()
 Returns the number of arguments enqueued per 2D tensor object. More...
 
static constexpr unsigned int num_arguments_per_3D_tensor ()
 Returns the number of arguments enqueued per 3D tensor object. More...
 
static constexpr unsigned int num_arguments_per_4D_tensor ()
 Returns the number of arguments enqueued per 4D tensor object. More...
 
static cl::NDRange gws_from_window (const Window &window)
 Get the global work size given an execution window. More...
 

Detailed Description

Interface to convert the 2D Fully Connected weights from NCHW to NHWC or vice versa.

Note
This function can be applied to the 2D weights used by a Fully Connected layer if:
  • It follows a Convolution layer
  • The data layout used by the network does not match the one the model has been trained in.
This function assumes the weights are already reshaped (transposed)

Definition at line 41 of file CLConvertFullyConnectedWeightsKernel.h.

Constructor & Destructor Documentation

◆ CLConvertFullyConnectedWeightsKernel() [1/3]

Default constructor.

Definition at line 35 of file CLConvertFullyConnectedWeightsKernel.cpp.

36  : _input(nullptr), _output(nullptr)
37 {
38 }

◆ CLConvertFullyConnectedWeightsKernel() [2/3]

Prevent instances of this class from being copied (As this class contains pointers)

◆ CLConvertFullyConnectedWeightsKernel() [3/3]

Allow instances of this class to be moved.

◆ ~CLConvertFullyConnectedWeightsKernel()

Default destructor.

Member Function Documentation

◆ configure()

void configure ( const ICLTensor input,
ICLTensor output,
const TensorShape original_input_shape,
DataLayout  data_layout 
)

Set the input and output tensor.

Parameters
[in]inputSource weights tensor to convert. Must be 2 dimensional. Data types supported: U8/S8/QASYMM8/U16/S16/U32/S32/F16/F32.
[out]outputThe converted weights tensor. Shape and Data Type: Same as input.
[in]original_input_shapeShape of the original input tensor (the one entering fully connected layer).
[in]data_layoutThe data layout the weights have been trained in.

Definition at line 40 of file CLConvertFullyConnectedWeightsKernel.cpp.

42 {
43  ARM_COMPUTE_ERROR_ON_NULLPTR(input, output);
44 
45  // Output tensor auto initialisation if not yet initialized
46  auto_init_if_empty(*output->info(), *input->info()->clone());
47 
48  ARM_COMPUTE_ERROR_THROW_ON(CLConvertFullyConnectedWeightsKernel::validate(input->info(), output->info(), original_input_shape, data_layout));
49 
50  _input = input;
51  _output = output;
52 
53  const DataLayout input_data_layout = (data_layout == DataLayout::NCHW) ? DataLayout::NHWC : DataLayout::NCHW;
54 
55  const int width_idx = get_data_layout_dimension_index(input_data_layout, DataLayoutDimension::WIDTH);
56  const int height_idx = get_data_layout_dimension_index(input_data_layout, DataLayoutDimension::HEIGHT);
57  const int channel_idx = get_data_layout_dimension_index(input_data_layout, DataLayoutDimension::CHANNEL);
58 
59  const unsigned int num_elems_per_input_plane = original_input_shape[width_idx] * original_input_shape[height_idx];
60  const unsigned int num_channels = original_input_shape[channel_idx];
61 
62  const unsigned int factor_1 = (data_layout == DataLayout::NCHW) ? num_elems_per_input_plane : num_channels;
63  const unsigned int factor_2 = (data_layout == DataLayout::NCHW) ? num_channels : num_elems_per_input_plane;
64 
65  // Set build options
66  CLBuildOptions build_opts;
67  build_opts.add_option("-DDATA_TYPE=" + get_cl_type_from_data_type(input->info()->data_type()));
68  build_opts.add_option("-DFACTOR_1=" + support::cpp11::to_string(factor_1));
69  build_opts.add_option("-DFACTOR_2=" + support::cpp11::to_string(factor_2));
70 
71  // Create kernel
72  _kernel = static_cast<cl::Kernel>(CLKernelLibrary::get().create_kernel("convert_fc_weights", build_opts.options()));
73 
74  // Configure kernel window
75  Window win = calculate_max_window(*input->info(), Steps());
76  ICLKernel::configure_internal(win);
77 }
const DataLayout data_layout
Definition: Im2Col.cpp:146
std::string to_string(T &&value)
Convert integer and float values to string.
static CLKernelLibrary & get()
Access the KernelLibrary singleton.
#define ARM_COMPUTE_ERROR_THROW_ON(status)
Definition: Error.h:327
static Status validate(const ITensorInfo *input, const ITensorInfo *output, const TensorShape &original_input_shape, DataLayout data_layout)
Static function to check if given info will lead to a valid configuration of CLConvertFullyConnectedW...
Window calculate_max_window(const ValidRegion &valid_region, const Steps &steps=Steps(), bool skip_border=false, BorderSize border_size=BorderSize())
Calculate the maximum window for a given tensor shape and border setting.
Definition: Helpers.cpp:28
bool auto_init_if_empty(ITensorInfo &info, const TensorShape &shape, int num_channels, DataType data_type, QuantizationInfo quantization_info=QuantizationInfo())
Auto initialize the tensor info (shape, number of channels and data type) if the current assignment i...
Definition: Helpers.inl:201
std::string get_cl_type_from_data_type(const DataType &dt)
Translates a tensor data type to the appropriate OpenCL type.
Definition: CLHelpers.cpp:35
std::unique_ptr< Kernel > create_kernel()
Helper function to create and return a unique_ptr pointed to a CL/GLES kernel object.
Definition: Helpers.h:86
Num samples, channels, height, width.
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
Definition: Validate.h:161
Num samples, height, width, channels.
size_t get_data_layout_dimension_index(const DataLayout data_layout, const DataLayoutDimension data_layout_dimension)
Get the index of the given dimension.
Definition: Helpers.inl:326
DataLayout
[DataLayout enum definition]
Definition: Types.h:114

References CLBuildOptions::add_option(), ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, arm_compute::auto_init_if_empty(), arm_compute::calculate_max_window(), arm_compute::CHANNEL, ICloneable< T >::clone(), arm_compute::create_kernel(), arm_compute::test::validation::data_layout, ITensorInfo::data_type(), CLKernelLibrary::get(), arm_compute::get_cl_type_from_data_type(), arm_compute::get_data_layout_dimension_index(), arm_compute::HEIGHT, ITensor::info(), arm_compute::NCHW, arm_compute::NHWC, CLBuildOptions::options(), arm_compute::support::cpp11::to_string(), CLConvertFullyConnectedWeightsKernel::validate(), and arm_compute::WIDTH.

◆ operator=() [1/2]

Prevent instances of this class from being copied (As this class contains pointers)

◆ operator=() [2/2]

Allow instances of this class to be moved.

◆ run()

void run ( const Window window,
cl::CommandQueue &  queue 
)
overridevirtual

Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue.

Note
The queue is not flushed by this method, and therefore the kernel will not have been executed by the time this method returns.
Parameters
[in]windowRegion on which to execute the kernel. (Must be a valid region of the window returned by window()).
[in,out]queueCommand queue on which to enqueue the kernel.

Implements ICLKernel.

Definition at line 102 of file CLConvertFullyConnectedWeightsKernel.cpp.

103 {
106 
107  unsigned int idx = 0;
108  add_2D_tensor_argument(idx, _input, window);
109  add_2D_tensor_argument(idx, _output, window);
110  enqueue(queue, *this, window);
111 }
const Window & window() const
The maximum window the kernel can be executed on.
Definition: IKernel.cpp:28
void enqueue(cl::CommandQueue &queue, ICLKernel &kernel, const Window &window, const cl::NDRange &lws_hint=CLKernelLibrary::get().default_ndrange(), bool use_dummy_work_items=false)
Add the kernel to the command queue with the given window.
Definition: ICLKernel.cpp:39
void add_2D_tensor_argument(unsigned int &idx, const ICLTensor *tensor, const Window &window)
Add the passed 2D tensor's parameters to the object's kernel's arguments starting from the index idx.
Definition: ICLKernel.h:134
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
Definition: Validate.h:205
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Definition: Validate.h:940

References ICLKernel::add_2D_tensor_argument(), ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, arm_compute::enqueue(), and IKernel::window().

◆ validate()

Status validate ( const ITensorInfo input,
const ITensorInfo output,
const TensorShape original_input_shape,
DataLayout  data_layout 
)
static

Static function to check if given info will lead to a valid configuration of CLConvertFullyConnectedWeightsKernel.

Parameters
[in]inputSource weights tensor info to convert. Must be 2 dimensional. Data types supported: U8/S8/QASYMM8/U16/S16/U32/S32/F16/F32.
[in]outputThe converted weights tensor info. Shape and Data Type: Same as input.
[in]original_input_shapeShape of the original input tensor (the one entering fully connected layer).
[in]data_layoutThe data layout the weights have been trained in.

Definition at line 79 of file CLConvertFullyConnectedWeightsKernel.cpp.

81 {
88  ARM_COMPUTE_RETURN_ERROR_ON(input->num_dimensions() != 2);
89  ARM_COMPUTE_RETURN_ERROR_ON(input->dimension(1) != original_input_shape.total_size_lower(3));
91 
92  // Checks performed when output is configured
93  if((output != nullptr) && (output->total_size() != 0))
94  {
97  }
98 
99  return Status{};
100 }
#define ARM_COMPUTE_RETURN_ERROR_ON_F16_UNSUPPORTED(tensor)
Definition: CLValidate.h:34
const DataLayout data_layout
Definition: Im2Col.cpp:146
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES(...)
Definition: Validate.h:545
1 channel, 1 U8 per channel
#define ARM_COMPUTE_RETURN_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(t, c,...)
Definition: Validate.h:791
1 channel, 1 F32 per channel
1 channel, 1 U16 per channel
#define ARM_COMPUTE_RETURN_ERROR_ON(cond)
If the condition is true, an error is returned.
Definition: Error.h:244
1 channel, 1 F16 per channel
1 channel, 1 S32 per channel
1 channel, 1 U32 per channel
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_SHAPES(...)
Definition: Validate.h:443
quantized, asymmetric fixed-point 8-bit number
1 channel, 1 S16 per channel
signed 8-bit number

References ARM_COMPUTE_RETURN_ERROR_ON, ARM_COMPUTE_RETURN_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN, ARM_COMPUTE_RETURN_ERROR_ON_F16_UNSUPPORTED, ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES, ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_SHAPES, arm_compute::test::validation::data_layout, ITensorInfo::dimension(), arm_compute::F16, arm_compute::F32, ITensorInfo::num_dimensions(), arm_compute::QASYMM8, arm_compute::S16, arm_compute::S32, arm_compute::S8, ITensorInfo::total_size(), TensorShape::total_size_lower(), arm_compute::U16, arm_compute::U32, arm_compute::U8, and arm_compute::UNKNOWN.

Referenced by CLConvertFullyConnectedWeightsKernel::configure(), and CLConvertFullyConnectedWeights::validate().


The documentation for this class was generated from the following files: