Compute Library
 21.02
GCBatchNormalizationLayerKernel Class Reference

Interface for the BatchNormalization layer kernel. More...

#include <GCBatchNormalizationLayerKernel.h>

Collaboration diagram for GCBatchNormalizationLayerKernel:
[legend]

Public Member Functions

 GCBatchNormalizationLayerKernel ()
 Constructor. More...
 
 GCBatchNormalizationLayerKernel (const GCBatchNormalizationLayerKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
GCBatchNormalizationLayerKerneloperator= (const GCBatchNormalizationLayerKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
 GCBatchNormalizationLayerKernel (GCBatchNormalizationLayerKernel &&)=default
 Default Move Constructor. More...
 
GCBatchNormalizationLayerKerneloperator= (GCBatchNormalizationLayerKernel &&)=default
 Default move assignment operator. More...
 
 ~GCBatchNormalizationLayerKernel ()=default
 Default destructor. More...
 
void configure (const IGCTensor *input, IGCTensor *output, const IGCTensor *mean, const IGCTensor *var, const IGCTensor *beta=nullptr, const IGCTensor *gamma=nullptr, float epsilon=0.001f, ActivationLayerInfo act_info=ActivationLayerInfo())
 Set the input and output tensors. More...
 
void run (const Window &window) override
 Enqueue the OpenGL ES shader to process the given window. More...
 
- Public Member Functions inherited from IGCKernel
 IGCKernel ()
 Constructor. More...
 
GCKernelkernel ()
 Returns a reference to the GLES kernel of this object. More...
 
void add_1D_tensor_argument (unsigned int &idx, const IGCTensor *tensor, const unsigned int binding_point, 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_2D_tensor_argument (unsigned int &idx, const IGCTensor *tensor, const unsigned int binding_point, 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_3D_tensor_argument (unsigned int &idx, const IGCTensor *tensor, const unsigned int binding_point, const Window &window)
 Add the passed 3D tensor's parameters to the object's kernel's arguments starting from the index idx. More...
 
unsigned int num_arguments_per_1D_tensor () const
 Returns the number of arguments enqueued per 1D tensor object. More...
 
unsigned int num_arguments_per_2D_tensor () const
 Returns the number of arguments enqueued per 2D tensor object. More...
 
unsigned int num_arguments_per_3D_tensor () const
 Returns the number of arguments enqueued per 3D tensor object. More...
 
void set_lws_hint (gles::NDRange &lws_hint)
 Set the Local-Workgroup-Size hint. More...
 
void set_target (GPUTarget target)
 Set the targeted GPU architecture. More...
 
GPUTarget get_target () const
 Get the targeted GPU architecture. More...
 
- 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 ITensorInfo *mean, const ITensorInfo *var, const ITensorInfo *beta=nullptr, const ITensorInfo *gamma=nullptr, float epsilon=0.001f, ActivationLayerInfo act_info=ActivationLayerInfo())
 Static function to check if given info will lead to a valid configuration of GCBatchNormalizationLayerKernel. More...
 

Detailed Description

Interface for the BatchNormalization layer kernel.

Definition at line 35 of file GCBatchNormalizationLayerKernel.h.

Constructor & Destructor Documentation

◆ GCBatchNormalizationLayerKernel() [1/3]

Constructor.

Definition at line 136 of file GCBatchNormalizationLayerKernel.cpp.

137  : _input(nullptr), _output(nullptr), _mean(nullptr), _var(nullptr), _beta(nullptr), _gamma(nullptr), _epsilon(0.0f)
138 {
139 }

◆ GCBatchNormalizationLayerKernel() [2/3]

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

◆ GCBatchNormalizationLayerKernel() [3/3]

Default Move Constructor.

◆ ~GCBatchNormalizationLayerKernel()

Default destructor.

Member Function Documentation

◆ configure()

void configure ( const IGCTensor input,
IGCTensor output,
const IGCTensor mean,
const IGCTensor var,
const IGCTensor beta = nullptr,
const IGCTensor gamma = nullptr,
float  epsilon = 0.001f,
ActivationLayerInfo  act_info = ActivationLayerInfo() 
)

Set the input and output tensors.

Parameters
[in]inputSource tensor. 3 lower dimensions represent a single input with dimensions [width, height, FM]. The rest are optional and used for representing batches. Data types supported: F16/F32.
[out]outputDestination tensor. Output will have the same number of dimensions as input. Data type supported: same as input
[in]meanMean values tensor. 1 dimension with size equal to the feature maps [FM]. Data types supported: Same as input
[in]varVariance values tensor. 1 dimension with size equal to the feature maps [FM]. Data types supported: Same as input
[in]beta(Optional) Beta values tensor info. 1 dimension with size equal to the feature maps [FM]. If not provided, default value for beta is 0. Data types supported: Same as input
[in]gamma(Optional) Gamma values tensor info. 1 dimension with size equal to the feature maps [FM]. If not provided, default value for gamma is 1. Data types supported: Same as input
[in]epsilon(optional) Small value to avoid division with zero.
[in]act_info(Optional) Activation layer information in case of a fused activation. Only RELU, BOUNDED_RELU and LU_BOUNDED_RELU supported.

Definition at line 141 of file GCBatchNormalizationLayerKernel.cpp.

References ActivationLayerInfo::a(), ActivationLayerInfo::activation(), ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, ActivationLayerInfo::b(), GCKernelLibrary::create_kernel(), ITensorInfo::data_type(), ActivationLayerInfo::enabled(), arm_compute::quantization::epsilon, arm_compute::F32, arm_compute::float_to_string_with_full_precision(), GCKernelLibrary::get(), ITensor::info(), arm_compute::test::validation::input, arm_compute::string_from_activation_func(), arm_compute::support::cpp11::to_string(), and arm_compute::validate_arguments().

Referenced by GCBatchNormalizationLayer::configure().

143 {
144  ARM_COMPUTE_ERROR_ON_NULLPTR(input, output, mean, var);
145 
146  ARM_COMPUTE_ERROR_THROW_ON(validate_arguments(input->info(), output->info(), mean->info(), var->info(),
147  (beta != nullptr) ? beta->info() : nullptr, (gamma != nullptr) ? gamma->info() : nullptr,
148  epsilon, act_info));
149 
150  _input = input;
151  _output = output;
152  _mean = mean;
153  _var = var;
154  _beta = beta;
155  _gamma = gamma;
156  _epsilon = epsilon;
157 
158  // Set build options
159  std::set<std::string> build_opts;
160  std::string dt_name = (input->info()->data_type() == DataType::F32) ? "DATA_TYPE_FP32" : "DATA_TYPE_FP16";
161  build_opts.emplace(("#define " + dt_name));
162  build_opts.emplace(("#define ESPILON " + float_to_string_with_full_precision(_epsilon)));
163  build_opts.emplace(("#define LOCAL_SIZE_X " + support::cpp11::to_string(1)));
164  build_opts.emplace(("#define LOCAL_SIZE_Y " + support::cpp11::to_string(1)));
165  build_opts.emplace(("#define LOCAL_SIZE_Z " + support::cpp11::to_string(1)));
166  if(beta == nullptr)
167  {
168  build_opts.emplace("#define USE_DEFAULT_BETA");
169  }
170  if(gamma == nullptr)
171  {
172  build_opts.emplace("#define USE_DEFAULT_GAMMA");
173  }
174 
175  if(act_info.enabled())
176  {
177  build_opts.emplace("#define " + string_from_activation_func(act_info.activation()));
178  build_opts.emplace("#define A_VAL " + float_to_string_with_full_precision(act_info.a()));
179  build_opts.emplace("#define B_VAL " + float_to_string_with_full_precision(act_info.b()));
180  }
181 
182  // Create kernel
183  _kernel = static_cast<GCKernel>(GCKernelLibrary::get().create_kernel("batchnormalization_layer", build_opts));
184 
185  // Configure kernel window
186  auto win_config = validate_and_configure_window(input->info(), output->info(), mean->info(), var->info(),
187  (beta != nullptr) ? beta->info() : nullptr, (gamma != nullptr) ? gamma->info() : nullptr);
188  ARM_COMPUTE_ERROR_THROW_ON(win_config.first);
189 
190  IGCKernel::configure(win_config.second);
191 }
bool enabled() const
Check if initialised.
Definition: Types.h:1600
float a() const
Get the alpha value.
Definition: Types.h:1590
std::string to_string(T &&value)
Convert integer and float values to string.
virtual DataType data_type() const =0
Data type used for each element of the tensor.
1 channel, 1 F32 per channel
const std::string & string_from_activation_func(ActivationLayerInfo::ActivationFunction act)
Translates a given activation function to a string.
Definition: Utils.cpp:163
#define ARM_COMPUTE_ERROR_THROW_ON(status)
Definition: Error.h:455
GCKernel class.
std::string float_to_string_with_full_precision(float val)
Create a string with the float in full precision.
Definition: Utils.h:1262
virtual ITensorInfo * info() const =0
Interface to be implemented by the child class to return the tensor&#39;s metadata.
static GCKernelLibrary & get()
Get the static instance of GCKernelLibrary.
Status validate_arguments(const ITensorInfo *input, const ITensorInfo *bias, const ITensorInfo *output, const GEMMLowpOutputStageInfo *output_stage)
GCKernel create_kernel(const std::string &shader_name, const StringSet &build_options_set={}) const
Creates a kernel from the kernel library.
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
Definition: Validate.h:161
ActivationFunction activation() const
Get the type of activation function.
Definition: Types.h:1585
float b() const
Get the beta value.
Definition: Types.h:1595

◆ operator=() [1/2]

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

◆ operator=() [2/2]

Default move assignment operator.

◆ run()

void run ( const Window window)
overridevirtual

Enqueue the OpenGL ES shader to process the given window.

Parameters
[in]windowRegion on which to execute the kernel. (Must be a valid region of the window returned by window()).

Implements IGCKernel.

Definition at line 207 of file GCBatchNormalizationLayerKernel.cpp.

References IGCKernel::add_1D_tensor_argument(), IGCKernel::add_3D_tensor_argument(), ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, Window::DimX, arm_compute::enqueue(), Window::first_slice_window_1D(), Window::first_slice_window_3D(), ITensor::info(), IGCKernel::num_arguments_per_3D_tensor(), ITensorInfo::padding(), Window::set(), IGCTensor::set_needs_shifting(), Window::shift(), arm_compute::test::validation::reference::slice(), Window::slide_window_slice_3D(), and IKernel::window().

208 {
211 
212  _kernel.use();
213 
214  _output->set_needs_shifting(true);
215 
217  Window slice_in = window.first_slice_window_3D();
218 
219  Window vector_slice = window.first_slice_window_1D();
220  vector_slice.set(Window::DimX, Window::Dimension(0, 0, 0));
221 
222  unsigned int idx = 2 * num_arguments_per_3D_tensor();
223  unsigned int binding_point = 3;
224  add_1D_tensor_argument(idx, _mean, binding_point, vector_slice);
225  add_1D_tensor_argument(idx, _var, ++binding_point, vector_slice);
226  if(_beta != nullptr)
227  {
228  add_1D_tensor_argument(idx, _beta, ++binding_point, vector_slice);
229  }
230  if(_gamma != nullptr)
231  {
232  add_1D_tensor_argument(idx, _gamma, ++binding_point, vector_slice);
233  }
234 
235  slice.shift(Window::DimX, -(_output->info()->padding()).left);
236 
237  do
238  {
239  idx = 0;
240  add_3D_tensor_argument(idx, _input, 1, slice_in);
241  add_3D_tensor_argument(idx, _output, 2, slice);
242 
243  _kernel.update_shader_params();
244  enqueue(*this, slice);
245  }
246  while(window.slide_window_slice_3D(slice) && window.slide_window_slice_3D(slice_in));
247 }
const Window & window() const
The maximum window the kernel can be executed on.
Definition: IKernel.cpp:28
void add_3D_tensor_argument(unsigned int &idx, const IGCTensor *tensor, const unsigned int binding_point, const Window &window)
Add the passed 3D tensor&#39;s parameters to the object&#39;s kernel&#39;s arguments starting from the index idx...
Definition: IGCKernel.cpp:132
void enqueue(IGCKernel &kernel, const Window &window, const gles::NDRange &lws=gles::NDRange(1U, 1U, 1U))
Add the kernel to the command queue with the given window.
Definition: IGCKernel.cpp:41
void shift(size_t dimension, int shift_value)
Shift the values of a given dimension by the given shift_value.
Definition: Window.inl:133
Describe one of the image&#39;s dimensions with a start, end and step.
Definition: Window.h:77
unsigned int num_arguments_per_3D_tensor() const
Returns the number of arguments enqueued per 3D tensor object.
Definition: IGCKernel.cpp:147
static constexpr size_t DimX
Alias for dimension 0 also known as X dimension.
Definition: Window.h:43
void set_needs_shifting(bool needs_shifting)
Set the flag indicating whether or not a tensor needs shifting.
Definition: IGCTensor.cpp:61
virtual ITensorInfo * info() const =0
Interface to be implemented by the child class to return the tensor&#39;s metadata.
void set(size_t dimension, const Dimension &dim)
Set the values of a given dimension.
Definition: Window.inl:49
virtual PaddingSize padding() const =0
Padding of tensor.
bool slide_window_slice_3D(Window &slice) const
Slide the passed 3D window slice.
Definition: Window.h:335
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Definition: Validate.h:941
Window first_slice_window_3D() const
First 3D slice of the window.
Definition: Window.h:291
Describe a multidimensional execution window.
Definition: Window.h:39
void add_1D_tensor_argument(unsigned int &idx, const IGCTensor *tensor, const unsigned int binding_point, const Window &window)
Add the passed 1D tensor&#39;s parameters to the object&#39;s kernel&#39;s arguments starting from the index idx...
Definition: IGCKernel.cpp:122
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
Definition: Validate.h:205
Window first_slice_window_1D() const
First 1D slice of the window.
Definition: Window.h:275
SimpleTensor< T > slice(const SimpleTensor< T > &src, Coordinates starts, Coordinates ends)

◆ validate()

Status validate ( const ITensorInfo input,
const ITensorInfo output,
const ITensorInfo mean,
const ITensorInfo var,
const ITensorInfo beta = nullptr,
const ITensorInfo gamma = nullptr,
float  epsilon = 0.001f,
ActivationLayerInfo  act_info = ActivationLayerInfo() 
)
static

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

Parameters
[in]inputSource tensor info. In case of output tensor info = nullptr, this tensor will store the result. 3 lower dimensions represent a single input with dimensions [width, height, FM]. The rest are optional and used for representing batches. Data types supported: F16/F32.
[in]outputDestination tensor info. Output will have the same number of dimensions as input. Data type supported: same as input
[in]meanMean values tensor info. 1 dimension with size equal to the feature maps [FM]. Data types supported: Same as input
[in]varVariance values tensor info. 1 dimension with size equal to the feature maps [FM]. Data types supported: Same as input
[in]beta(Optional) Beta values tensor info. 1 dimension with size equal to the feature maps [FM]. If not provided, default value for beta is 0. Data types supported: Same as input
[in]gamma(Optional) Gamma values tensor info. 1 dimension with size equal to the feature maps [FM]. If not provided, default value for gamma is 1. Data types supported: Same as input
[in]epsilon(Optional) Small value to avoid division with zero. Default value is 0.001f.
[in]act_info(Optional) Activation layer information in case of a fused activation. Only RELU, BOUNDED_RELU and LU_BOUNDED_RELU supported.
Returns
a status

Definition at line 193 of file GCBatchNormalizationLayerKernel.cpp.

References ARM_COMPUTE_RETURN_ON_ERROR, ICloneable< T >::clone(), and arm_compute::validate_arguments().

197 {
198  ARM_COMPUTE_RETURN_ON_ERROR(validate_arguments(input, output, mean, var, beta, gamma, epsilon, act_info));
199  ARM_COMPUTE_RETURN_ON_ERROR(validate_and_configure_window(input->clone().get(), output->clone().get(),
200  mean->clone().get(), var->clone().get(),
201  beta->clone().get(), gamma->clone().get())
202  .first);
203 
204  return Status{};
205 }
#define ARM_COMPUTE_RETURN_ON_ERROR(status)
Checks if a status contains an error and returns it.
Definition: Error.h:204
Status class.
Definition: Error.h:52
virtual std::unique_ptr< T > clone() const =0
Provide a clone of the current object of class T.
Status validate_arguments(const ITensorInfo *input, const ITensorInfo *bias, const ITensorInfo *output, const GEMMLowpOutputStageInfo *output_stage)

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