71 const bool is_norm_accross_width = norm_idx == 0;
73 const unsigned int border_width = is_norm_accross_width ? num_elems_processed_per_iteration - 1 : 0;
77 bool window_changed =
false;
81 if(is_norm_accross_width)
94 output_access.set_valid_region(win, input->
valid_region());
97 return std::make_pair(err, win);
102 : _input(nullptr), _output(nullptr), _border_size(0), _is_norm_across_width(false)
131 _is_norm_across_width = norm_idx == 0;
132 const unsigned int border_width = _is_norm_across_width ? num_elems_processed_per_iteration - 1 : 0;
159 kernel_name =
"normalization_layer_cross_map";
164 kernel_name =
"normalization_layer_in_map_nchw";
170 auto win_config = validate_and_configure_window(input->
info(), output->
info(), norm_info);
172 ICLKernel::configure_internal(win_config.second);
175 _config_id =
"normalization_layer_";
200 const int collapsed_dimension = _is_norm_across_width ?
Window::DimZ : 4;
206 unsigned int idx = 0;
float scale_coeff() const
Return the scaling factor of the normalization function.
Window calculate_max_window(const ValidRegion &valid_region, const Steps &steps, bool skip_border, BorderSize border_size)
#define ARM_COMPUTE_RETURN_ERROR_ON_F16_UNSUPPORTED(tensor)
void run(const Window &window, cl::CommandQueue &queue) override
Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue...
BorderSize border_size() const override
The size of the border for that kernel.
const Window & window() const
The maximum window the kernel can be executed on.
float kappa() const
Get the kappa value.
#define ARM_COMPUTE_RETURN_ERROR_ON_DATA_LAYOUT_NOT_IN(t,...)
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.
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_LAYOUT(...)
bool is_in_map() const
Check if normalization is not cross map.
virtual size_t dimension(size_t index) const =0
Return the size of the requested dimension.
Container for 2D border size.
const StringSet & options() const
Gets the current options list set.
cl::NDRange lws_hint() const
Return the Local-Workgroup-Size hint.
uint32_t norm_size() const
Get the normalization size.
NormType type() const
Get the normalization type.
#define ARM_COMPUTE_RETURN_ON_ERROR(status)
Checks if a status contains an error and returns it.
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
Normalization Layer Information class.
bool is_cross_map() const
Check if normalization is cross map.
CLNormalizationLayerKernel()
Constructor.
const DataLayout data_layout
static CLKernelLibrary & get()
Access the KernelLibrary singleton.
Store the tensor's metadata.
#define ARM_COMPUTE_ERROR_THROW_ON(status)
std::string lower_string(const std::string &val)
Lower a given string.
decltype(strategy::transforms) typedef type
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...
Copyright (c) 2017-2021 Arm Limited.
1 channel, 1 F16 per channel
virtual ValidRegion valid_region() const =0
Valid region of the tensor.
Implementation of a static rectangular access pattern.
#define ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(...)
void add_option(std::string option)
Adds option to the existing build option list.
cl::Kernel create_kernel(const CLCompileContext &ctx, const std::string &kernel_name, const std::set< std::string > &build_opts=std::set< std::string >())
Creates an opencl kernel using a compile context.
const std::string & string_from_data_type(DataType dt)
Convert a data type identity into a string.
bool update_window_and_padding(Window &win, Ts &&... patterns)
Update window and padding size for each of the access patterns.
Window collapse_if_possible(const Window &full_window, size_t first, size_t last, bool *has_collapsed=nullptr) const
Collapse the dimensions between first and last if possible.
std::string float_to_string_with_full_precision(float val)
Create a string with the float in full precision.
Class to describe a number of elements in each dimension.
Implementation of a row access pattern.
void configure(const ICLTensor *input, ICLTensor *output, NormalizationLayerInfo norm_info)
Set the input and output tensors.
std::string get_cl_type_from_data_type(const DataType &dt)
Translates a tensor data type to the appropriate OpenCL type.
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...
virtual std::unique_ptr< T > clone() const =0
Provide a clone of the current object of class T.
virtual ITensorInfo * info() const =0
Interface to be implemented by the child class to return the tensor's metadata.
float beta() const
Get the beta value.
void add_option_if(bool cond, std::string option)
Adds option if a given condition is true;.
unsigned int left
left of the border
bool slide_window_slice_3D(Window &slice) const
Slide the passed 3D window slice.
unsigned int right
right of the border
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Num samples, channels, height, width.
Interface for OpenCL tensor.
const std::string & string_from_data_layout(DataLayout dl)
Convert a data layout identity into a string.
virtual size_t total_size() const =0
Returns the total size of the tensor in bytes.
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_SHAPES(...)
#define ARM_COMPUTE_CREATE_ERROR(error_code, msg)
Creates an error with a given message.
static constexpr size_t DimZ
Alias for dimension 2 also known as Z dimension.
Manages all the OpenCL kernels compilation and caching, provides accessors for the OpenCL Context...
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES(...)
static Status validate(const ITensorInfo *input, const ITensorInfo *output, NormalizationLayerInfo norm_info)
Static function to check if given info will lead to a valid configuration of CLNormalizationLayerKern...
Num samples, height, width, channels.
#define ARM_COMPUTE_RETURN_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(t, c,...)
Status validate_arguments(const ITensorInfo *input, const ITensorInfo *bias, const ITensorInfo *output, const GEMMLowpOutputStageInfo *output_stage)
unsigned int num_elems_processed_per_iteration
#define ARM_COMPUTE_RETURN_ERROR_ON_MSG(cond, msg)
If the condition is true, an error is returned.
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
Window first_slice_window_3D() const
First 3D slice of the window.
unsigned int get_normalization_dimension_index(DataLayout layout, const NormalizationLayerInfo &info)
Calculate the normalization dimension index for a given normalization type.
DataLayout
[DataLayout enum definition]
Describe a multidimensional execution window.
Normalization applied within the same map in 2D region.
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
SimpleTensor< T > slice(const SimpleTensor< T > &src, Coordinates starts, Coordinates ends)
virtual DataLayout data_layout() const =0
Get the data layout of the tensor.