34 : _input(nullptr), _output(nullptr), _factor1(0), _factor2(0)
57 const unsigned int num_elems_per_input_plane = original_input_shape[width_idx] * original_input_shape[height_idx];
58 const unsigned int num_channels = original_input_shape[channel_idx];
60 _factor1 = (data_layout ==
DataLayout::NCHW) ? num_elems_per_input_plane : num_channels;
61 _factor2 = (data_layout ==
DataLayout::NCHW) ? num_channels : num_elems_per_input_plane;
65 INEKernel::configure(win);
79 if((output !=
nullptr) && (output->
total_size() != 0))
89 void NEConvertFullyConnectedWeightsKernel::run_convert_fc_weights(
const Window &
window)
99 *
reinterpret_cast<T *
>(output.
ptr() +
id.x() * dst_stride_x + (
id.y() % _factor1 * _factor2 +
id.y() / _factor1) * dst_stride_y) = *
reinterpret_cast<T *
>(input.
ptr());
113 run_convert_fc_weights<uint8_t>(
window);
116 run_convert_fc_weights<uint16_t>(
window);
119 run_convert_fc_weights<uint32_t>(
window);
virtual size_t num_dimensions() const =0
The number of dimensions of the tensor (rank)
Window calculate_max_window(const ValidRegion &valid_region, const Steps &steps, bool skip_border, BorderSize border_size)
const Window & window() const
The maximum window the kernel can be executed on.
virtual size_t dimension(size_t index) const =0
Return the size of the requested dimension.
#define ARM_COMPUTE_ERROR(msg)
Print the given message then throw an std::runtime_error.
virtual DataType data_type() const =0
Data type used for each element of the tensor.
const DataLayout data_layout
Store the tensor's metadata.
#define ARM_COMPUTE_ERROR_THROW_ON(status)
NEConvertFullyConnectedWeightsKernel()
Default constructor.
#define ARM_COMPUTE_RETURN_ERROR_ON(cond)
If the condition is true, an error is returned.
Interface for Neon tensor.
size_t total_size_lower(size_t dimension) const
Compute size of dimensions lower than the given one.
Copyright (c) 2017-2021 Arm Limited.
#define ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(...)
T x() const
Alias to access the size of the first dimension.
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 NEConvertFullyConnectedW...
#define ARM_COMPUTE_UNUSED(...)
To avoid unused variables warnings.
Class to describe a number of elements in each dimension.
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.
constexpr uint8_t * ptr() const
Return a pointer to the current pixel.
virtual size_t element_size() const =0
Element size in bytes calculated as data_size() * num_channels()
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Num samples, channels, height, width.
ScaleKernelInfo info(interpolation_policy, default_border_mode, PixelValue(), sampling_policy, false)
Information about executing thread and CPU.
virtual size_t total_size() const =0
Returns the total size of the tensor in bytes.
void configure(const ITensor *input, ITensor *output, const TensorShape &original_input_shape, DataLayout data_layout)
Set the input and output tensor.
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_SHAPES(...)
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES(...)
Num samples, height, width, channels.
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
void execute_window_loop(const Window &w, L &&lambda_function, Ts &&... iterators)
Iterate through the passed window, automatically adjusting the iterators and calling the lambda_funct...
T y() const
Alias to access the size of the second dimension.
void run(const Window &window, const ThreadInfo &info) override
Execute the kernel on the passed window.
virtual const Strides & strides_in_bytes() const =0
The strides in bytes for accessing each dimension of the tensor.
size_t get_data_layout_dimension_index(const DataLayout data_layout, const DataLayoutDimension data_layout_dimension)
Get the index of the given dimension.
Iterator updated by execute_window_loop for each window element.
DataLayout
[DataLayout enum definition]
Describe a multidimensional execution window.
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)