mirror of
https://github.com/opencv/opencv.git
synced 2024-12-16 02:19:12 +08:00
613c12e590
CUDA backend for the DNN module * stub cuda4dnn design * minor fixes for tests and doxygen * add csl public api directory to module headers * add low-level CSL components * add high-level CSL components * integrate csl::Tensor into backbone code * switch to CPU iff unsupported; otherwise, fail on error * add fully connected layer * add softmax layer * add activation layers * support arbitary rank TensorDescriptor * pass input wrappers to `initCUDA()` * add 1d/2d/3d-convolution * add pooling layer * reorganize and refactor code * fixes for gcc, clang and doxygen; remove cxx14/17 code * add blank_layer * add LRN layer * add rounding modes for pooling layer * split tensor.hpp into tensor.hpp and tensor_ops.hpp * add concat layer * add scale layer * add batch normalization layer * split math.cu into activations.cu and math.hpp * add eltwise layer * add flatten layer * add tensor transform api * add asymmetric padding support for convolution layer * add reshape layer * fix rebase issues * add permute layer * add padding support for concat layer * refactor and reorganize code * add normalize layer * optimize bias addition in scale layer * add prior box layer * fix and optimize normalize layer * add asymmetric padding support for pooling layer * add event API * improve pooling performance for some padding scenarios * avoid over-allocation of compute resources to kernels * improve prior box performance * enable layer fusion * add const layer * add resize layer * add slice layer * add padding layer * add deconvolution layer * fix channelwise ReLU initialization * add vector traits * add vectorized versions of relu, clipped_relu, power * add vectorized concat kernels * improve concat_with_offsets performance * vectorize scale and bias kernels * add support for multi-billion element tensors * vectorize prior box kernels * fix address alignment check * improve bias addition performance of conv/deconv/fc layers * restructure code for supporting multiple targets * add DNN_TARGET_CUDA_FP64 * add DNN_TARGET_FP16 * improve vectorization * add region layer * improve tensor API, add dynamic ranks 1. use ManagedPtr instead of a Tensor in backend wrapper 2. add new methods to tensor classes - size_range: computes the combined size of for a given axis range - tensor span/view can be constructed from a raw pointer and shape 3. the tensor classes can change their rank at runtime (previously rank was fixed at compile-time) 4. remove device code from tensor classes (as they are unused) 5. enforce strict conditions on tensor class APIs to improve debugging ability * fix parametric relu activation * add squeeze/unsqueeze tensor API * add reorg layer * optimize permute and enable 2d permute * enable 1d and 2d slice * add split layer * add shuffle channel layer * allow tensors of different ranks in reshape primitive * patch SliceOp to allow Crop Layer * allow extra shape inputs in reshape layer * use `std::move_backward` instead of `std::move` for insert in resizable_static_array * improve workspace management * add spatial LRN * add nms (cpu) to region layer * add max pooling with argmax ( and a fix to limits.hpp) * add max unpooling layer * rename DNN_TARGET_CUDA_FP32 to DNN_TARGET_CUDA * update supportBackend to be more rigorous * remove stray include from preventing non-cuda build * include op_cuda.hpp outside condition #if * refactoring, fixes and many optimizations * drop DNN_TARGET_CUDA_FP64 * fix gcc errors * increase max. tensor rank limit to six * add Interp layer * drop custom layers; use BackendNode * vectorize activation kernels * fixes for gcc * remove wrong assertion * fix broken assertion in unpooling primitive * fix build errors in non-CUDA build * completely remove workspace from public API * fix permute layer * enable accuracy and perf. tests for DNN_TARGET_CUDA * add asynchronous forward * vectorize eltwise ops * vectorize fill kernel * fixes for gcc * remove CSL headers from public API * remove csl header source group from cmake * update min. cudnn version in cmake * add numerically stable FP32 log1pexp * refactor code * add FP16 specialization to cudnn based tensor addition * vectorize scale1 and bias1 + minor refactoring * fix doxygen build * fix invalid alignment assertion * clear backend wrappers before allocateLayers * ignore memory lock failures * do not allocate internal blobs * integrate NVTX * add numerically stable half precision log1pexp * fix indentation, following coding style, improve docs * remove accidental modification of IE code * Revert "add asynchronous forward" This reverts commit 1154b9da9da07e9b52f8a81bdcea48cf31c56f70. * [cmake] throw error for unsupported CC versions * fix rebase issues * add more docs, refactor code, fix bugs * minor refactoring and fixes * resolve warnings/errors from clang * remove haveCUDA() checks from supportBackend() * remove NVTX integration * changes based on review comments * avoid exception when no CUDA device is present * add color code for CUDA in Net::dump
74 lines
3.3 KiB
C++
74 lines
3.3 KiB
C++
// This file is part of OpenCV project.
|
|
// It is subject to the license terms in the LICENSE file found in the top-level directory
|
|
// of this distribution and at http://opencv.org/license.html.
|
|
|
|
#ifndef OPENCV_DNN_SRC_CUDA_ARRAY_HPP
|
|
#define OPENCV_DNN_SRC_CUDA_ARRAY_HPP
|
|
|
|
#include <cuda_runtime.h>
|
|
|
|
#include "types.hpp"
|
|
|
|
#include <cstddef>
|
|
#include <type_traits>
|
|
#include <iterator>
|
|
|
|
namespace cv { namespace dnn { namespace cuda4dnn { namespace csl { namespace device {
|
|
|
|
template <class T, std::size_t N>
|
|
struct array {
|
|
using value_type = T;
|
|
using size_type = device::size_type;
|
|
using difference_type = std::ptrdiff_t;
|
|
using reference = typename std::add_lvalue_reference<value_type>::type;
|
|
using const_reference = typename std::add_lvalue_reference<typename std::add_const<value_type>::type>::type;
|
|
using pointer = typename std::add_pointer<value_type>::type;
|
|
using const_pointer = typename std::add_pointer<typename std::add_const<value_type>::type>::type;
|
|
using iterator = pointer;
|
|
using const_iterator = const_pointer;
|
|
using reverse_iterator = std::reverse_iterator<iterator>;
|
|
using const_reverse_iterator = std::reverse_iterator<const_iterator>;
|
|
|
|
__host__ __device__ bool empty() const noexcept { return N == 0; }
|
|
__host__ __device__ size_type size() const noexcept { return N; }
|
|
|
|
__host__ __device__ iterator begin() noexcept { return ptr; }
|
|
__host__ __device__ iterator end() noexcept { return ptr + N; }
|
|
__host__ __device__ const_iterator begin() const noexcept { return ptr; }
|
|
__host__ __device__ const_iterator end() const noexcept { return ptr + N; }
|
|
|
|
__host__ __device__ const_iterator cbegin() const noexcept { return ptr; }
|
|
__host__ __device__ const_iterator cend() const noexcept { return ptr + N; }
|
|
|
|
__host__ __device__ reverse_iterator rbegin() noexcept { return ptr + N; }
|
|
__host__ __device__ reverse_iterator rend() noexcept { return ptr; }
|
|
__host__ __device__ const_reverse_iterator rbegin() const noexcept { return ptr + N; }
|
|
__host__ __device__ const_reverse_iterator rend() const noexcept { return ptr; }
|
|
|
|
__host__ __device__ const_reverse_iterator crbegin() const noexcept { return ptr + N; }
|
|
__host__ __device__ const_reverse_iterator crend() const noexcept { return ptr; }
|
|
|
|
template <class InputItr>
|
|
__host__ void assign(InputItr first, InputItr last) {
|
|
std::copy(first, last, std::begin(ptr));
|
|
}
|
|
|
|
__host__ __device__ reference operator[](int idx) { return ptr[idx]; }
|
|
__host__ __device__ const_reference operator[](int idx) const { return ptr[idx]; }
|
|
|
|
__host__ __device__ reference front() { return ptr[0]; }
|
|
__host__ __device__ const_reference front() const { return ptr[0]; }
|
|
|
|
__host__ __device__ reference back() { return ptr[N - 1]; }
|
|
__host__ __device__ const_reference back() const { return ptr[N - 1]; }
|
|
|
|
__host__ __device__ pointer data() noexcept { return ptr; }
|
|
__host__ __device__ const_pointer data() const noexcept { return ptr; }
|
|
|
|
T ptr[N];
|
|
};
|
|
|
|
}}}}} /* namespace cv::dnn::cuda4dnn::csl::device */
|
|
|
|
#endif /* OPENCV_DNN_SRC_CUDA_ARRAY_HPP */
|