mirror of
https://github.com/opencv/opencv.git
synced 2024-12-12 23:49:36 +08:00
1d1faaabef
Added int32, int64 support and type inference to dnn #24411 **Added a type inference to dnn similar to the shape inference, added int32 and int64 support.** - Added getTypes method for layers that calculates layer outputs types and internals types from inputs types (Similar to getMemoryShapes). By default outputs and internals types = input[0] type - Added type inference pipeline similar to shape inference pipeline. LayersShapes struct (that is used in shape inference pipeline) now contains both shapes and types - All layers output blobs are now allocated using the calculated types from the type inference. - Inputs and constants with int32 and int64 types are not automatically converted into float32 now. - Added int32 and int64 support for all the layers with indexing and for all the layers required in tests. Added int32 and int64 support for CUDA: - Added host<->device data moving for int32 and int64 - Added int32 and int64 support for several layers (just slightly modified CUDA C++ templates) Passed all the accuracy tests on CPU, OCL, OCL_FP16, CUDA, CUDA_FP16. (except RAFT model) **CURRENT PROBLEMS**: - ONNX parser always converts int64 constants and layers attributes to int32, so some models with int64 constants doesn't work (e.g. RAFT). The solution is to disable int64->int32 conversion and fix attributes reading in a lot of ONNX layers parsers (https://github.com/opencv/opencv/issues/25102) - I didn't add type inference and int support to VULCAN, so it doesn't work at all now. - Some layers don't support int yet, so some unknown models may not work. **CURRENT WORKAROUNDS**: - CPU arg_layer indides are implemented in int32 followed by a int32->int64 conversion (the master branch has the same workaround with int32->float conversion) - CPU and OCL pooling_layer indices are implemented in float followed by a float->int64 conversion - CPU gather_layer indices are implemented in int32, so int64 indices are converted to int32 (the master branch has the same workaround with float->int32 conversion) **DISABLED TESTS**: - RAFT model **REMOVED TESTS**: - Greater_input_dtype_int64 (because it doesn't fit ONNX rules, the whole test is just comparing float tensor with int constant) **TODO IN NEXT PULL REQUESTS**: - Add int64 support for ONNX parser - Add int support for more layers - Add int support for OCL (currently int layers just run on CPU) - Add int tests - Add int support for other backends
104 lines
2.7 KiB
C++
104 lines
2.7 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.
|
|
//
|
|
// Copyright (C) 2017, Intel Corporation, all rights reserved.
|
|
// Third party copyrights are property of their respective owners.
|
|
|
|
#include "test_precomp.hpp"
|
|
#include "npy_blob.hpp"
|
|
|
|
namespace cv
|
|
{
|
|
|
|
static std::string getType(const std::string& header)
|
|
{
|
|
std::string field = "'descr':";
|
|
int idx = header.find(field);
|
|
CV_Assert(idx != -1);
|
|
|
|
int from = header.find('\'', idx + field.size()) + 1;
|
|
int to = header.find('\'', from);
|
|
return header.substr(from, to - from);
|
|
}
|
|
|
|
static std::string getFortranOrder(const std::string& header)
|
|
{
|
|
std::string field = "'fortran_order':";
|
|
int idx = header.find(field);
|
|
CV_Assert(idx != -1);
|
|
|
|
int from = header.find_last_of(' ', idx + field.size()) + 1;
|
|
int to = header.find(',', from);
|
|
return header.substr(from, to - from);
|
|
}
|
|
|
|
static std::vector<int> getShape(const std::string& header)
|
|
{
|
|
std::string field = "'shape':";
|
|
int idx = header.find(field);
|
|
CV_Assert(idx != -1);
|
|
|
|
int from = header.find('(', idx + field.size()) + 1;
|
|
int to = header.find(')', from);
|
|
|
|
std::string shapeStr = header.substr(from, to - from);
|
|
if (shapeStr.empty())
|
|
return std::vector<int>(1, 1);
|
|
|
|
// Remove all commas.
|
|
shapeStr.erase(std::remove(shapeStr.begin(), shapeStr.end(), ','),
|
|
shapeStr.end());
|
|
|
|
std::istringstream ss(shapeStr);
|
|
int value;
|
|
|
|
std::vector<int> shape;
|
|
while (ss >> value)
|
|
{
|
|
shape.push_back(value);
|
|
}
|
|
return shape;
|
|
}
|
|
|
|
Mat blobFromNPY(const std::string& path)
|
|
{
|
|
std::ifstream ifs(path.c_str(), std::ios::binary);
|
|
CV_Assert(ifs.is_open());
|
|
|
|
std::string magic(6, '*');
|
|
ifs.read(&magic[0], magic.size());
|
|
CV_Assert(magic == "\x93NUMPY");
|
|
|
|
ifs.ignore(1); // Skip major version byte.
|
|
ifs.ignore(1); // Skip minor version byte.
|
|
|
|
unsigned short headerSize;
|
|
ifs.read((char*)&headerSize, sizeof(headerSize));
|
|
|
|
std::string header(headerSize, '*');
|
|
ifs.read(&header[0], header.size());
|
|
|
|
// Extract data type.
|
|
int matType;
|
|
if (getType(header) == "<f4")
|
|
matType = CV_32F;
|
|
else if (getType(header) == "<i4")
|
|
matType = CV_32S;
|
|
else if (getType(header) == "<i8")
|
|
matType = CV_64S;
|
|
else
|
|
CV_Error(Error::BadDepth, "Unsupported numpy type");
|
|
|
|
CV_Assert(getFortranOrder(header) == "False");
|
|
std::vector<int> shape = getShape(header);
|
|
|
|
Mat blob(shape, matType);
|
|
ifs.read((char*)blob.data, blob.total() * blob.elemSize());
|
|
CV_Assert((size_t)ifs.gcount() == blob.total() * blob.elemSize());
|
|
|
|
return blob;
|
|
}
|
|
|
|
} // namespace cv
|