718c41634f
1.项目后端整体迁移至PaddleOCR-NCNN算法，已通过基本的兼容性测试 2.工程改为使用CMake组织，后续为了更好地兼容第三方库，不再提供QMake工程 3.重整权利声明文件，重整代码工程，确保最小化侵权风险 Log: 切换后端至PaddleOCR-NCNN，切换工程为CMake Change-Id: I4d5d2c5d37505a4a24b389b1a4c5d12f17bfa38c
2.1 KiB
Mat structure is now allocator-aware via an extra allocator parameter with default zero value.
The good-old ncnn::fastMalloc()/ncnn::fastFree() will be used for a null allocator.
You could pass a custom allocator to delegate all memory allocation and deallocation.
class Allocator
{
public:
virtual void* fastMalloc(size_t size) = 0;
virtual void fastFree(void* ptr) = 0;
};
ncnn has already implemented two simple pooled Allocator class, with mutex lock or without it.
ncnn::PoolAllocator locked_mempool;
ncnn::UnlockedPoolAllocator unlocked_mempool;
the two allocator types in ncnn
-
blob allocator
used to allocate memory for all named blobs, which you could retrieve by Extractor::extract()
-
workspace allocator
used to allocate memory for internal temporary use in layer implementation, such as the temp blob after padding in convolution
by default, all Extractor instance use the two allocator in the default option You can alter them by ncnn::set_default_option() or you can set them per Extractor by Extractor::set_blob_allocator()/Extractor::set_workspace_allocator()
blob allocator is guaranteed to be called in-order in layer implementation during each Extractor lifecycle while workspace allocator may be called synchronously
the practical usage
-
one network, one-by-one inference
shared unlocked blob allocator for all Extractor
shared locked workspace allocator for all Extractor
-
one network, concurrent inference
shared unlocked blob allocator for all Extractor in each thread
shared locked workspace allocator for all Extractor among all threads
-
concurrent multiple networks, one-by-one inference for each network
shared unlocked blob allocator for all Extractor of each network
shared locked workspace allocator for all Extractor among all networks (for saving memory)
-
concurrent multiple networks, concurrent inference for each network
shared unlocked blob allocator for all Extractor of each network in each thread
shared locked workspace allocator for all Extractor among all networks (for saving memory)