* Update onnx2ncnn.cpp

num_filter for ConvTranspose is wrong (line 1075), should be the same sa Conv, which reads the number of filters from dim(0) (line 998)
int num_filter = W.dims(0);

* Update onnx2ncnn.cpp

* [CHG]when use HybridBlock to call F.softmax,the softmax op name is "softmax"(mxnet_version:10301)

* [CHG]Remove type mismatch error when using static code detection tool

* add the armv7a conv3x3s1 implement without overflow,remove old codes

* fix the bug of conv3x3s2 packed int8

* new int8 implement,weight quant by perchanel,better accuracy~

* fix the bug of conv3x3s1 packed int8 neon

* add the naive c fp32 and int8 winograd F(2,3)

* add the neon intrinsic int8 winograd F(2,3)

* optimize the armv7a int8 winograd F(2,3) with neon assembly

* optimize the armv7a int8 winograd F(2,3) input transform with assembly.

* add the requantize layer and int8 relu implement.

* add graph optimize conv1x1s2 -> conv1x1s1,begin optimize int8 aarch64.

* fix int8 bugs

* add the c naive im2col with sgemm

* add aarch64 int8 winograd f23, conv3x3s2 naive implement

* add the int8 sgemm conv7x7s2 on x86/armv7a platform

* optimize the int8 sgemm by neon intrinsic and packed kernel

* optimize the int8 sgemm with packed data

* optimize the int8 sgemm with armv7a neon assembly

* add the int8 sgemm on arm64-v8a platform

* perpare to merge latest codes from master

* add the int8 param files

* In the Class Net,add the fuse_network method

* vulkan infrastructure

* vkallocator and vkmat

* layer interface for vulkan compute

* wip...

* default vulkan device, command wrapper, upload model weight in load_model to simplify layer interface

* simplify command api, vkmat holds staging buffer, relu works

* initialize specialization constant, simplify command dispatch, fix staging buffer copy with different shape, convolution works

* init extension functions

* dynamic local size and group count

* group count=1 is invalid

* regard device max workgroup size limit

* fix relu oooops

* decouple command record and staging allocation

* create result blob

* add pooling shader

* buffer is faster than image :)

* fix pooling shader

* add innerproduct shader

* readonly writeonly decoration

* simplify buffer creation

* decouple command and layer, VK_KHR_descriptor_update_template extension makes descriptor binding update easy :D

* fix vulkan building issues in visual studio (#1)

* fix building issues on visual studio

* ignore benchmark

* cancel changes

* ... ...

* decouple paramdict and vulkandevice

* fix staging buffer destroy in model loading

* remove vkdev member in option

* add padding shader

* simplify vulkan layer creation, simplify convolution and pooling shader for no padding, less debug output

* add convolutiondepthwise and softmax shader

* specialization float type, add leakyrelu

* add dropout shader

* add batchnorm shader

* split vulkan forward

* add scale shader

* push constant type can be int or float

* set_optimal_local_size_xyz

* add eltwise shader

* concat vulkan forward

* fix convolution without bias

* add dummy shader for concat and split, more fix ...

* optional VK_KHR_descriptor_update_template and VK_KHR_push_descriptor

* check VK_KHR_push_descriptor for vkCmdPushDescriptorSetWithTemplateKHR

* binaryop and unaryop shader

* hide raw command buffer

* simple vkbenchncnn benchmark

* create device with transfer queue

* rename command to vkcompute, add vktransfer and layer upload_model interface

* external VkMat, copy and map wrt buffer offset

* command copy respect offset and size

* decouple weight upload and load, simplify upload weight api, use one big staging buffer for uploading weights

* fix build on android

* binding count can not vary :(

* barrier check state, fix sub-op destruction

* declare local_size_xyz constant, fix crash on radv

* fix local_size_xyz, second try

* more barrier and state fix

* fix softmax

* reconstruct buffer memory allocator, reuse blob buffer, less verbose output

* find unified memory type index

* weight staging buffer allocator and weight buffer allocator, respect descriptor buffer offset alignment

* use VK_KHR_descriptor_update_template for faster descriptor update if available, multithread pipeline creation

* find more useful vulkan extensions and enable them

* fix msvc build

* respect VK_KHR_dedicated_allocation for weight buffer allocation

* fix android build

* fix bias name conflicts with metal

* decouple pipeline and layer, building shader sources into shader module, dedicated create_pipeline api, simplify pipeline recording

* drop dummy shader, inplace softmax, multiple shader module works

* fix unique queue family index error

* flatten support vulkan

* mnasnet run

* find shader module by name, each entry point per shader module, fix attribute/id conflict on moltenvk

* some minor changes

* add some high level api

* use dedicated transfer queue to upload weight model

* prefer mappable buffer on unified memory

* global pooling and convolution fc, reuse staging buffer

* implement ring-buffer style blob allocator, add VkBufferMemory capacity

* use blob allocator for workspace blob, it works fine :)

* vulkan option off

* Update layer.cpp

* fix build with vulkan off

* less verbose output, fix crash on vulkan_compute off

* merge benchncnn tool

* allocator clear api, use new weight buffer allocator per net

* add default locked allocator

* mapped mat ptr api, persistent mapped memory works generally :)

* travis ci linux vulkan

* travis ci vulkan wip ...

* more gpu wip ...

* more gpu wip ...

* wip...

* wip...

* wip... ...

* wip... ios vulkan build...

* find glslangValidator on ios build

* use dynamic moltenvk library

* travis ci wip ...

* ios simulator does not support metal at all

* fix cpu only extractor

* optimize workgroup size, first try

* optimize workgroup size, second try

* conv1x1s1d1 vec4

* revert build system

* fix ncnn2mem build

* fix ncnn2mem build

fix: increase min cmake version

fix also cmake usage in tools/