root
/
MNN
mirror of https://github.com/alibaba/MNN.git
1
0
Fork 0
Code Issues Actions 2 Packages Projects Releases Wiki Activity
1,395 Commits 20 Branches 109 Tags 396 MiB
Commit Graph

24 Commits

Author SHA1 Message Date
xiaying ea4f13d3cf [MNN:Sync] Sync Internal 2.7.0 2023-09-04 10:42:11 +08:00
xiaying f26fc2efd8 [MNN:Sync] Sync 2.4.2 2023-04-11 11:12:00 +08:00
xiaying d46b6b998d [MNN:Sync] Sync Internal 2.3.0 2022-12-30 15:18:58 +08:00
Yulv-git 8a43ea2011 Fix some typos in source/. 2022-05-27 23:46:44 +08:00
xiaying 0c718e552b [Sync] Sync internal Gitlab 2022-02-18 11:30:27 +08:00
xiaying 69dba73dc7 [MNN:Sync] Sync internal gitlab 
Main Feature:
1. Add OpenCV API and Numpy API Support
2. Protobuf move into MNN
3. Add more op for torchscript convert
4. Add recompute to speed up geometry compute
5. Add ModuleBasic Test
 2021-11-30 10:10:53 +08:00
xiaying c172010bfd Fix bug for mali sync error 2020-12-31 14:39:08 +08:00
Hui Shu ab711d484c Synchronize internal master to Github 2020-12-15 14:12:35 +08:00
Hui Shu d6795ad031 Github release 1.1.0 2020-11-05 16:49:17 +08:00
rinthel cc9fea13c9 fix vulkan validation errors 
- add image layout barrier after copy-buffer-to-image
- tensor input/output now should set its image layout before dispatching, since output tensors would be input as a next operation
 2020-08-12 15:20:05 +09:00
rinthel 300ef68350 fix image layout-related validation errors 
- VulkanImage now has its image layout
- use `barrierImageIfNeeded()` before `writeImage()` function
 2020-08-11 18:44:19 +09:00
rinthel c9c461a8dd add missing sType 2020-08-11 18:42:32 +09:00
rinthel 919888da92 add flag when creating descriptor pool in order to use vkFreeDescriptorSets 2020-08-11 18:41:23 +09:00
rinthel 3a462e640d align size for buffer mapping and flushing according to device's limits 2020-08-11 18:40:16 +09:00
xiaying a76be60722 [MNN:Sync] Fix compile bug for windows, fix bug for device not support 
fma
 2020-04-14 22:52:24 +08:00
xiaying 1c1ee5b2b3 [PATCH 128/160] [Vulkan:Feature] Support squeeze, expandim 2020-03-22 19:02:12 +08:00
xiaying 86d7732ddc [PATCH 089/160] [Vulkan:Feature] Support Relu / Relu6 with buffer, add matmul 2020-03-22 19:02:08 +08:00
xiaying d96b4d979a [PATCH 077/160] [Vulkan:Refractor] Seperate VulkanTensor 2020-03-22 19:02:07 +08:00
xiaying 091330447c [PATCH 063/160] [Vulkan:Feature] Support precision_high (use fp32) 2020-03-22 19:02:06 +08:00
xiaying 46c11b3128 [PATCH 060/160] [Vulkan:Feature] Support use system lib for vulkan 2020-03-22 19:02:05 +08:00
Zhang 91b5ade49a
Sync. Fix OpenGL related building issues. Build the whole suite on Android CI (#580) 
* Sync code with latest internal version

* Update CMake

* Fix logging issues

* Fix OpenGL Building

* Bump CMakeLists version. Update Podspec

* Update MetalLib Lookup logic

* Fix Windows Build
 2020-01-16 16:55:46 +08:00
Zhang 002ac367e4
Update 2019-12-27 22:16:57 +08:00
liqing 73ad3413cc - dynamic computation graph (beta) 
- add supports (/express)
	- add tests
	- add benchmarks with it (/benchmark/exprModels)
- Python
	- MNN engine and tools were submitted to pip
	- available on Windows/macOS/Linux
- Engine/Converter
	- add supports for each op benchmarking
	- refactor optimizer by separating steps
- CPU
	- add supports for Conv3D, Pool3D, ELU, ReverseSequence
	- fix ArgMax, Permute, Scale, BinaryOp, Slice, SliceTf
- OpenCL
	- add half transform in CPU
	- add broadcast supports for binary
	- optimize Conv2D, Reshape, Eltwise, Gemm, etc.
- OpenGL
	- add sub, real div supports for binary
	- add supports for unary
	- optimize Conv2D, Reshape
- Vulkan
	- add max supports for eltwise
- Metal
	- fix metallib missing problem
- Train/Quantization
	- use express to refactor training codes
 2019-09-26 21:02:07 +08:00
liqing 5551108af8 beta 0.1.0 2019-04-19 20:50:09 +08:00