root
/
MNN
mirror of https://github.com/alibaba/MNN.git
1
0
Fork 0
Code Issues Actions 1 Packages Projects Releases Wiki Activity
1,480 Commits 22 Branches 109 Tags 405 MiB
Commit Graph

17 Commits

Author SHA1 Message Date
zhaode.wzd 387775be2a [MNN:Sync] Sync Internal 2.8.0 2023-12-04 11:19:10 +08:00
xiaying 3ff49cbf4a [MNN:Sync] Sync Internal 2.7.2 2023-10-18 10:31:02 +08:00
xiaying ea4f13d3cf [MNN:Sync] Sync Internal 2.7.0 2023-09-04 10:42:11 +08:00
xiaying 68708c5d66 Sync Internal 2.0.4 2022-08-12 10:30:48 +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
tianhang.yth d85952d826 sync from internal repo 2021-04-28 18:02:10 +08:00
xiaying d91fc63976 [MNN:Sync] Sync internal Gitlab 2021-04-08 15:34:23 +08:00
stephenlyu a06df5125b
Add quantization debug tool. (#1317) 
* Add Calibration::dumpTensorScales to dump tensor scales for quantization debug.

* Refactoring analyzeQuantErrors.py to dump dequant output.

* Refactoring analyzeQuantErrors.py.

Co-authored-by: jun.lv <jun.lv@17zuoye.com>
 2021-02-03 10:04:41 +08:00
弗人 7bdbaf167d [PATCH 10/19] [Quantization:Feature] add debug, and bugfix in compute distance 2021-01-08 14:16:24 +08:00
弗人 48c520869c [PATCH 05/19] [Quantization:Feature] add option to set clamp value 2021-01-08 14:16:24 +08:00
弗人 3c4906a715 [PATCH 01/19] [Quantization:Feature] add distance debug info and option to skip quant ops 2021-01-08 14:16:24 +08:00
Zhang 002ac367e4
Update 2019-12-27 22:16:57 +08:00
xiaying 9ad653d0bb [Tools:Bugfix] Fix wrong path of schema head file for quantization tools 2019-10-30 17:31:24 +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 b995b25db9 beta 0.2.0.8 
- add NaN check-up
- add quantification support for ScaleAdd Op
- add binary to eltwise optimization
- add console logs for quantization tool
- better document for quantization tool
- replace redundant dimension flags with dimension format
- optimize performance of TensorFlow Lite Quantized Convolution
- fix axis support for ONNX softmax
- fix get performance compile error on Windows
 2019-08-22 20:13:46 +08:00
liqing f085106da9 release 0.2.0.6 
- fix bugs in quantization
- add evaluating tool for quantization
- add ADMM support in quantization
- fix lock in thread pool
- fix fusing for deconv
- fix reshape converting from ONNX to MNN
- turn off blob size checking by default
 2019-08-07 16:44:09 +08:00
liqing a367406308 beta 0.2.0.3 
- add quantization tool & cpu impl & demo/exec
- add thread pool
- add tests
- fix onnx converter tensor name mismatch
- optimize cpu performance with SSE for windows
 2019-07-11 13:56:52 +08:00