nihuini 535f5ed037 fix convolutiondepthwise int8 scale weight saving

2021-05-24 19:00:46 +08:00

..

caffe

fix caffe2ncnn input shape for 1-dim and 2-dim blob

2021-05-06 11:35:17 +08:00

darknet

fix tools/darknet/darknet2ncnn.cpp sign-compare warning (#2396)

2020-12-05 18:25:15 +08:00

keras

Add docs for keras2ncnn tools (#2286)

2020-11-05 15:06:21 +08:00

mlir

copy-pasta makes msvc happy

2021-05-20 19:23:36 +08:00

mxnet

drop fp16 and int8 mode from caffe2ncnn, ncnnoptimize and ncnn2int8 should be used instead

2021-04-26 14:18:57 +08:00

onnx

drop fp16 and int8 mode from caffe2ncnn, ncnnoptimize and ncnn2int8 should be used instead

2021-04-26 14:18:57 +08:00

plugin

fix image URL path (#1255)

2019-09-12 17:47:33 +08:00

pytorch

update link

2020-03-09 21:06:57 +08:00

quantize

generate random weight when null bin passed

2021-05-24 15:54:12 +08:00

tensorflow

mention the community-maintained tensorflow2ncnn tool

2019-11-07 14:30:23 +08:00

CMakeLists.txt

cmake option NCNN_INT8 (#2839)

2021-04-14 12:49:35 +08:00

modelwriter.h

fix convolutiondepthwise int8 scale weight saving

2021-05-24 19:00:46 +08:00

ncnn2mem.cpp

fix float locale issue in ncnn2mem, fix long line parsing in ncnn2int8

2021-04-14 18:59:28 +08:00

ncnnmerge.cpp

removewarn ncnnmerge C4267 (#2269)

2020-11-03 15:05:00 +08:00

ncnnoptimize.cpp

generate random weight when null bin passed

2021-05-24 15:54:12 +08:00