 Evgeny Proydakov
|
4699b26933
|
Using snprintf instead of sprintf for a tools (#6554)
Signed-off-by: Evgeny Proydakov <e.proydakov@gmail.com>
|
2026-02-26 10:29:28 +08:00 |
|
|
nihui
|
171b9d1bba
|
use spdx license header, copyright Tencent (#6152)
|
2025-07-08 11:01:29 +08:00 |
|
|
li mengyang
|
ff4d05a713
|
fix typo (#4482)
|
2023-01-20 12:27:50 +08:00 |
|
|
nihui
|
3181616439
|
treat old reduction axes param as failure
|
2022-02-06 21:20:54 +08:00 |
|
|
nihuini
|
f02b259a15
|
convert some pnnx reduction family
|
2021-12-23 16:19:25 +08:00 |
|
|
Jimmy
|
52c6502ae7
|
Feature/ncnntool/add install (#3212)
|
2021-09-10 14:08:10 +08:00 |
|
|
nihuini
|
00b0094b2f
|
copy-pasta makes msvc happy
|
2021-05-20 19:23:36 +08:00 |
|
|
nihuini
|
26dc9820e4
|
custom mlir ncnn optimize pass, add efficientnetv2_b0 benchmark
|
2021-05-19 16:34:18 +08:00 |
|
|
nihuini
|
b7959a4fc7
|
fuse mlir swish and conv-addv2
|
2021-05-19 11:24:11 +08:00 |
|
|
nihuini
|
f9e42d4ee4
|
drop fp16 and int8 mode from caffe2ncnn, ncnnoptimize and ncnn2int8 should be used instead
|
2021-04-26 14:18:57 +08:00 |
|
|
nihuini
|
e449435dbe
|
fix mlir2ncnn warning, prettier alignment :)
|
2021-03-05 16:33:29 +08:00 |
|
|
nihuini
|
c8ccccf045
|
adapt mlir changes
|
2021-03-05 16:21:25 +08:00 |
|
|
daquexian
|
f684dc236b
|
allow set llvm/mlir dirs from cli (#2624)
|
2021-01-26 21:56:14 +08:00 |
|
|
nihuini
|
6550a517ef
|
adapt mlir api changes, update tf dialect
|
2021-01-25 20:04:52 +08:00 |
|
|
nihuini
|
fbf0ffda53
|
pixelshuffle nhwc mode, convert onnx DepthToSpace mode DCR, convert mlir tf.DepthToSpace
|
2020-12-29 19:47:53 +08:00 |
|
|
nihuini
|
aa695831f1
|
rewrite most mlir2ncnn node_reference and binary weight logic, convert tf.SpaceToDepth
|
2020-12-29 11:45:26 +08:00 |
|
|
nihuini
|
cc773ec8e5
|
adapt mlir api changes
|
2020-12-23 17:39:48 +08:00 |
|
|
nihuini
|
5d40a42e2f
|
shorter blob name
|
2020-12-22 19:34:49 +08:00 |
|
|
nihuini
|
b3bbc1b8e9
|
update tensorflow dialect, adpat mlir api changes
|
2020-11-09 15:14:18 +08:00 |
|
|
nihuini
|
a742979fea
|
do not fuse mlir scalar mul-add pattern
|
2020-10-30 11:23:10 +08:00 |
|
|
nihuini
|
0a533dcaac
|
mlir2ncnn fuse keras batchnorm, handle instancenorm affine in ncnnoptimize
|
2020-10-26 16:11:55 +08:00 |
|
|
nihuini
|
245e31ebca
|
adapt mlir api changes
|
2020-10-16 10:26:57 +08:00 |
|
|
nihuini
|
7b5b829143
|
adapt mlir api changes
|
2020-09-24 14:02:51 +08:00 |
|
|
nihuini
|
cd7f59d25b
|
adapt mlir dialect registration changes
|
2020-09-07 12:52:28 +08:00 |
|
|
nihuini
|
63247a32a7
|
mlir fix keras conv2d dense bias, fix pooling type
|
2020-08-31 16:43:49 +08:00 |
|
|
nihuini
|
6a15cb1a0e
|
mlir fuse keras conv2d dense
|
2020-08-27 16:35:16 +08:00 |
|
|
nihuini
|
d279e1f514
|
mlir fuse instancenorm without affine
|
2020-08-27 15:21:54 +08:00 |
|
|
nihuini
|
78580dc648
|
sync tf dialect, mlir fuse instancenorm
|
2020-08-26 17:31:29 +08:00 |
|
|
nihuini
|
7b3ab5024d
|
convert to gemm layer
|
2020-08-18 10:57:41 +08:00 |
|
|
nihuini
|
4b470949c2
|
update tf2 dialect, adapt new mlir api, convert tf.Maximum tf.Minimum tf.ResizeBilinear
|
2020-08-14 19:34:44 +08:00 |
|
|
nihui
|
02e880fc42
|
fix concatv2 axis
|
2020-07-11 13:28:46 +08:00 |
|
|
nihuini
|
00ef566609
|
implement full permute tag support for reshape
|
2020-07-08 20:06:45 +08:00 |
|
|
nihuini
|
b2b86fea16
|
convert tf.ResizeNearestNeighbor
|
2020-07-08 15:05:00 +08:00 |
|
|
nihui
|
afb09cccbb
|
build mlir2ncnn with latest mlir with updated tf2 dialect (#1925)
|
2020-07-07 19:44:20 +08:00 |
|
|
nihui
|
46c6f3a4a2
|
hmmm, mlir need c++14 anyway
|
2020-07-07 11:21:46 +08:00 |
|
|
nihui
|
cfcee2298d
|
mlir2ncnn requires c+11
|
2020-07-07 11:01:34 +08:00 |
|
|
nihui
|
6e340f5e79
|
MLIR converter (#1810)
* tf2sb
* wip
* wip
* concat maxpool avgpool
* StridedSlice
* handle stridedslice mask
* convert mlir deconvolution
* convert deconvolution output shape
* convert tanh
* code format
|
2020-07-02 14:15:28 +08:00 |
|