 nihui
|
eceac35a7f
|
implement MultiheadAttention kdim vdim (#4347)
|
2022-11-14 12:46:51 +08:00 |
|
|
Lry89757
|
6a47f8d15c
|
gridsample op support (#4288)
Co-authored-by: LRY89757 <LRY89757@users.noreply.github.com>
Co-authored-by: nihuini <nihuini@tencent.com>
Co-authored-by: nihui <shuizhuyuanluo@126.com>
|
2022-11-11 20:55:57 +08:00 |
|
|
Fangjun Kuang
|
5281d51535
|
implement GLU and pnnx conversion (#4283)
|
2022-10-19 12:41:23 +08:00 |
|
|
nihui
|
77eda4c19f
|
implement lstm proj_size (#4263)
|
2022-10-14 10:54:03 +08:00 |
|
|
miemie2013
|
720f3c9aab
|
Add DeformableConv2D (#4070)
* Add DeformableConv2D
* add unittest and docs
* pnnx torchvision deformconv2d conversion
Co-authored-by: miemie2013 <miemie2013@users.noreply.github.com>
Co-authored-by: nihui <shuizhuyuanluo@126.com>
|
2022-07-28 11:45:09 +08:00 |
|
|
Zhouzhou
|
4158e63668
|
docs：add sse optimized zh (#4053)
Signed-off-by: Zhouzhou <1197236910@qq.com>
|
2022-07-25 16:24:44 +08:00 |
|
|
Lry89757
|
ca9abd1c4a
|
Update the add-custom-layer.zh.md (#3741)
1. 🐛Fix Bug of float and int. 修复了std::max()中参数int和float参数不符合的Bug
2. 👀 The structure of ncnn changes. ncnn文件结构变动,所有testlayer.cpp改成在tests/文件夹中
|
2022-04-27 15:02:10 +08:00 |
|
|
nihui
|
2880eff264
|
deconv1d deconv3d (#3584)
* fix sigmoid returns nan with very large input
|
2022-03-01 21:50:17 +08:00 |
|
|
nihuini
|
bc188ece58
|
update modelwriter for new operators
|
2022-02-25 11:27:01 +08:00 |
|
|
nihui
|
c5d7f963b9
|
layer tile (#3491)
|
2022-01-10 15:05:07 +08:00 |
|
|
nihuini
|
014387dfae
|
update operators doc
|
2021-12-31 17:47:23 +08:00 |
|
|
nihui
|
3a83704c38
|
binary4d, unary4d (#3443)
|
2021-12-28 23:13:44 +08:00 |
|
|
FeiGeChuanShu
|
0dea7a04a8
|
fix typo in doc (#3436)
|
2021-12-20 17:20:21 +08:00 |
|
|
nihuini
|
e8d1d40398
|
update operators doc
|
2021-12-07 11:10:22 +08:00 |
|
|
nihui
|
f10cc6dd93
|
initial data structure changes for 3dcnn, conv3d, pooling3d (#3378)
Co-authored-by: ElvisYu <elvisyuovo@gmail.com>
Co-authored-by: 余浩文 <m18107220188@163.com>
Co-authored-by: Zr2223 <67497651+Zr2223@users.noreply.github.com>
|
2021-12-02 16:50:55 +08:00 |
|
|
huoshuai-dot
|
d8665b3687
|
Update how-to-implement-custom-layer-step-by-step.md (#3348)
|
2021-11-15 17:18:52 +08:00 |
|
|
空言
|
dbf2db26fe
|
Update operators.md (#3345)
change weight type
|
2021-11-14 14:30:07 +08:00 |
|
|
nihui
|
52721dd1eb
|
Update operators.md
|
2021-09-22 11:15:25 +08:00 |
|
|
nihui
|
0902594334
|
Update operators.md
|
2021-09-22 10:35:01 +08:00 |
|
|
nihui
|
a74c64df78
|
Update operators.md
|
2021-09-15 17:11:33 +08:00 |
|
|
Tijmen Verhulsdonck
|
eaa7e24db6
|
Added ability to switch AVX/AVX2 during runtime (#3076)
|
2021-07-14 20:28:15 +08:00 |
|
|
nihui
|
4f135e07bf
|
implement convolution1d and pooling1d (#3035)
* implement convolution1d and pooling1d
* add conv1d pool1d test
* fuse convolution1d activation
* update operator doc
* fix vulkan adpative pooling
|
2021-06-30 20:19:19 +08:00 |
|
|
nihui
|
01be0ee226
|
update operators.md
|
2021-06-09 12:52:43 +08:00 |
|
|
nihuini
|
e19c7dbb39
|
update operators.md
|
2021-06-08 19:26:16 +08:00 |
|
|
nihuini
|
2129ed8cc3
|
update operators.md
|
2021-06-08 17:05:00 +08:00 |
|
|
nihuini
|
cc8332107c
|
update operators.md
|
2021-06-08 15:44:36 +08:00 |
|
|
nihui
|
66455c1b95
|
implement 2823 binary broadcasting type (#2827)
|
2021-04-13 22:20:10 +08:00 |
|
|
teng
|
cc8e7a13fa
|
Update operation-param-weight-table (#2811)
|
2021-04-02 22:27:05 +08:00 |
|
|
Zhuo Zhang
|
d20bf380f7
|
fix typos in docs (#2639)
* fix typos in docs
* still fix some typos in docs
|
2021-01-29 15:59:26 +08:00 |
|
|
nihuini
|
4534195897
|
update low-level op api doc
|
2021-01-27 15:54:47 +08:00 |
|
|
Zhuo Zhang
|
1ff623b0fe
|
doc: supplementary explanation for how to commit (#2626)
|
2021-01-26 21:47:48 +08:00 |
|
|
tpoisonooo
|
4dbef4535d
|
docs(develop-guide): add second pr (#2589)
|
2021-01-14 11:48:03 +08:00 |
|
|
Qing
|
8a1f654f95
|
add pooling operator doc (#2591)
Co-authored-by: wq.chu <wq.chu@tianrang-inc.com>
|
2021-01-12 15:09:21 +08:00 |
|
|
Qing
|
d3a30437b8
|
Update operation-param-weight-table.md (#2590)
|
2021-01-12 14:43:07 +08:00 |
|
|
tpoisonooo
|
6dcf86b0e6
|
Add pr doc (#2571)
|
2021-01-11 11:47:35 +08:00 |
|
|
cavalleria
|
e6928dd7f1
|
add convolutiondepthwise/crop/sigmoid/tanh in operators.md (#2484)
* add convolutiondepthwise/crop/sigmoid/tanh in operators.md
* sort by alphabet
* delete impl_type
* cannot delete impl_type
* cannot delete impl_type
Co-authored-by: yaobin.li <yaobin.li@rokid.com>
|
2020-12-22 19:05:33 +08:00 |
|
|
xingxingRealzyx
|
74d1193eb9
|
update operators.md, add cast (#2430)
|
2020-12-11 12:44:13 +08:00 |
|
|
xingxingRealzyx
|
6e5d819826
|
update operators.md, add binaryop (#2359)
* update operators.md, add binaryop/Operation type
* fix with_scalar
* Update operators.md
* Update operators.md
|
2020-11-28 21:04:36 +08:00 |
|
|
LosReturn
|
327ac301d3
|
update operators.md, add bnll op (#2360)
|
2020-11-27 15:44:31 +08:00 |
|
|
Leighton Choi
|
6f49529da2
|
Fix markdown format (#2347)
|
2020-11-24 17:00:23 +08:00 |
|
|
Leighton Choi
|
2ef07413b7
|
Add LSTM and softmax to operators.md (#2346)
* Add LSTM and softmax to operators.md
* Fix lowercase and support_inplace
|
2020-11-24 15:53:31 +08:00 |
|
|
LosReturn
|
98bf3f4dc5
|
update operators.md, add dequantize (#2341)
|
2020-11-24 09:32:16 +08:00 |
|
|
xingxingRealzyx
|
8d8eb6a133
|
update operators.md,add argmax and bias (#2337)
|
2020-11-21 07:29:21 +08:00 |
|
|
Hollow Man
|
37cfc373cb
|
Fix typo (#2338)
prvious -> previous
|
2020-11-21 07:27:19 +08:00 |
|
|
nihui
|
4cc5197b94
|
Doc operators (#2310)
|
2020-11-13 11:03:45 +08:00 |
|
|
ncnnnnn
|
697767b062
|
Update add-custom-layer.zh.md (#2164)
|
2020-10-09 17:03:08 +08:00 |
|
|
Zhuo Zhang
|
8d984f105b
|
update readme: metion yolact, retinaface, etc (#1916)
* update readme: metion yolact, retinaface, etc
* update doc: add c/cpp/python for code region
|
2020-07-06 00:05:04 +08:00 |
|
|
nihui
|
83f433aee2
|
update operation-param-weight-table
|
2020-06-14 11:11:55 +08:00 |
|
|
nihuini
|
ab7fa0c48a
|
fix staging download
|
2020-05-07 10:51:53 +08:00 |
|
|
nihui
|
62da1228e1
|
adreno image shader + fp16 + fp16a (#1714)
* wip
* wip
* fix
* image and imageview can not be destroyed until command execution ends
* fast copy path for tightly packed data
* wip
* texture load works
* 1d 3d image
* record clone image, multiple commands share one image reference
* upload download image
* layer forward accept vkimagemat
* vkimagemat graph works
* staging vkimagemat for passing dynamic parameters, macro for fp32+image shader, padding image shader
* vkimagemat elemsize
* convolution test pass
* conv1x1s1 image shader
* fast staging image allocator from host memory, pooling image shader
* convolutiondepthwise image shader
* innerproduct image shader
* packing image shader
* crop deconvolution image shader
* resolve spirv binding types
* image fp16 and fp16a, cast image shader
* eltwise image shader
* wip
* absval image shader
* deconvolutiondepthwise image shader
* concat image shader, squeezenet works
* noop split image shader
* uniform precision hint
* layer support_image_storage
* wip
* vulkan device utility operator
* command is storage and packing option aware
* fallback to cpu on image allocation failed, mobilenetssd works
* flatten image shader, enable more test
* ci test
* check imgfp32 imgfp16 imgfp16a features
* fix ci test
* fix ci test
* upgrade swiftshader
* wip
* opt aggressive
* imgfp16p
* opt none
* convolution winograd image shader
* fix flush range, fast copy path for continous buffer
* minor fix
* fix innerproduct
* wip ...
* wip
* cast fix
* packing test
* wip
* image fp16p is fp16p
* wip
* silence
* more line info
* code clean
* softmax image shader
|
2020-04-30 17:08:30 +08:00 |
|