Skip to content

/ ncnn

Pinned issues

后续是否会支持将 tensorflow pb模型转为ncnn的模型呢?
#5 opened Jul 24, 2017 by dangbo
Open 29
Android的JNI开发，使用两个基于ncnn的本地库时，运行出现 Fatal signal 6 (SIGABRT)错误
#976 opened May 5, 2019 by DolbyYu
Open 15
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

212 Open 1,230 Closed
212 Open 1,230 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels.
Projects
Filter by project
Milestones
Filter by milestone
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀
quantized int8 iference with opt.use_packing_layout does not work on aarch64
#1837 opened Jun 11, 2020 by iivanich
rk3288上面绑定不了大核
#1832 opened Jun 10, 2020 by xulingling516
5
rk3288 上相同计算量的shufflenet跑的比mobilenet快，有办法优化mobilenet或者加速rk3288上面跑的速度吗？比如优化指令啥的？
#1830 opened Jun 10, 2020 by xulingling516
3
enforce code style enhancement
#1829 opened Jun 9, 2020 by nihui
Vulkan convolution wrong output with shape hint bug
#1828 opened Jun 9, 2020 by zhiliu6
1
reshape层似乎有bug
#1827 opened Jun 9, 2020 by perfyperfect
使用darknet2ncnn 转化yolov-lite模型后，在安卓平台上进行调用，无法正常加载模型
#1824 opened Jun 8, 2020 by lhxy1991
未经过x86的优化代码无法准确的预测出结果 bug
#1819 opened Jun 6, 2020 by Hank0223
1
i get negative softmax outputs and higher than 1 values !!
#1817 opened Jun 5, 2020 by abdinf
convolutional layer ctests VULKAN version fails on OSX
#1816 opened Jun 5, 2020 by Timen
2
使用ncnnoptimize量化yolov3和tiny-yolov3报layer DarknetActivation not exists or registered，Segmentation fault，是什么问题呢，参考https://blog.csdn.net/liuwei36120516/article/details/105675956，为什么人家就一步对，我感觉我有毒
#1815 opened Jun 5, 2020 by 2017ZYS
预编译的库ncnn-vulkan.framework有问题，直接ld: Framework not found ncnn-vulkan
#1814 opened Jun 4, 2020 by chenminghong
5
模型量化後比量化前速度還要慢
#1813 opened Jun 4, 2020 by Hank0223
3
训练完的yolov3网络不能识别extract方法返回-1
#1812 opened Jun 4, 2020 by tomchen008
test_convolution fails on ARM gnueabihf bug
#1811 opened Jun 3, 2020 by saseptim
ncnn自己的分割能跑通benchmark，但无法跑通实测
#1809 opened Jun 3, 2020 by makaaay
3
Slice layer output empty
#1804 opened Jun 1, 2020 by hoanganhpham1006
2
使用darknet2ncnn 转化yolov3-tiny模型后，在安卓平台上进行调用，真机测试可以运行，但是没有输出结果
#1800 opened May 31, 2020 by skybocai
3
为什么用 onnx 导出的 softmax 层会被分解成多个层，而不是单个 softmax 层
#1795 opened May 29, 2020 by ItchyHiker
1
find_blob_index_by_name splitncnn_4 failed
#1794 opened May 28, 2020 by Ghul-huan
2
[Resolved] Large accuracy and performance difference between x86-64 and ARM architecture when using quantized model
#1793 opened May 28, 2020 by Mirito28
1
ncnn模型在Android端跑压力测试时出现signal 11 (SIGSEGV), code 1 (SEGV_MAPERR)导致应用崩溃退出
#1791 opened May 27, 2020 by bestpower
8
Segmentation fault: 11 when converting onnx
#1790 opened May 26, 2020 by GHLab
Android Posenet Inference at 300ms. Faster speeds suggestions
#1786 opened May 21, 2020 by minenkod
带lstm的crnn模型是不支持int8量化吗
#1784 opened May 21, 2020 by zqnnn
ProTip! Mix and match filters to narrow down what you’re looking for.
You can’t perform that action at this time.