ARM-software / ComputeLibrary

Watch 226
Star 1.7k
Fork 561

Code
Issues 25
Pull requests
Actions
Projects
Wiki
Security
Insights

Code
Issues
Pull requests
Actions
Projects
Wiki
Security
Insights

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.

Pick a username

Email Address

Password

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

25 Open 792 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

NEFullyConnectedLayer runtime slower than naive implementation Question

#854 opened Aug 5, 2020 by alexjung v20.08

Softmax output mismatch in v20.05 Help wanted

#851 opened Jul 29, 2020 by uu-praveeng v20.08

ACL performance with onnxruntime_perf_test Performance Question

#850 opened Jul 28, 2020 by Dan5002 v20.08

SSD postprocessing layer Help wanted

#849 opened Jul 28, 2020 by krgor v20.08

clang++ does support OpenMP Feature Request

#847 opened Jul 23, 2020 by alexeyr

I compare ComputeLibrary with arch x86_64,how can i run test in pc? Question

#845 opened Jul 21, 2020 by mathpopo

Sgemm optimize on A53 core Question

#843 opened Jul 13, 2020 by yiicy

loading .npy weights into neon_cnn.cpp example Help wanted Question

#840 opened Jul 8, 2020 by GalMoore

OpenCL missing functions Feature Request Question

#838 opened Jul 4, 2020 by NPellet

rounding modes int qasymm8_signed inference Bug Question

#834 opened Jun 19, 2020 by uu-praveeng v20.08

NEConvolution3x3 function output not correct Question

#833 opened Jun 18, 2020 by smiglan v20.08

Image->allocator()->allocate() is too slow for large image Feature Request

#830 opened Jun 13, 2020 by gallex v20.08

Performance on 32bits system with quantized model is very poor Performance Question

#829 opened Jun 11, 2020 by vinceab v20.08

about mali gpu opencl coding skill Question

#828 opened Jun 10, 2020 by bitxsw93 v20.08

Incorrect results in conv layer for particluar input Help wanted

#827 opened Jun 4, 2020 by pranathibl v20.08

is it right that reset the shape in NEGEMM.cpp Question

#823 opened May 25, 2020 by cogbee v20.08

Incorrect results in fc layer when it is preceded by a concat layer in v19.05 Question

#818 opened May 1, 2020 by nhkrishna v20.05

FullyConnected Layer QASYMM8_SIGNED data processing time is more than FP32 Question

#816 opened Apr 28, 2020 by pateldarsh v20.05

ACL on NEON is taking much more time than NCNN Question

#815 opened Apr 12, 2020 by krgor v20.05

huge memory consumption during configure Feature Request Question

#801 opened Feb 4, 2020 by pranathibl

ACL LSTM layer performs 2X slower than OpenMP implementation Performance

#789 opened Jan 9, 2020 by nhkrishna v20.05

NELSTMLayer gives nan values as output Feature Request Help wanted

#779 opened Nov 20, 2019 by nhkrishna v20.05

Not able to convert yolov3 CFG/WEIGHT files to cafffe model files Help wanted

#778 opened Nov 19, 2019 by Prem-compute v20.05

Return error "free(): invalid pointer" when executing NELSTMLayer::validate Help wanted

#768 opened Oct 23, 2019 by alanhsu5678 v20.05

MobileNetV2 - Importing weights from TensorFlow to ACL Help wanted

#748 opened Aug 30, 2019 by yasirmahmoodqureshi v20.05

ProTip! Adding no:label will show everything without a label.