Comments (4)
By the way, If i only want to compile example_cldnn.cpp (in tutorial folder), how to compile it? gcc example_cldnn.cpp -o example_cldnn ?
When i see the code of example_cldnn.cpp, I find that i don't have the files, conv1_weights.bin, fc1_weights.data..etc, how to get this files?
Thank you very much
from cldnn.
Hi Jia-HongHenryLee,
We didn't have your device id in our list of supported HW's. I've added it already. Thanks for pointing it out.
Regarding to your second question: you have to prepare your own files with data and pare it to cldnn format.
from cldnn.
Hi tponieck,
What conv1_weights.bin and fc1_weights.data is ? How can i prepare for it?
from cldnn.
You need to fill memory primitive with data based on weights layout i.e.:
layout conv1_weights_layout(data_type, format::bfyx,{ conv1_out_channels, input_channels, conv_krnl_size, conv_krnl_size });
bfyx means order will be:
output featre map - input feature map - height (spatial y) - width (spatial x)
data should be float precision
to get better understanding I recommend to follow test case: basic_ofm_wsiz3x2x2x1_in2x2x1_nopad from: https://github.com/intel/clDNN/blob/master/tests/test_cases/convolution_gpu_test.cpp
from cldnn.
Related Issues (20)
- corei7 8750H support? HOT 5
- Errors in GPU device IDs HOT 1
- Drop 12.0 does not work with OpenVINO R4 HOT 1
- clDNNPlugin R5 cannot be built with clDNN Drop 12.1 without graphics driver installed HOT 3
- Building on ClearLinux Fails HOT 3
- Fail to build with MINGW64 compiler within MSYS2 environment HOT 1
- System error HOT 1
- clDNN makes [bad] assumptions about c++ runtime
- use CMAKE_BINARY_DIR appropriately
- make tag for release
- How to set the size of weights memory when convolution‘s groups is not equal to 1. HOT 1
- ONNXIFI wrapper
- Is there any case to verify depthwise convolution in CLDNN?
- Is there any case to verify depthwise convolution in CLDNN?
- Missing include HOT 1
- Value stored to 'input_block_array_size' during its initialization is never read
- Function 'is_power_of_two()', which defined in an anonymous namespace, is never used
- Can I use it in Upboard or upcore chip
- Could clDNN be compiled for armv7l ?
- How can I benchmark, say a GEMM, in clDNN
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from cldnn.