This repository has been archived by the owner on Dec 1, 2021. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 86
Added image reading function for runtime #577
Merged
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- command line: cmake => cmake . - sample path: /home/.../git/ => <repost_dir>
(mainly from tkng/emscripten branch.) - FormatYoloV2, NMS, - softmax, sigmoid, CalcIoU - ConvertBboxCoordinate, PerImageStandardization - etc. required Tensor functions.
TODO: copyright (all files)
(little modified examples/run.cpp, fitting to 80-chara width)
TODO: Missing username in TODO
…ries(opencv, libpng) installation situation. But, image readers(png,npy) not implemented yet.
delete randomImage (debug function)
replace it to GLOB & REMOVE_ITEM. for Cmake 3.5
- add npy, data_processor - del opencv. (require cmake option -DUSE_OPENCV=ON)
previously, display flatten array. non human readable.
fix: comment space, include functional
tkng
reviewed
Nov 22, 2019
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Could you remove the binary file runtime/examples/dlk_lib/libdlk_x86.a
?
tkng
reviewed
Nov 22, 2019
Other than the small comments above, LGTM. |
add import dlk library procedure text to README.md
No longer represents imagedata, just data.
tkng
reviewed
Nov 26, 2019
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for your contribution, other than commented points, looks good to me.
- for (a ; b ;c) => for (a; b; c)
- change example executable name. a.out => run - modify bad style of parenthesis.
tkng
approved these changes
Nov 26, 2019
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for your contribution! I'll merge the PR after unit test passed.
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Added image reading function for runtime.
Motivation and Context
In the runtime examples run.cpp,
I want to read the actual image, not the dummy random image.
Description
Added image reading function for runtime.
Tensor Tensor_loadImage(std::string filename);
We can load images in npy format even if neither link external image library.
When linking libpng, PNG can be read.
If you link opencv, you can read the format that opencv can read.
How has this been tested?
$ cd blueoil/output_template/python $ python run.py -m lib_x86.so -c meta.yaml -i raw_image.png Output: (before post process) [[1.0594523e-04 6.2350206e-05 3.2353133e-02 3.6062470e-03 1.2402927e-02 2.3177502e-04 9.5100403e-01 8.7061970e-05 9.8417870e-05 4.8058930e-05]] Output: [[1.0594523e-04 6.2350206e-05 3.2353133e-02 3.6062470e-03 1.2402927e-02 2.3177502e-04 9.5100403e-01 8.7061970e-05 9.8417870e-05 4.8058930e-05]] save json: output/output.json save image: output/images/raw_image.png
Screenshots (if appropriate):
Types of changes
Checklist: