[E-103104] - Port gaze_estimation_demo gapi demo to OV API2.0 #3891
Conversation
demos/tests/cases.py
Outdated
| TestCase(options={'-no_show': None, | ||
| **MONITORS, | ||
| '-i': TestDataArg('coco128/images/train2017/')}), | ||
| '-i': DataPatternArg('coco128-every-480x640x3')}), |
There was a problem hiding this comment.
This case is closer to the video input (since the frame size does not change)
There was a problem hiding this comment.
For some reason there are issues with reading video input in github actions: https://github.com/openvinotoolkit/open_model_zoo/actions/runs/7408585487/job/20157102210?pr=3887
Working on it.
There was a problem hiding this comment.
You may check OpenCV cmake flags. I heavily reduced build time by disabling modules
There was a problem hiding this comment.
I see, will check them. Thanks!
There was a problem hiding this comment.
Done, thanks!
DariaMityagina
force-pushed
the
icv/dm/gaze-est-demo-gapi
branch
from
7653574 to
7f34a19
Compare
| } | ||
| COCO128_URL = "https://ultralytics.com/assets/coco128.zip" | ||
|
|
||
| VIDEO_URL = "https://storage.openvinotoolkit.org/data/test_data/videos/head-pose-face-detection-male.mp4" |
There was a problem hiding this comment.
This is the same video used in the gaze_estimation_demo readme file (here)
.github/workflows/cpp_gapi-demos.yml
Outdated
| sudo apt install pkg-config | ||
| sudo apt install ffmpeg libavcodec-dev libavformat-dev libavutil-dev libswscale-dev libavresample-dev |
There was a problem hiding this comment.
Required for -DWITH_FFMPEG=y.
There was a problem hiding this comment.
This does not affect OpenCV build time.
| single_option_cases( | ||
| '-i', | ||
| str('/tmp/video.mp4'), | ||
| DataPatternArg('coco128-every-480x640x3')), |
There was a problem hiding this comment.
Both options:
- video input
- folder with images as input
|
@Wovchena hi! Could you please review this PR? |
|
gapi demos are passing |
DariaMityagina
force-pushed
the
icv/dm/gaze-est-demo-gapi
branch
from
d4b02f2 to
75d371d
Compare
DariaMityagina
force-pushed
the
icv/dm/gaze-est-demo-gapi
branch
from
75d371d to
80d52b0
Compare
|
Thanks a lot @Wovchena @DariaMityagina ! |
3 participants
Tiket:
103104
Description:
G-API Background Subtraction Demo, Classification Benchmark C++ G-API Demo, G-API Gaze Estimation Demo and other - fail on NPU with the following error:
dynamic shape issuesOpenVINO is actively removing API 1.0 from their code
Both G-API framework and G-API demos use API 1.0 --> which leads to disruption of certain functionality
Conclusion: We need to port the G-API demos to API2.0 to make them work.
gaze_estimation_demo
OK: Fixed on NPU. Works with a single image and with a video input.
FAIL: But still has issues in case folder with images is provided (in CI) - WIP
Failed to copy data from cv::Mat to ov::Tensor. Data type or number of elements mismatch. ov::Tensor: u8 [1,490,1183,3] and cv::Mat: 8UC3 1180x490It seems to fail if the input folder contains images of different sizes. It works fine with the first image from the folder and does not work with the second (if it is a different size).