[FFmpeg-devel] [PATCH 4/4] FATE/dnn: add unit test for dnn depth_to_space layer

[Guo, Yejun]

> -----Original Message-----
> From: Guo, Yejun
> Sent: Thursday, September 05, 2019 2:01 PM
> To: ffmpeg-devel at ffmpeg.org
> Cc: Guo, Yejun <yejun.guo at intel.com>
> Subject: [PATCH 4/4] FATE/dnn: add unit test for dnn depth_to_space layer
> 
> 'make fate-dnn-layer-depth2space' to run the test
> 
> Signed-off-by: Guo, Yejun <yejun.guo at intel.com>
> ---
>  tests/dnn/Makefile                     |   1 +
>  tests/dnn/dnn-layer-depth2space-test.c | 100
> +++++++++++++++++++++++++++++++++
>  tests/fate/dnn.mak                     |   5 ++
>  3 files changed, 106 insertions(+)
>  create mode 100644 tests/dnn/dnn-layer-depth2space-test.c

this patch set ask for review, thanks.

btw, I've finished some more patches locally, the final patch is to
add a generic dnn based rgb processing filter (dnn_rgb_processing),
hope to get feedback earlier and so I can add more general dnn based
filters such as dnn_gray/yuv_processing and dnn_rgb/gray/yuv_analytics
and dnn_rgb/gray/yuv_box_analytics ...

see my new patches at https://github.com/guoyejun/ffmpeg/tree/dnn0919.
and I also copy the oneline log here for your convenient.
d29d02e libavfilter: add a generic filter for rgb proccessing with dnn networks
0ab6ec6 dnn: get the data type of network output from dnn execution result
7c9478d dnn: get the data type of network input from model file
f97d480 dnn: add tf.nn.conv2d support for native model
9cfcd48 libavfilter/dnn: support multiple outputs for native mode
9521a8b libavfilter/dnn/dnn_backend_native: find the input operand according to input name
198eef5 FATE/dnn: add unit test for layer maximum
486722a libavfilter/dnn: add layer maximum for native mode.