All of lore.kernel.org
 help / color / mirror / Atom feed
From: Denys Dmytriyenko <denys@ti.com>
To: "Gou, Hongmei" <h-gou@ti.com>
Cc: "meta-arago@arago-project.org" <meta-arago@arago-project.org>
Subject: Re: [zeus/master] [PATCH 2/3] tensorflow-lite-demo: add version 01.00.00
Date: Fri, 28 Feb 2020 12:25:26 -0500	[thread overview]
Message-ID: <20200228172526.GH2466@beryl> (raw)
In-Reply-To: <92987f994a9c49c5ae44a75c80dad390@ti.com>

On Fri, Feb 28, 2020 at 12:22:36PM -0500, Gou, Hongmei wrote:
> > -----Original Message-----
> > From: Dmytriyenko, Denys
> > Sent: Friday, February 28, 2020 12:12 PM
> > To: Gou, Hongmei
> > Cc: meta-arago@arago-project.org
> > Subject: Re: [meta-arago] [zeus/master] [PATCH 2/3] tensorflow-lite-demo:
> > add version 01.00.00
> > 
> > On Fri, Feb 28, 2020 at 12:00:46PM -0500, Gou, Hongmei wrote:
> > > > -----Original Message-----
> > > > From: Dmytriyenko, Denys
> > > > Sent: Thursday, February 27, 2020 6:15 PM
> > > > To: Gou, Hongmei
> > > > Cc: meta-arago@arago-project.org
> > > > Subject: Re: [meta-arago] [zeus/master] [PATCH 2/3] tensorflow-lite-
> > demo:
> > > > add version 01.00.00
> > > >
> > > > On Tue, Feb 25, 2020 at 06:12:25PM -0500, Hongmei Gou wrote:
> > > > > * This supports classification and segmentation demos with tensorflow
> > lite
> > > > models
> > > > >   running on Arm. It demonstrates the whole pipeline from
> > > > image/video/camera input,
> > > > >   to tensorflow lite inference, to display the classification/segemenation
> > > > results.
> > > > >
> > > > > * OpenCV is used for capturing the input and displaying the results.
> > > > >
> > > > > Signed-off-by: Hongmei Gou <a0271529@ti.com>
> > > > > ---
> > > > >  .../files/run_classification.sh               |  7 +++
> > > > >  .../tensorflow-lite/files/run_segmentation.sh |  8 +++
> > > > >  .../tensorflow-lite-demo_git.bb               | 53 +++++++++++++++++++
> > > > >  3 files changed, 68 insertions(+)
> > > > >  create mode 100644 meta-arago-extras/recipes-support/tensorflow-
> > > > lite/files/run_classification.sh
> > > > >  create mode 100644 meta-arago-extras/recipes-support/tensorflow-
> > > > lite/files/run_segmentation.sh
> > > > >  create mode 100644 meta-arago-extras/recipes-support/tensorflow-
> > > > lite/tensorflow-lite-demo_git.bb
> > > > >
> > > > > diff --git a/meta-arago-extras/recipes-support/tensorflow-
> > > > lite/files/run_classification.sh b/meta-arago-extras/recipes-
> > > > support/tensorflow-lite/files/run_classification.sh
> > > > > new file mode 100644
> > > > > index 00000000..b2ad7fc4
> > > > > --- /dev/null
> > > > > +++ b/meta-arago-extras/recipes-support/tensorflow-
> > > > lite/files/run_classification.sh
> > > > > @@ -0,0 +1,7 @@
> > > > > +#!/bin/sh
> > > > > +
> > > > > +cd /usr/share/tensorflow-lite/demos
> > > > > +
> > > > > +# Run tflite_classification binary with the model, the input image, and
> > the
> > > > label file specified.
> > > > > +# Classification label is overlayed with the input image. Right click the
> > > > image display window to exit.
> > > > > +./tflite_classification -m
> > ../examples/mobilenet_v1_1.0_224_quant.tflite -
> > > > i ../examples/grace_hopper.bmp -l ../examples/labels.txt
> > > > > diff --git a/meta-arago-extras/recipes-support/tensorflow-
> > > > lite/files/run_segmentation.sh b/meta-arago-extras/recipes-
> > > > support/tensorflow-lite/files/run_segmentation.sh
> > > > > new file mode 100644
> > > > > index 00000000..5caea127
> > > > > --- /dev/null
> > > > > +++ b/meta-arago-extras/recipes-support/tensorflow-
> > > > lite/files/run_segmentation.sh
> > > > > @@ -0,0 +1,8 @@
> > > > > +#!/bin/sh
> > > > > +
> > > > > +cd /usr/share/tensorflow-lite/demos
> > > > > +
> > > > > +# Run tflite_segmentation binary with the model and the input image
> > > > specified.
> > > > > +# The display window shows the input(resized) image, segmentation
> > > > map, overlay
> > > > > +# of the former two. Right click the image display window to exit.
> > > > > +./tflite_segmentation -m ./deeplabv3_257_mv_gpu.tflite -i
> > > > ./bird_segmentation.bmp
> > > > > diff --git a/meta-arago-extras/recipes-support/tensorflow-
> > lite/tensorflow-
> > > > lite-demo_git.bb b/meta-arago-extras/recipes-support/tensorflow-
> > > > lite/tensorflow-lite-demo_git.bb
> > > > > new file mode 100644
> > > > > index 00000000..9b99b63c
> > > > > --- /dev/null
> > > > > +++ b/meta-arago-extras/recipes-support/tensorflow-lite/tensorflow-
> > lite-
> > > > demo_git.bb
> > > > > @@ -0,0 +1,53 @@
> > > > > +DESCRIPTION = "Tensorflow Lite Demo with input and display via
> > OpenCV
> > > > and TIDL acceleration for AM5"
> > > >
> > > > SUMMARY?
> > >
> > > Do you mean adding "SUMMARY" or replacing "DESCRIPTION" with
> > "SUMMARY"?
> > 
> > Either.
> 
> Thank you! Just submitted a v2 patch to replace "DESCRIPTION" with "SUMMARY".

SUMMARY is required and is a short one-line.
DESCRIPTION is optional and can be a longer, more detailed one.

BTW, I already merged v1 - can you please submit a separate change? Thanks!


> > > > > +LICENSE = "Apache-2.0"
> > > > > +LIC_FILES_CHKSUM =
> > > > "file://LICENSE;md5=d8927f3331d2b3e321b7dd1925166d25"
> > > > > +
> > > > > +DEPENDS = "tensorflow-lite flatbuffers opencv"
> > > > > +
> > > > > +COMPATIBLE_MACHINE = "ti33x|ti43x|omap-a15|am65xx"
> > > >
> > > > Why ^^^?
> > >
> > > This demo has dependency on OpenCV for GUI display, which is available
> > for the machines above.
> > 
> > Yes, pushed a fix for that - OpenCV was limited to DSP-enabled platforms in
> > Zeus due to initial integration limitations.
> > 
> > 
> > > > > +PV = "01.00.00"
> > > > > +PR = "r0"
> > > > > +
> > > > > +BRANCH = "master"
> > > > > +SRC_URI  = "git://git.ti.com/apps/tensorflow-lite-
> > > > examples.git;protocol=git;branch=${BRANCH} \
> > > > > +
> > > >
> > http://storage.googleapis.com/download.tensorflow.org/models/tflite/gpu/
> > > >
> > deeplabv3_257_mv_gpu.tflite;name=deeplabv3;subdir=${WORKDIR}/model
> > > > ;destsuffix=model \
> > > > > +            http://raw.githubusercontent.com/google-
> > > >
> > coral/edgetpu/master/test_data/bird_segmentation.bmp;name=bird_segm
> > > > entation;subdir=${WORKDIR}/test_data;destsuffix=test_data \
> > > > > +            file://run_classification.sh \
> > > > > +            file://run_segmentation.sh"
> > > > > +
> > > > > +SRC_URI[deeplabv3.md5sum] =
> > "4a24db5a5fb05c47586a1197765e8548"
> > > > > +SRC_URI[deeplabv3.sha256sum] =
> > > >
> > "68a539782c2c6a72f8aac3724600124a85ed977162b44e84cbae5db717c933c6"
> > > > > +SRC_URI[bird_segmentation.md5sum] =
> > > > "fc3202ac4e3033b36df3043de6dc32c9"
> > > > > +SRC_URI[bird_segmentation.sha256sum] =
> > > >
> > "e43cedd29ab385db787531c8a6cdcb31c5e4292af34f242877ed40611e502670"
> > > > > +
> > > > > +SRCREV = "d84f1d43585c0db2fa6a1c15db9145ab53f859ce"
> > > > > +
> > > > > +S = "${WORKDIR}/git"
> > > > > +
> > > > > +CXXFLAGS_append = " -O3 -DNDEBUG -fPIC -I${STAGING_INCDIR}"
> > > > > +LDFLAGS_append = " -L${STAGING_LIBDIR}"
> > > > > +
> > > > > +EXTRA_OEMAKE = "\
> > > > > +    'CXX=${CXX}' \
> > > > > +    'CXXFLAGS=${CXXFLAGS}' \
> > > > > +    'AR=${AR}' \
> > > > > +    'LD=${LD}' \
> > > > > +    'LDFLAGS=${LDFLAGS}' \
> > > > > +    'TARGET=${TARGET_OS}' \
> > > > > +    'TARGET_ARCH=${TARGET_ARCH}'"
> > > > > +
> > > > > +do_compile() {
> > > > > +    oe_runmake -f Makefile
> > > > > +}
> > > > > +
> > > > > +do_install() {
> > > > > +    install -d ${D}${datadir}/tensorflow-lite/demos
> > > > > +    install -m 0755 ${S}/tflite_classification ${D}${datadir}/tensorflow-
> > > > lite/demos
> > > > > +    install -m 0755 ${S}/tflite_segmentation ${D}${datadir}/tensorflow-
> > > > lite/demos
> > > > > +    install -m 0644 ${WORKDIR}/model/deeplabv3_257_mv_gpu.tflite
> > > > ${D}${datadir}/tensorflow-lite/demos
> > > > > +    install -m 0644 ${WORKDIR}/test_data/bird_segmentation.bmp
> > > > ${D}${datadir}/tensorflow-lite/demos
> > > > > +    install -m 0755 ${WORKDIR}/run*.sh ${D}${datadir}/tensorflow-
> > > > lite/demos
> > > > > +}
> > > > > +
> > > > > +FILES_${PN} = "${datadir}/tensorflow-lite/demos"
> > > > > --
> > > > > 2.17.1
> > > > >
> > > > > _______________________________________________
> > > > > meta-arago mailing list
> > > > > meta-arago@arago-project.org
> > > > > http://arago-project.org/cgi-bin/mailman/listinfo/meta-arago


  reply	other threads:[~2020-02-28 17:27 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-02-25 23:12 [zeus/master] [PATCH 1/3] tensorflow-lite: add header files and change the install location of the example files Hongmei Gou
2020-02-25 23:12 ` [zeus/master] [PATCH 2/3] tensorflow-lite-demo: add version 01.00.00 Hongmei Gou
2020-02-27 23:14   ` Denys Dmytriyenko
2020-02-28 17:00     ` Gou, Hongmei
2020-02-28 17:12       ` Denys Dmytriyenko
2020-02-28 17:22         ` Gou, Hongmei
2020-02-28 17:25           ` Denys Dmytriyenko [this message]
2020-02-28 17:54             ` Gou, Hongmei
2020-02-25 23:12 ` [zeus/master] [PATCH 3/3] packagegroup-arago-tisdk-addons: replace tensorflow-lite-examples with tensorflow-lite and add tensorflow-lite-demo Hongmei Gou
2020-02-25 23:31   ` Denys Dmytriyenko

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200228172526.GH2466@beryl \
    --to=denys@ti.com \
    --cc=h-gou@ti.com \
    --cc=meta-arago@arago-project.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.