From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from lelv0143.ext.ti.com (lelv0143.ext.ti.com [198.47.23.248]) by arago-project.org (Postfix) with ESMTPS id 0E7CF52988 for ; Mon, 2 Mar 2020 19:39:50 +0000 (UTC) Received: from fllv0034.itg.ti.com ([10.64.40.246]) by lelv0143.ext.ti.com (8.15.2/8.15.2) with ESMTP id 022Jbmrk054636 for ; Mon, 2 Mar 2020 13:37:48 -0600 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=ti.com; s=ti-com-17Q1; t=1583177868; bh=u8Xujw2jRc/7/TmdH3rNwPtt3upwVJoRPhAT/WS+m74=; h=From:To:CC:Subject:Date:References:In-Reply-To; b=ICQipa+/1tMADf4kggTdyv2rYgkiSiEAkgQV7Oeng/CH+QhJlpLaZqI5/jJ7qpM7o VdxUZ0sNtpzv0enU+pbBb/YLNZMv6Ouce0zqNNFcIqkfQSZ++V/SLpxKB4ARPkorMC vinBnZ2SICW0VOoxA2nZtWgTFkIVQjpabNFMHVT0= Received: from DFLE110.ent.ti.com (dfle110.ent.ti.com [10.64.6.31]) by fllv0034.itg.ti.com (8.15.2/8.15.2) with ESMTPS id 022JbmIM123821 (version=TLSv1.2 cipher=AES256-GCM-SHA384 bits=256 verify=FAIL) for ; Mon, 2 Mar 2020 13:37:48 -0600 Received: from DFLE113.ent.ti.com (10.64.6.34) by DFLE110.ent.ti.com (10.64.6.31) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA256_P256) id 15.1.1847.3; Mon, 2 Mar 2020 13:37:48 -0600 Received: from DFLE113.ent.ti.com ([fe80::5de1:db32:7f81:772f]) by DFLE113.ent.ti.com ([fe80::5de1:db32:7f81:772f%18]) with mapi id 15.01.1847.007; Mon, 2 Mar 2020 13:37:48 -0600 From: "Gou, Hongmei" To: "Dmytriyenko, Denys" Thread-Topic: [meta-arago] [zeus/master] [PATCH] tensorflow-lite-demo: Bump SRCREV and add tidl offload support for AM5 Thread-Index: AQHV7ou+FTjRPNORq0GHFk7qYWtDHKg2EICA//+mQwA= Date: Mon, 2 Mar 2020 19:37:48 +0000 Message-ID: References: <20200228225858.24538-1-a0271529@ti.com> <20200302185805.GQ2466@beryl> In-Reply-To: <20200302185805.GQ2466@beryl> Accept-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [158.218.112.213] x-exclaimer-md-config: e1e8a2fd-e40a-4ac6-ac9b-f7e9cc9ee180 MIME-Version: 1.0 Cc: "meta-arago@arago-project.org" Subject: Re: [zeus/master] [PATCH] tensorflow-lite-demo: Bump SRCREV and add tidl offload support for AM5 X-BeenThere: meta-arago@arago-project.org X-Mailman-Version: 2.1.12 Precedence: list List-Id: Arago metadata layer for TI SDKs - OE-Core/Yocto compatible List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 02 Mar 2020 19:39:51 -0000 Content-Language: en-US Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable > -----Original Message----- > From: Dmytriyenko, Denys > Sent: Monday, March 2, 2020 1:58 PM > To: Gou, Hongmei > Cc: meta-arago@arago-project.org > Subject: Re: [meta-arago] [zeus/master] [PATCH] tensorflow-lite-demo: > Bump SRCREV and add tidl offload support for AM5 >=20 > On Fri, Feb 28, 2020 at 05:58:58PM -0500, Hongmei Gou wrote: > > * Build the demos with tidl offload option for AM5 > > * Include mobilenet v1 model for demonstrating tidl offload > > * Remove the demo scripts under the files directory. The scripts are no= w > > maintained in the source repo. > > * Make adjustments with the updated Makefile > > > > Signed-off-by: Hongmei Gou > > --- > > .../files/run_classification.sh | 7 ----- > > .../tensorflow-lite/files/run_segmentation.sh | 8 ------ > > .../tensorflow-lite-demo_git.bb | 27 +++++++++++-------- > > 3 files changed, 16 insertions(+), 26 deletions(-) > > delete mode 100644 meta-arago-extras/recipes-support/tensorflow- > lite/files/run_classification.sh > > delete mode 100644 meta-arago-extras/recipes-support/tensorflow- > lite/files/run_segmentation.sh > > > > 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 > > deleted file mode 100644 > > index b2ad7fc4..00000000 > > --- a/meta-arago-extras/recipes-support/tensorflow- > lite/files/run_classification.sh > > +++ /dev/null > > @@ -1,7 +0,0 @@ > > -#!/bin/sh > > - > > -cd /usr/share/tensorflow-lite/demos > > - > > -# Run tflite_classification binary with the model, the input image, an= d 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.tfli= te -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 > > deleted file mode 100644 > > index 5caea127..00000000 > > --- a/meta-arago-extras/recipes-support/tensorflow- > lite/files/run_segmentation.sh > > +++ /dev/null > > @@ -1,8 +0,0 @@ > > -#!/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/tensorfl= ow- > lite-demo_git.bb b/meta-arago-extras/recipes-support/tensorflow- > lite/tensorflow-lite-demo_git.bb > > index 9b99b63c..57d6ef20 100644 > > --- 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 > > @@ -1,33 +1,33 @@ > > -DESCRIPTION =3D "Tensorflow Lite Demo with input and display via OpenC= V > and TIDL acceleration for AM5" > > +SUMMARY =3D "Tensorflow Lite Demo with input and display via OpenCV > and TIDL acceleration for AM5" > > LICENSE =3D "Apache-2.0" > > LIC_FILES_CHKSUM =3D > "file://LICENSE;md5=3Dd8927f3331d2b3e321b7dd1925166d25" > > > > DEPENDS =3D "tensorflow-lite flatbuffers opencv" > > +DEPENDS_append_dra7xx =3D " tidl-api" > > > > COMPATIBLE_MACHINE =3D "ti33x|ti43x|omap-a15|am65xx" > > +PACKAGE_ARCH =3D "${MACHINE_ARCH}" > > > > PV =3D "01.00.00" > > -PR =3D "r0" > > +PR =3D "r1" > > > > BRANCH =3D "master" > > SRC_URI =3D "git://git.ti.com/apps/tensorflow-lite- > examples.git;protocol=3Dgit;branch=3D${BRANCH} \ > > > http://storage.googleapis.com/download.tensorflow.org/models/tflite/gpu/ > deeplabv3_257_mv_gpu.tflite;name=3Ddeeplabv3;subdir=3D${WORKDIR}/model > ;destsuffix=3Dmodel \ > > - http://raw.githubusercontent.com/google- > coral/edgetpu/master/test_data/bird_segmentation.bmp;name=3Dbird_segm > entation;subdir=3D${WORKDIR}/test_data;destsuffix=3Dtest_data \ > > - file://run_classification.sh \ > > - file://run_segmentation.sh" > > + > http://storage.googleapis.com/download.tensorflow.org/models/mobilenet > _v1_2018_02_22/mobilenet_v1_1.0_224.tgz;name=3Dmobilenetv1;subdir=3D${W > ORKDIR}/model;destsuffix=3Dmodel \ > > + http://raw.githubusercontent.com/google- > coral/edgetpu/master/test_data/bird_segmentation.bmp;name=3Dbird_segm > entation;subdir=3D${WORKDIR}/test_data;destsuffix=3Dtest_data" > > > > SRC_URI[deeplabv3.md5sum] =3D "4a24db5a5fb05c47586a1197765e8548" > > SRC_URI[deeplabv3.sha256sum] =3D > "68a539782c2c6a72f8aac3724600124a85ed977162b44e84cbae5db717c933c6" > > +SRC_URI[mobilenetv1.md5sum] =3D "d5f69cef81ad8afb335d9727a17c462a" > > +SRC_URI[mobilenetv1.sha256sum] =3D > "1ccb74dbd9c5f7aea879120614e91617db9534bdfaa53dfea54b7c14162e126b" > > SRC_URI[bird_segmentation.md5sum] =3D > "fc3202ac4e3033b36df3043de6dc32c9" > > SRC_URI[bird_segmentation.sha256sum] =3D > "e43cedd29ab385db787531c8a6cdcb31c5e4292af34f242877ed40611e502670" > > > > -SRCREV =3D "d84f1d43585c0db2fa6a1c15db9145ab53f859ce" > > +SRCREV =3D "bd6a429c21f96d5112e0b6dea44a13b748eefd74" > > > > S =3D "${WORKDIR}/git" > > > > -CXXFLAGS_append =3D " -O3 -DNDEBUG -fPIC -I${STAGING_INCDIR}" > > -LDFLAGS_append =3D " -L${STAGING_LIBDIR}" > > - > > EXTRA_OEMAKE =3D "\ > > 'CXX=3D${CXX}' \ > > 'CXXFLAGS=3D${CXXFLAGS}' \ > > @@ -37,8 +37,12 @@ EXTRA_OEMAKE =3D "\ > > 'TARGET=3D${TARGET_OS}' \ > > 'TARGET_ARCH=3D${TARGET_ARCH}'" > > > > +EXTRA_OEMAKE +=3D "SYSROOT_INCDIR=3D"${STAGING_INCDIR}" > SYSROOT_LIBDIR=3D"${STAGING_LIBDIR}" \ > > + TIDL_API_DIR=3D"${STAGING_DATADIR}/ti/tidl"" > > + > > +TIDL_dra7xx =3D "yes" >=20 > Will TIDL be undefined for other platforms? Yes, TIDL is undefined for other platforms. >=20 >=20 > > do_compile() { > > - oe_runmake -f Makefile > > + oe_runmake -f Makefile TIDL_ACC=3D${TIDL} > > } > > > > do_install() { > > @@ -46,8 +50,9 @@ do_install() { > > install -m 0755 ${S}/tflite_classification ${D}${datadir}/tensorfl= ow- > 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}/model/mobilenet_v1_1.0_224.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 > > + install -m 0755 ${S}/scripts/run*.sh ${D}${datadir}/tensorflow- > lite/demos > > } > > > > FILES_${PN} =3D "${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