Recherche avancée

Sur d’autres sites (8787)

• dnn_backend_native_layer_mathunary : add floor support

  6 août 2020, par Mingyu Yin

  dnn_backend_native_layer_mathunary : add floor support
  It can be tested with the model generated with below python script :
  import tensorflow as tf
  
  import os
  
  import numpy as np
  
  import imageio
  
  from tensorflow.python.framework import graph_util
  
  name = 'floor'
  pb_file_path = os.getcwd()
  
  if not os.path.exists(pb_file_path+'/{}_savemodel/'.format(name)) :
  
      os.mkdir(pb_file_path+'/{}_savemodel/'.format(name))
  with tf.Session(graph=tf.Graph()) as sess :
  
      in_img = imageio.imread('detection.jpg')
  
      in_img = in_img.astype(np.float32)
  
      in_data = in_img[np.newaxis, :]
  
      input_x = tf.placeholder(tf.float32, shape=[1, None, None, 3], name='dnn_in')
  
      y_ = tf.math.floor(input_x*255)/255
  
      y = tf.identity(y_, name='dnn_out')
  
      sess.run(tf.global_variables_initializer())
  
      constant_graph = graph_util.convert_variables_to_constants(sess, sess.graph_def, ['dnn_out'])
      with tf.gfile.FastGFile(pb_file_path+'/{}_savemodel/model.pb'.format(name), mode='wb') as f :
  
          f.write(constant_graph.SerializeToString())
      print("model.pb generated, please in ffmpeg path use\n \n \
  
      python tools/python/convert.py {}_savemodel/model.pb —outdir={}_savemodel/ \n \nto generate model.model\n".format(name,name))
      output = sess.run(y, feed_dict= input_x : in_data)
  
      imageio.imsave("out.jpg", np.squeeze(output))
      print("To verify, please ffmpeg path use\n \n \
  
      ./ffmpeg -i detection.jpg -vf format=rgb24,dnn_processing=model={}_savemodel/model.pb:input=dnn_in:output=dnn_out:dnn_backend=tensorflow -f framemd5 {}_savemodel/tensorflow_out.md5\n  \
  
      or\n \
  
      ./ffmpeg -i detection.jpg -vf format=rgb24,dnn_processing=model={}_savemodel/model.pb:input=dnn_in:output=dnn_out:dnn_backend=tensorflow {}_savemodel/out_tensorflow.jpg\n \nto generate output result of tensorflow model\n".format(name, name, name, name))
      print("To verify, please ffmpeg path use\n \n \
  
      ./ffmpeg -i detection.jpg -vf format=rgb24,dnn_processing=model={}_savemodel/model.model:input=dnn_in:output=dnn_out:dnn_backend=native -f framemd5 {}_savemodel/native_out.md5\n  \
  
      or \n \
  
      ./ffmpeg -i detection.jpg -vf format=rgb24,dnn_processing=model={}_savemodel/model.model:input=dnn_in:output=dnn_out:dnn_backend=native {}_savemodel/out_native.jpg\n \nto generate output result of native model\n".format(name, name, name, name))
  Signed-off-by : Mingyu Yin <mingyu.yin@intel.com>
  

  • [DH] libavfilter/dnn/dnn_backend_native_layer_mathunary.c
  • [DH] libavfilter/dnn/dnn_backend_native_layer_mathunary.h
  • [DH] tests/dnn/dnn-layer-mathunary-test.c
  • [DH] tools/python/convert_from_tensorflow.py
  • [DH] tools/python/convert_header.py

• dnn_backend_native_layer_mathunary : add ceil support

  31 juillet 2020, par Mingyu Yin

  dnn_backend_native_layer_mathunary : add ceil support
  It can be tested with the model generated with below python script :
  import tensorflow as tf
  
  import os
  
  import numpy as np
  
  import imageio
  
  from tensorflow.python.framework import graph_util
  
  name = 'ceil'
  pb_file_path = os.getcwd()
  
  if not os.path.exists(pb_file_path+'/{}_savemodel/'.format(name)) :
  
      os.mkdir(pb_file_path+'/{}_savemodel/'.format(name))
  with tf.Session(graph=tf.Graph()) as sess :
  
      in_img = imageio.imread('detection.jpg')
  
      in_img = in_img.astype(np.float32)
  
      in_data = in_img[np.newaxis, :]
  
      input_x = tf.placeholder(tf.float32, shape=[1, None, None, 3], name='dnn_in')
  
      y = tf.math.ceil( input_x, name='dnn_out')
  
      sess.run(tf.global_variables_initializer())
  
      constant_graph = graph_util.convert_variables_to_constants(sess, sess.graph_def, ['dnn_out'])
      with tf.gfile.FastGFile(pb_file_path+'/{}_savemodel/model.pb'.format(name), mode='wb') as f :
  
          f.write(constant_graph.SerializeToString())
      print("model.pb generated, please in ffmpeg path use\n \n \
  
      python tools/python/convert.py ceil_savemodel/model.pb —outdir=ceil_savemodel/ \n \n \
  
      to generate model.model\n")
      output = sess.run(y, feed_dict= input_x : in_data)
  
      imageio.imsave("out.jpg", np.squeeze(output))
      print("To verify, please ffmpeg path use\n \n \
  
      ./ffmpeg -i detection.jpg -vf format=rgb24,dnn_processing=model=ceil_savemodel/model.pb:input=dnn_in:output=dnn_out:dnn_backend=tensorflow -f framemd5 ceil_savemodel/tensorflow_out.md5\n \n \
  
      to generate output result of tensorflow model\n")
      print("To verify, please ffmpeg path use\n \n \
  
      ./ffmpeg -i detection.jpg -vf format=rgb24,dnn_processing=model=ceil_savemodel/model.model:input=dnn_in:output=dnn_out:dnn_backend=native -f framemd5 ceil_savemodel/native_out.md5\n \n \
  
      to generate output result of native model\n")
  Signed-off-by : Mingyu Yin <mingyu.yin@intel.com>
  
  Reviewed-by : Guo, Yejun <yejun.guo@intel.com>
  

  • [DH] libavfilter/dnn/dnn_backend_native_layer_mathunary.c
  • [DH] libavfilter/dnn/dnn_backend_native_layer_mathunary.h
  • [DH] tests/dnn/dnn-layer-mathunary-test.c
  • [DH] tools/python/convert_from_tensorflow.py
  • [DH] tools/python/convert_header.py

• ffmpeg on Intel Edison cannot find pkg-config

  4 février 2016, par Joel Gallant

  I’ve had a surprisingly difficult time finding documentation for what I’m seeing. I’m cross-compiling ffmpeg for the Intel Edison using the poky linux sdk. I’ve set up an upper level makefile to do the following :

  ffmpeg_DIR=$(shell realpath libs/ffmpeg)
  
  EdisonSDK_DIR=/opt/poky-edison/1.7.2
  
  EdisonSysroot=$(EdisonSDK_DIR)/sysroots/core2-32-poky-linux
  
  PATH:=$(EdisonSysroot)/usr/bin/:$(EdisonSysroot)/usr/bin/i586-poky-linux:$(PATH)
  
  
  
  ffmpeg-config: FORCE
  
      mkdir -p $(ffmpeg_DIR)/build; \
  
      cd $(ffmpeg_DIR); \
  
      PATH=$(PATH) ./configure \
  
          --prefix=$(ffmpeg_DIR)/build \
  
          --enable-shared \
  
          --disable-static \
  
          --disable-doc \
  
          --arch=i686 \
  
          --enable-cross-compile \
  
          --cross-prefix=i586-poky-linux- \
  
          --sysinclude=$(EdisonSysroot)/include \
  
          --pkg-config=$(EdisonSysroot)/usr/bin/pkg-config \
  
          --target-os=linux
  
  
  
  ifeq (,$(wildcard $(ffmpeg_DIR)/build))
  
  ffmpeg: ffmpeg-config FORCE
  
  else
  
  ffmpeg: FORCE
  
  endif
  
      +make -C$(ffmpeg_DIR)

  So as far as I understand it, it’s using the PATH correctly, sysroot is being inserted in cc and ld calls, and sysinclude is working.

  I’m seeing this in the output of the main makefile :

  tput: error while loading shared libraries: libtinfo.so.5: cannot open shared object file: No such file or directory

  And seeing this in the config.log

  i586-poky-linux-gcc -O2 -pipe -g -feliminate-unused-debug-types -c -o /tmp/ffconf.T3Y8Tm6G.o /tmp/ffconf.t8bOuCO2.c
  
  /opt/poky-edison/1.7.2/sysroots/core2-32-poky-linux/usr/bin/../lib/gcc/gcc/i586-poky-linux/4.9.1/cc1: error while loading shared libraries: libmpc.so.3: cannot open shared object file: No such file or directory
  
  /opt/poky-edison/1.7.2/sysroots/core2-32-poky-linux/usr/bin/../lib/gcc/i586-poky-linux/4.9.1/../../../../i586-poky-linux/bin/as: error while loading shared libraries: libopcodes-2.24.so: cannot open shared object file: No such file or directory
  
  C compiler test failed.

  So to me, that seems like a linker error. And in the config.log, I also see that pkg-config isn’t working.

  WARNING: /opt/poky-edison/1.7.2/sysroots/core2-32-poky-linux/usr/bin/pkg-config not found, library detection may fail.

  So I’m not sure what I’m doing wrong exactly. I’ve tried seeing sysroot or not, and not specifying the pkg-config.

  https://ffmpeg.org/pipermail/ffmpeg-devel/2012-June/126683.html

  This seems related but is fixed now. So not sure.