Python io_ops.read_file函数代码示例

  def _evalDecodeJpeg(self, image_name, parallelism, num_iters, tile=None):
    """Evaluate DecodeJpegOp for the given image.

    TODO(tanmingxing): add decoding+cropping as well.

    Args:
      image_name: a string of image file name (without suffix).
      parallelism: the number of concurrent decode_jpeg ops to be run.
      num_iters: number of iterations for evaluation.
      tile: if not None, tile the image to composite a larger fake image.

    Returns:
      The duration of the run in seconds.
    """
    ops.reset_default_graph()

    image_file_path = os.path.join(prefix_path, image_name)

    if tile is None:
      image_content = variable_scope.get_variable(
          'image_%s' % image_name,
          initializer=io_ops.read_file(image_file_path))
    else:
      single_image = image_ops.decode_jpeg(
          io_ops.read_file(image_file_path), channels=3, name='single_image')
      # Tile the image to composite a new larger image.
      tiled_image = array_ops.tile(single_image, tile)
      image_content = variable_scope.get_variable(
          'tiled_image_%s' % image_name,
          initializer=image_ops.encode_jpeg(tiled_image))

    with session.Session() as sess:
      sess.run(variables.global_variables_initializer())
      images = []
      for i in xrange(parallelism):
        images.append(
            image_ops.decode_jpeg(
                image_content, channels=3, name='image_%d' % (i)))

      r = control_flow_ops.group(*images)

      for _ in xrange(3):
        # Skip warm up time.
        sess.run(r)

      start_time = time.time()
      for _ in xrange(num_iters):
        sess.run(r)
    return time.time() - start_time

 def testCmyk(self):
     # Confirm that CMYK reads in as RGB
     base = "tensorflow/core/lib/jpeg/testdata"
     rgb_path = os.path.join(base, "jpeg_merge_test1.jpg")
     cmyk_path = os.path.join(base, "jpeg_merge_test1_cmyk.jpg")
     shape = 256, 128, 3
     for channels in 3, 0:
         with self.test_session() as sess:
             rgb = image_ops.decode_jpeg(io_ops.read_file(rgb_path), channels=channels)
             cmyk = image_ops.decode_jpeg(io_ops.read_file(cmyk_path), channels=channels)
             rgb, cmyk = sess.run([rgb, cmyk])
             self.assertEqual(rgb.shape, shape)
             self.assertEqual(cmyk.shape, shape)
             error = self.averageError(rgb, cmyk)
             self.assertLess(error, 4)

  def prepare_background_data(self):
    """Searches a folder for background noise audio, and loads it into memory.

    It's expected that the background audio samples will be in a subdirectory
    named '_background_noise_' inside the 'data_dir' folder, as .wavs that match
    the sample rate of the training data, but can be much longer in duration.

    If the '_background_noise_' folder doesn't exist at all, this isn't an
    error, it's just taken to mean that no background noise augmentation should
    be used. If the folder does exist, but it's empty, that's treated as an
    error.

    Returns:
      List of raw PCM-encoded audio samples of background noise.

    Raises:
      Exception: If files aren't found in the folder.
    """
    self.background_data = []
    background_dir = os.path.join(self.data_dir, BACKGROUND_NOISE_DIR_NAME)
    if not os.path.exists(background_dir):
      return self.background_data
    with tf.Session(graph=tf.Graph()) as sess:
      wav_filename_placeholder = tf.placeholder(tf.string, [])
      wav_loader = io_ops.read_file(wav_filename_placeholder)
      wav_decoder = contrib_audio.decode_wav(wav_loader, desired_channels=1)
      search_path = os.path.join(self.data_dir, BACKGROUND_NOISE_DIR_NAME,
                                 '*.wav')
      for wav_path in gfile.Glob(search_path):
        wav_data = sess.run(
            wav_decoder,
            feed_dict={wav_filename_placeholder: wav_path}).audio.flatten()
        self.background_data.append(wav_data)
      if not self.background_data:
        raise Exception('No background wav files were found in ' + search_path)

  def testGif(self):
    # Read some real GIFs
    path = os.path.join(prefix_path, "gif", "testdata", "scan.gif")
    width = 20
    height = 40
    stride = 5
    shape = (12, height, width, 3)

    with self.session(use_gpu=True) as sess:
      gif0 = io_ops.read_file(path)
      image0 = image_ops.decode_image(gif0)
      image1 = image_ops.decode_gif(gif0)
      gif0, image0, image1 = self.evaluate([gif0, image0, image1])

      self.assertEqual(image0.shape, shape)
      self.assertAllEqual(image0, image1)

      for frame_idx, frame in enumerate(image0):
        gt = np.zeros(shape[1:], dtype=np.uint8)
        start = frame_idx * stride
        end = (frame_idx + 1) * stride
        if end <= width:
          gt[:, start:end, :] = 255
        else:
          start -= width
          end -= width
          gt[start:end, :, :] = 255

        self.assertAllClose(frame, gt)

        bad_channels = image_ops.decode_image(gif0, channels=1)
        with self.assertRaises(errors_impl.InvalidArgumentError):
          self.evaluate(bad_channels)

 def _restore_op(self, iterator_resource):
   iterator_state_variant = parsing_ops.parse_tensor(
       io_ops.read_file(self._iterator_checkpoint_prefix_local()),
       dtypes.variant)
   restore_op = gen_dataset_ops.deserialize_iterator(iterator_resource,
                                                     iterator_state_variant)
   return restore_op

 def get_unprocessed_data(self, how_many, model_settings, mode):
   """Gets sample data without transformations."""
   candidates = self.data_index[mode]
   if how_many == -1:
     sample_count = len(candidates)
   else:
     sample_count = how_many
   desired_samples = model_settings['desired_samples']
   words_list = self.words_list
   data = np.zeros((sample_count, desired_samples))
   labels = []
   with tf.Session(graph=tf.Graph()) as sess:
     wav_filename_placeholder = tf.placeholder(tf.string, [], name='filename')
     wav_loader = io_ops.read_file(wav_filename_placeholder)
     wav_decoder = contrib_audio.decode_wav(
         wav_loader, desired_channels=1, desired_samples=desired_samples)
     foreground_volume_placeholder = tf.placeholder(
         tf.float32, [], name='foreground_volume')
     scaled_foreground = tf.multiply(wav_decoder.audio,
                                     foreground_volume_placeholder)
     for i in range(sample_count):
       if how_many == -1:
         sample_index = i
       else:
         sample_index = np.random.randint(len(candidates))
       sample = candidates[sample_index]
       input_dict = {wav_filename_placeholder: sample['file']}
       if sample['label'] == SILENCE_LABEL:
         input_dict[foreground_volume_placeholder] = 0
       else:
         input_dict[foreground_volume_placeholder] = 1
       data[i, :] = sess.run(scaled_foreground, feed_dict=input_dict).flatten()
       label_index = self.word_to_index[sample['label']]
       labels.append(words_list[label_index])
   return data, labels

  def testGif(self):
    # Read some real GIFs
    path = os.path.join(prefix_path, "gif", "testdata", "scan.gif")
    WIDTH = 20
    HEIGHT = 40
    STRIDE = 5
    shape = (12, HEIGHT, WIDTH, 3)

    with self.test_session(use_gpu=True) as sess:
      gif0 = io_ops.read_file(path)
      image0 = image_ops.decode_image(gif0)
      image1 = image_ops.decode_gif(gif0)
      gif0, image0, image1 = sess.run([gif0, image0, image1])

      self.assertEqual(image0.shape, shape)
      self.assertAllEqual(image0, image1)

      for frame_idx, frame in enumerate(image0):
        gt = np.zeros(shape[1:], dtype=np.uint8)
        start = frame_idx * STRIDE
        end = (frame_idx + 1) * STRIDE
        if end <= WIDTH:
          gt[:, start:end, :] = 255
        else:
          start -= WIDTH
          end -= WIDTH
          gt[start:end, :, :] = 255

        self.assertAllClose(frame, gt)

        bad_channels = image_ops.decode_image(gif0, channels=1)
        with self.assertRaises(errors_impl.InvalidArgumentError):
          bad_channels.eval()

  def prepare_processing_graph(self, model_settings):
    """Builds a TensorFlow graph to apply the input distortions.

    Creates a graph that loads a WAVE file, decodes it, scales the volume,
    shifts it in time, adds in background noise, calculates a spectrogram, and
    then builds an MFCC fingerprint from that.

    This must be called with an active TensorFlow session running, and it
    creates multiple placeholder inputs, and one output:

      - wav_filename_placeholder_: Filename of the WAV to load.
      - foreground_volume_placeholder_: How loud the main clip should be.
      - time_shift_padding_placeholder_: Where to pad the clip.
      - time_shift_offset_placeholder_: How much to move the clip in time.
      - background_data_placeholder_: PCM sample data for background noise.
      - background_volume_placeholder_: Loudness of mixed-in background.
      - mfcc_: Output 2D fingerprint of processed audio.

    Args:
      model_settings: Information about the current model being trained.
    """
    desired_samples = model_settings['desired_samples']
    self.wav_filename_placeholder_ = tf.placeholder(tf.string, [])
    wav_loader = io_ops.read_file(self.wav_filename_placeholder_)
    wav_decoder = contrib_audio.decode_wav(
        wav_loader, desired_channels=1, desired_samples=desired_samples)
    # Allow the audio sample's volume to be adjusted.
    self.foreground_volume_placeholder_ = tf.placeholder(tf.float32, [])
    scaled_foreground = tf.multiply(wav_decoder.audio,
                                    self.foreground_volume_placeholder_)
    # Shift the sample's start position, and pad any gaps with zeros.
    self.time_shift_padding_placeholder_ = tf.placeholder(tf.int32, [2, 2])
    self.time_shift_offset_placeholder_ = tf.placeholder(tf.int32, [2])
    padded_foreground = tf.pad(
        scaled_foreground,
        self.time_shift_padding_placeholder_,
        mode='CONSTANT')
    sliced_foreground = tf.slice(padded_foreground,
                                 self.time_shift_offset_placeholder_,
                                 [desired_samples, -1])
    # Mix in background noise.
    self.background_data_placeholder_ = tf.placeholder(tf.float32,
                                                       [desired_samples, 1])
    self.background_volume_placeholder_ = tf.placeholder(tf.float32, [])
    background_mul = tf.multiply(self.background_data_placeholder_,
                                 self.background_volume_placeholder_)
    background_add = tf.add(background_mul, sliced_foreground)
    background_clamp = tf.clip_by_value(background_add, -1.0, 1.0)
    # Run the spectrogram and MFCC ops to get a 2D 'fingerprint' of the audio.
    spectrogram = contrib_audio.audio_spectrogram(
        background_clamp,
        window_size=model_settings['window_size_samples'],
        stride=model_settings['window_stride_samples'],
        magnitude_squared=True)
    self.mfcc_ = contrib_audio.mfcc(
        spectrogram,
        wav_decoder.sample_rate,
        dct_coefficient_count=model_settings['dct_coefficient_count'])

def load_wav_file(filename):
  """Loads an audio file and returns a float PCM-encoded array of samples."""
  with tf.Session(graph=tf.Graph()) as sess:
    wav_filename_placeholder = tf.placeholder(tf.string, [])
    wav_loader = io_ops.read_file(wav_filename_placeholder)
    wav_decoder = contrib_audio.decode_wav(wav_loader, desired_channels=1)
    return sess.run(
        wav_decoder, feed_dict={
            wav_filename_placeholder: filename
        }).audio.flatten()

 def testBmp(self):
   # Read a real bmp and verify shape
   path = os.path.join(prefix_path, "bmp", "testdata", "lena.bmp")
   with self.session(use_gpu=True) as sess:
     bmp0 = io_ops.read_file(path)
     image0 = image_ops.decode_image(bmp0)
     image1 = image_ops.decode_bmp(bmp0)
     bmp0, image0, image1 = self.evaluate([bmp0, image0, image1])
     self.assertEqual(len(bmp0), 4194)
     self.assertAllEqual(image0, image1)

 def testExisting(self):
     # Read a real jpeg and verify shape
     path = "tensorflow/core/lib/jpeg/testdata/" "jpeg_merge_test1.jpg"
     with self.test_session() as sess:
         jpeg0 = io_ops.read_file(path)
         image0 = image_ops.decode_jpeg(jpeg0)
         image1 = image_ops.decode_jpeg(image_ops.encode_jpeg(image0))
         jpeg0, image0, image1 = sess.run([jpeg0, image0, image1])
         self.assertEqual(len(jpeg0), 3771)
         self.assertEqual(image0.shape, (256, 128, 3))
         self.assertLess(self.averageError(image0, image1), 0.8)

 def testJpeg(self):
   # Read a real jpeg and verify shape
   path = os.path.join(prefix_path, "jpeg", "testdata", "jpeg_merge_test1.jpg")
   with self.test_session(use_gpu=True) as sess:
     jpeg0 = io_ops.read_file(path)
     image0 = image_ops.decode_image(jpeg0)
     image1 = image_ops.decode_jpeg(jpeg0)
     jpeg0, image0, image1 = sess.run([jpeg0, image0, image1])
     self.assertEqual(len(jpeg0), 3771)
     self.assertEqual(image0.shape, (256, 128, 3))
     self.assertAllEqual(image0, image1)

 def testReadFile(self):
   cases = ['', 'Some contents', 'Неки садржаји на српском']
   for contents in cases:
     contents = compat.as_bytes(contents)
     with tempfile.NamedTemporaryFile(
         prefix='ReadFileTest', dir=self.get_temp_dir(), delete=False) as temp:
       temp.write(contents)
     with self.cached_session():
       read = io_ops.read_file(temp.name)
       self.assertEqual([], read.get_shape())
       self.assertEqual(read.eval(), contents)
     os.remove(temp.name)

 def testPng(self):
   # Read some real PNGs, converting to different channel numbers
   inputs = [(1, "lena_gray.png")]
   for channels_in, filename in inputs:
     for channels in 0, 1, 3, 4:
       with self.cached_session(use_gpu=True) as sess:
         path = os.path.join(prefix_path, "png", "testdata", filename)
         png0 = io_ops.read_file(path)
         image0 = image_ops.decode_image(png0, channels=channels)
         image1 = image_ops.decode_png(png0, channels=channels)
         png0, image0, image1 = self.evaluate([png0, image0, image1])
         self.assertEqual(image0.shape, (26, 51, channels or channels_in))
         self.assertAllEqual(image0, image1)

 def prepare_processing_graph(self, model_settings):
   """Builds a TensorFlow graph to apply the input distortions"""
   desired_samples = model_settings['desired_samples']
   self.wav_filename_placeholder_ = tf.placeholder(
       tf.string, [], name='filename')
   wav_loader = io_ops.read_file(self.wav_filename_placeholder_)
   wav_decoder = contrib_audio.decode_wav(
       wav_loader, desired_channels=1, desired_samples=desired_samples)
   # Allow the audio sample's volume to be adjusted.
   self.foreground_volume_placeholder_ = tf.placeholder(
       tf.float32, [], name='foreground_volme')
   scaled_foreground = tf.multiply(wav_decoder.audio,
                                   self.foreground_volume_placeholder_)
   # Shift the sample's start position, and pad any gaps with zeros.
   self.time_shift_placeholder_ = tf.placeholder(tf.int32, name='timeshift')
   shifted_foreground = tf_roll(scaled_foreground,
                                self.time_shift_placeholder_)
   # Mix in background noise.
   self.background_data_placeholder_ = tf.placeholder(
       tf.float32, [desired_samples, 1], name='background_data')
   self.background_volume_placeholder_ = tf.placeholder(
       tf.float32, [], name='background_volume')
   background_mul = tf.multiply(self.background_data_placeholder_,
                                self.background_volume_placeholder_)
   background_add = tf.add(background_mul, shifted_foreground)
   # removed clipping: tf.clip_by_value(background_add, -1.0, 1.0)
   self.background_clamp_ = background_add
   self.background_clamp_ = tf.reshape(self.background_clamp_,
                                       (1, model_settings['desired_samples']))
   # Run the spectrogram and MFCC ops to get a 2D 'fingerprint' of the audio.
   stfts = tf.contrib.signal.stft(
       self.background_clamp_,
       frame_length=model_settings['window_size_samples'],
       frame_step=model_settings['window_stride_samples'],
       fft_length=None)
   self.spectrogram_ = tf.abs(stfts)
   num_spectrogram_bins = self.spectrogram_.shape[-1].value
   lower_edge_hertz, upper_edge_hertz = 80.0, 7600.0
   linear_to_mel_weight_matrix = \
       tf.contrib.signal.linear_to_mel_weight_matrix(
           model_settings['dct_coefficient_count'],
           num_spectrogram_bins, model_settings['sample_rate'],
           lower_edge_hertz, upper_edge_hertz)
   mel_spectrograms = tf.tensordot(self.spectrogram_,
                                   linear_to_mel_weight_matrix, 1)
   mel_spectrograms.set_shape(self.spectrogram_.shape[:-1].concatenate(
       linear_to_mel_weight_matrix.shape[-1:]))
   log_mel_spectrograms = tf.log(mel_spectrograms + 1e-6)
   self.mfcc_ = tf.contrib.signal.mfccs_from_log_mel_spectrograms(
       log_mel_spectrograms)[:, :, :
                             model_settings['num_log_mel_features']]  # :13