Python vgslspecs.VGSLSpecs方法代码示例

# 需要导入模块: import vgslspecs [as 别名]
# 或者: from vgslspecs import VGSLSpecs [as 别名]
def ExpectScaledSize(self, spec, target_shape, factor=1):
    """Tests that the output of the graph of the given spec has target_shape."""
    with tf.Graph().as_default():
      with self.test_session() as sess:
        self.SetupInputs()
        # Only the placeholders are given at construction time.
        vgsl = vgslspecs.VGSLSpecs(self.ph_widths, self.ph_heights, True)
        outputs = vgsl.Build(self.ph_image, spec)
        # Compute the expected output widths from the given scale factor.
        target_widths = tf.div(self.in_widths, factor).eval()
        target_heights = tf.div(self.in_heights, factor).eval()
        # Run with the 'real' data.
        tf.global_variables_initializer().run()
        res_image, res_widths, res_heights = sess.run(
            [outputs, vgsl.GetLengths(2), vgsl.GetLengths(1)],
            feed_dict={self.ph_image: self.in_image,
                       self.ph_widths: self.in_widths,
                       self.ph_heights: self.in_heights})
        self.assertEqual(tuple(res_image.shape), target_shape)
        if target_shape[1] > 1:
          self.assertEqual(tuple(res_heights), tuple(target_heights))
        if target_shape[2] > 1:
          self.assertEqual(tuple(res_widths), tuple(target_widths)) 

# 需要导入模块: import vgslspecs [as 别名]
# 或者: from vgslspecs import VGSLSpecs [as 别名]
def ExpectScaledSize(self, spec, target_shape, factor=1):
    """Tests that the output of the graph of the given spec has target_shape."""
    with tf.Graph().as_default():
      with self.test_session() as sess:
        self.SetupInputs()
        # Only the placeholders are given at construction time.
        vgsl = vgslspecs.VGSLSpecs(self.ph_widths, self.ph_heights, True)
        outputs = vgsl.Build(self.ph_image, spec)
        # Compute the expected output widths from the given scale factor.
        target_widths = tf.div(self.in_widths, factor).eval()
        target_heights = tf.div(self.in_heights, factor).eval()
        # Run with the 'real' data.
        tf.initialize_all_variables().run()
        res_image, res_widths, res_heights = sess.run(
            [outputs, vgsl.GetLengths(2), vgsl.GetLengths(1)],
            feed_dict={self.ph_image: self.in_image,
                       self.ph_widths: self.in_widths,
                       self.ph_heights: self.in_heights})
        self.assertEqual(tuple(res_image.shape), target_shape)
        if target_shape[1] > 1:
          self.assertEqual(tuple(res_heights), tuple(target_heights))
        if target_shape[2] > 1:
          self.assertEqual(tuple(res_widths), tuple(target_widths)) 

# 需要导入模块: import vgslspecs [as 别名]
# 或者: from vgslspecs import VGSLSpecs [as 别名]
def Build(self, input_pattern, input_spec, model_spec, output_spec,
            optimizer_type, num_preprocess_threads, reader):
    """Builds the model from the separate input/layers/output spec strings.

    Args:
      input_pattern: File pattern of the data in tfrecords of TF Example format.
      input_spec: Specification of the input layer:
        batchsize,height,width,depth (4 comma-separated integers)
          Training will run with batches of batchsize images, but runtime can
          use any batch size.
          height and/or width can be 0 or -1, indicating variable size,
          otherwise all images must be the given size.
          depth must be 1 or 3 to indicate greyscale or color.
          NOTE 1-d image input, treating the y image dimension as depth, can
          be achieved using S1(1x0)1,3 as the first op in the model_spec, but
          the y-size of the input must then be fixed.
      model_spec: Model definition. See vgslspecs.py
      output_spec: Output layer definition:
        O(2|1|0)(l|s|c)n output layer with n classes.
          2 (heatmap) Output is a 2-d vector map of the input (possibly at
            different scale).
          1 (sequence) Output is a 1-d sequence of vector values.
          0 (value) Output is a 0-d single vector value.
          l uses a logistic non-linearity on the output, allowing multiple
            hot elements in any output vector value.
          s uses a softmax non-linearity, with one-hot output in each value.
          c uses a softmax with CTC. Can only be used with s (sequence).
          NOTE Only O1s and O1c are currently supported.
      optimizer_type: One of 'GradientDescent', 'AdaGrad', 'Momentum', 'Adam'.
      num_preprocess_threads: Number of threads to use for image processing.
      reader: Function that returns an actual reader to read Examples from input
        files. If None, uses tf.TFRecordReader().
    """
    self.global_step = tf.Variable(0, name='global_step', trainable=False)
    shape = _ParseInputSpec(input_spec)
    out_dims, out_func, num_classes = _ParseOutputSpec(output_spec)
    self.using_ctc = out_func == 'c'
    images, heights, widths, labels, sparse, _ = vgsl_input.ImageInput(
        input_pattern, num_preprocess_threads, shape, self.using_ctc, reader)
    self.labels = labels
    self.sparse_labels = sparse
    self.layers = vgslspecs.VGSLSpecs(widths, heights, self.mode == 'train')
    last_layer = self.layers.Build(images, model_spec)
    self._AddOutputs(last_layer, out_dims, out_func, num_classes)
    if self.mode == 'train':
      self._AddOptimizer(optimizer_type)

    # For saving the model across training and evaluation
    self.saver = tf.train.Saver()