def read_image(self, image_path):
# tf.decode_image does not return the image size, this is an ugly workaround to handle both jpeg and png
path_length = string_length_tf(image_path)[0]
file_extension = tf.substr(image_path, path_length - 3, 3)
file_cond = tf.equal(file_extension, 'jpg')
image = tf.cond(file_cond, lambda: tf.image.decode_jpeg(tf.read_file(image_path)), lambda: tf.image.decode_png(tf.read_file(image_path)))
# if the dataset is cityscapes, we crop the last fifth to remove the car hood
if self.dataset == 'cityscapes':
o_height = tf.shape(image)[0]
crop_height = (o_height * 4) / 5
image = image[:crop_height,:,:]
image = tf.image.convert_image_dtype(image, tf.float32)
image = tf.image.resize_images(image, [self.params.height, self.params.width], tf.image.ResizeMethod.AREA)
return image
python类substr()的实例源码
def read_image(self, image_path):
# tf.decode_image does not return the image size, this is an ugly workaround to handle both jpeg and png
path_length = string_length_tf(image_path)[0]
file_extension = tf.substr(image_path, path_length - 3, 3)
file_cond = tf.equal(file_extension, 'jpg')
image = tf.cond(file_cond, lambda: tf.image.decode_jpeg(tf.read_file(image_path)), lambda: tf.image.decode_png(tf.read_file(image_path)))
# if the dataset is cityscapes, we crop the last fifth to remove the car hood
if self.dataset == 'cityscapes':
o_height = tf.shape(image)[0]
crop_height = (o_height * 4) // 5
image = image[:crop_height,:,:]
image = tf.image.convert_image_dtype(image, tf.float32)
image = tf.image.resize_images(image, [self.params.height, self.params.width], tf.image.ResizeMethod.AREA)
return image
def __init__(self, config, batch_size, one_hot=False):
self.lookup = None
reader = tf.TextLineReader()
filename_queue = tf.train.string_input_producer(["chargan.txt"])
key, x = reader.read(filename_queue)
vocabulary = self.get_vocabulary()
table = tf.contrib.lookup.string_to_index_table_from_tensor(
mapping = vocabulary, default_value = 0)
x = tf.string_join([x, tf.constant(" " * 64)])
x = tf.substr(x, [0], [64])
x = tf.string_split(x,delimiter='')
x = tf.sparse_tensor_to_dense(x, default_value=' ')
x = tf.reshape(x, [64])
x = table.lookup(x)
self.one_hot = one_hot
if one_hot:
x = tf.one_hot(x, len(vocabulary))
x = tf.cast(x, dtype=tf.float32)
x = tf.reshape(x, [1, int(x.get_shape()[0]), int(x.get_shape()[1]), 1])
else:
x = tf.cast(x, dtype=tf.float32)
x -= len(vocabulary)/2.0
x /= len(vocabulary)/2.0
x = tf.reshape(x, [1,1, 64, 1])
num_preprocess_threads = 8
x = tf.train.shuffle_batch(
[x],
batch_size=batch_size,
num_threads=num_preprocess_threads,
capacity= 5000,
min_after_dequeue=500,
enqueue_many=True)
self.x = x
self.table = table
def read_image(self, image_path):
# tf.decode_image does not return the image size, this is an ugly workaround to handle both jpeg and png
path_length = string_length_tf(image_path)[0]
file_extension = tf.substr(image_path, path_length - 3, 3)
file_cond = tf.equal(file_extension, 'jpg')
image = tf.cond(file_cond, lambda: tf.image.decode_jpeg(tf.read_file(image_path)),
lambda: tf.image.decode_png(tf.read_file(image_path)))
image = tf.image.convert_image_dtype(image, tf.float32)
image = tf.image.resize_images(image, [self.params.height, self.params.width], tf.image.ResizeMethod.AREA)
return image
def decode_image(contents, channels=None, name=None):
"""Convenience function for `decode_gif`, `decode_jpeg`, and `decode_png`.
Detects whether an image is a GIF, JPEG, or PNG, and performs the appropriate
operation to convert the input bytes `string` into a `Tensor` of type `uint8`.
Note: `decode_gif` returns a 4-D array `[num_frames, height, width, 3]`, as
opposed to `decode_jpeg` and `decode_png`, which return 3-D arrays
`[height, width, num_channels]`. Make sure to take this into account when
constructing your graph if you are intermixing GIF files with JPEG and/or PNG
files.
Args:
contents: 0-D `string`. The encoded image bytes.
channels: An optional `int`. Defaults to `0`. Number of color channels for
the decoded image.
name: A name for the operation (optional)
Returns:
`Tensor` with type `uint8` with shape `[height, width, num_channels]` for
JPEG and PNG images and shape `[num_frames, height, width, 3]` for GIF
images.
"""
with ops.name_scope(name, 'decode_image') as scope:
if channels not in (None, 0, 1, 3):
raise ValueError('channels must be in (None, 0, 1, 3)')
substr = tf.substr(contents, 0, 4)
def _gif():
# Create assert op to check that bytes are GIF decodable
is_gif = tf.equal(substr, b'\x47\x49\x46\x38', name='is_gif')
decode_msg = 'Unable to decode bytes as JPEG, PNG, or GIF'
assert_decode = control_flow_ops.Assert(is_gif, [decode_msg])
# Create assert to make sure that channels is not set to 1
# Already checked above that channels is in (None, 0, 1, 3)
gif_channels = 0 if channels is None else channels
good_channels = tf.not_equal(gif_channels, 1, name='check_channels')
channels_msg = 'Channels must be in (None, 0, 3) when decoding GIF images'
assert_channels = control_flow_ops.Assert(good_channels, [channels_msg])
with ops.control_dependencies([assert_decode, assert_channels]):
return gen_image_ops.decode_gif(contents)
def _png():
return gen_image_ops.decode_png(contents, channels)
def check_png():
is_png = tf.equal(substr, b'\211PNG', name='is_png')
return control_flow_ops.cond(is_png, _png, _gif, name='cond_png')
def _jpeg():
return gen_image_ops.decode_jpeg(contents, channels)
is_jpeg = tf.logical_or(tf.equal(substr, b'\xff\xd8\xff\xe0', name='is_jpeg0'),
tf.equal(substr, b'\xff\xd8\xff\xe1', name='is_jpeg0'))
return control_flow_ops.cond(is_jpeg, _jpeg, check_png, name='cond_jpeg')