def resize_audio_with_crop_or_pad(image, target_height, target_width,
dynamic_shape=False):
image = tf.convert_to_tensor(image, name='audio')
original_height, _ = _ImageDimensions(image, dynamic_shape=dynamic_shape)
if target_height <= 0:
raise ValueError('target_height must be > 0.')
if dynamic_shape:
max_ = math_ops.maximum
min_ = math_ops.minimum
else:
max_ = max
min_ = min
height_diff = target_height - original_height
offset_crop_height = max_(-height_diff // 2, 0)
offset_pad_height = max_(height_diff // 2, 0)
# Maybe crop if needed.
cropped = crop_to_1d_bounding_box(image, offset_crop_height,
min_(target_height, original_height),
dynamic_shape=dynamic_shape)
# Maybe pad if needed.
resized = pad_to_1d_bounding_box(cropped, offset_pad_height,
target_height,
dynamic_shape=dynamic_shape)
if resized.get_shape().ndims is None:
raise ValueError('resized contains no shape.')
if not resized.get_shape()[0].is_compatible_with(target_height):
raise ValueError('resized height is not correct.')
return resized
# In[5]:
评论列表
文章目录