def extract_image_patches(X,
ksizes,
strides,
padding='valid',
data_format='channels_first'):
patch_size = ksizes[1]
if padding == 'same':
padding = 'ignore_borders'
if data_format == 'channels_last':
X = KTH.permute_dimensions(X, [0, 3, 1, 2])
# Thanks to https://github.com/awentzonline for the help!
batch, c, w, h = KTH.shape(X)
xs = KTH.shape(X)
num_rows = 1 + (xs[-2] - patch_size) // strides[1]
num_cols = 1 + (xs[-1] - patch_size) // strides[1]
num_channels = xs[-3]
patches = images2neibs(X, ksizes, strides, padding)
# Theano is sorting by channel
patches = KTH.reshape(
patches,
(batch, num_channels, num_rows * num_cols, patch_size, patch_size))
patches = KTH.permute_dimensions(patches, (0, 2, 1, 3, 4))
# arrange in a 2d-grid (rows, cols, channels, px, py)
patches = KTH.reshape(
patches,
(batch, num_rows, num_cols, num_channels, patch_size, patch_size))
if data_format == 'channels_last':
patches = KTH.permute_dimensions(patches, [0, 1, 2, 4, 5, 3])
return patches
def extract_image_patches(X,
ksizes,
strides,
padding="valid",
data_format="channels_first"):
"""
Extract the patches from an image
Parameters
----------
X : The input image
ksizes : 2-d tuple with the kernel size
strides : 2-d tuple with the strides size
padding : 'same' or 'valid'
data_format : 'channels_last' or 'channels_first'
Returns
-------
The (k_w,k_h) patches extracted
TF ==> (batch_size,w,h,k_w,k_h,c)
TH ==> (batch_size,w,h,c,k_w,k_h)
"""
patch_size = ksizes[1]
if padding == "same":
padding = "ignore_borders"
if data_format == "channels_last":
X = KTH.permute_dimensions(X, [0, 3, 1, 2])
# Thanks to https://github.com/awentzonline for the help!
batch, c, w, h = KTH.shape(X)
xs = KTH.shape(X)
num_rows = 1 + (xs[-2] - patch_size) // strides[1]
num_cols = 1 + (xs[-1] - patch_size) // strides[1]
num_channels = xs[-3]
patches = images2neibs(X, ksizes, strides, padding)
# Theano is sorting by channel
new_shape = (batch, num_channels, num_rows * num_cols, patch_size,
patch_size)
patches = KTH.reshape(patches, new_shape)
patches = KTH.permute_dimensions(patches, (0, 2, 1, 3, 4))
# arrange in a 2d-grid (rows, cols, channels, px, py)
new_shape = (batch, num_rows, num_cols, num_channels, patch_size,
patch_size)
patches = KTH.reshape(patches, new_shape)
if data_format == "channels_last":
patches = KTH.permute_dimensions(patches, [0, 1, 2, 4, 5, 3])
return patches
def extract_image_patches(X,
ksizes,
strides,
border_mode="valid",
dim_ordering="th"):
'''
Extract the patches from an image
Parameters
----------
X : The input image
ksizes : 2-d tuple with the kernel size
strides : 2-d tuple with the strides size
border_mode : 'same' or 'valid'
dim_ordering : 'tf' or 'th'
Returns
-------
The (k_w,k_h) patches extracted
TF ==> (batch_size,w,h,k_w,k_h,c)
TH ==> (batch_size,w,h,c,k_w,k_h)
'''
patch_size = ksizes[1]
if border_mode == "same":
border_mode = "ignore_borders"
if dim_ordering == "tf":
X = KTH.permute_dimensions(X, [0, 3, 1, 2])
# Thanks to https://github.com/awentzonline for the help!
batch, c, w, h = KTH.shape(X)
xs = KTH.shape(X)
num_rows = 1 + (xs[-2] - patch_size) // strides[1]
num_cols = 1 + (xs[-1] - patch_size) // strides[1]
num_channels = xs[-3]
patches = images2neibs(X, ksizes, strides, border_mode)
# Theano is sorting by channel
patches = KTH.reshape(patches,
(batch, num_channels, KTH.shape(patches)[0] //
num_channels, patch_size, patch_size))
patches = KTH.permute_dimensions(patches, (0, 2, 1, 3, 4))
# arrange in a 2d-grid (rows, cols, channels, px, py)
patches = KTH.reshape(
patches,
(batch, num_rows, num_cols, num_channels, patch_size, patch_size))
if dim_ordering == "tf":
patches = KTH.permute_dimensions(patches, [0, 1, 2, 4, 5, 3])
return patches
