Python theano.tensor.signal.pool.pool_3d() Examples
The following are 10
code examples of theano.tensor.signal.pool.pool_3d().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
theano.tensor.signal.pool
, or try the search function
.
.
Example #1
| Source File: theano_backend.py From GraphicDesignPatternByPython with MIT License | 4 votes |
|
def pool3d(x, pool_size, strides=(1, 1, 1), padding='valid',
data_format=None, pool_mode='max'):
data_format = normalize_data_format(data_format)
if padding == 'same':
w_pad = pool_size[0] - 2 if pool_size[0] % 2 == 1 else pool_size[0] - 1
h_pad = pool_size[1] - 2 if pool_size[1] % 2 == 1 else pool_size[1] - 1
d_pad = pool_size[2] - 2 if pool_size[2] % 2 == 1 else pool_size[2] - 1
pad = (w_pad, h_pad, d_pad)
elif padding == 'valid':
pad = (0, 0, 0)
else:
raise ValueError('Invalid padding:', padding)
if data_format == 'channels_last':
x = x.dimshuffle((0, 4, 1, 2, 3))
if pool_mode == 'max':
pool_out = pool.pool_3d(x, ws=pool_size, stride=strides,
ignore_border=True,
pad=pad,
mode='max')
elif pool_mode == 'avg':
pool_out = pool.pool_3d(x, ws=pool_size, stride=strides,
ignore_border=True,
pad=pad,
mode='average_exc_pad')
else:
raise ValueError('Invalid pooling mode:', pool_mode)
if padding == 'same':
expected_width = (x.shape[2] + strides[0] - 1) // strides[0]
expected_height = (x.shape[3] + strides[1] - 1) // strides[1]
expected_depth = (x.shape[4] + strides[2] - 1) // strides[2]
pool_out = pool_out[:, :,
: expected_width,
: expected_height,
: expected_depth]
if data_format == 'channels_last':
pool_out = pool_out.dimshuffle((0, 2, 3, 4, 1))
return pool_out
Example #2
| Source File: theano_backend.py From DeepLearning_Wavelet-LSTM with MIT License | 4 votes |
|
def pool3d(x, pool_size, strides=(1, 1, 1), padding='valid',
data_format=None, pool_mode='max'):
if data_format is None:
data_format = image_data_format()
if data_format not in {'channels_first', 'channels_last'}:
raise ValueError('Unknown data_format:', data_format)
if padding == 'same':
w_pad = pool_size[0] - 2 if pool_size[0] % 2 == 1 else pool_size[0] - 1
h_pad = pool_size[1] - 2 if pool_size[1] % 2 == 1 else pool_size[1] - 1
d_pad = pool_size[2] - 2 if pool_size[2] % 2 == 1 else pool_size[2] - 1
pad = (w_pad, h_pad, d_pad)
elif padding == 'valid':
pad = (0, 0, 0)
else:
raise ValueError('Invalid padding:', padding)
if data_format == 'channels_last':
x = x.dimshuffle((0, 4, 1, 2, 3))
if pool_mode == 'max':
pool_out = pool.pool_3d(x, ws=pool_size, stride=strides,
ignore_border=True,
pad=pad,
mode='max')
elif pool_mode == 'avg':
pool_out = pool.pool_3d(x, ws=pool_size, stride=strides,
ignore_border=True,
pad=pad,
mode='average_exc_pad')
else:
raise ValueError('Invalid pooling mode:', pool_mode)
if padding == 'same':
expected_width = (x.shape[2] + strides[0] - 1) // strides[0]
expected_height = (x.shape[3] + strides[1] - 1) // strides[1]
expected_depth = (x.shape[4] + strides[2] - 1) // strides[2]
pool_out = pool_out[:, :,
: expected_width,
: expected_height,
: expected_depth]
if data_format == 'channels_last':
pool_out = pool_out.dimshuffle((0, 2, 3, 4, 1))
return pool_out
Example #3
| Source File: theano_backend.py From DeepLearning_Wavelet-LSTM with MIT License | 4 votes |
|
def pool3d(x, pool_size, strides=(1, 1, 1), padding='valid',
data_format=None, pool_mode='max'):
if data_format is None:
data_format = image_data_format()
if data_format not in {'channels_first', 'channels_last'}:
raise ValueError('Unknown data_format:', data_format)
if padding == 'same':
w_pad = pool_size[0] - 2 if pool_size[0] % 2 == 1 else pool_size[0] - 1
h_pad = pool_size[1] - 2 if pool_size[1] % 2 == 1 else pool_size[1] - 1
d_pad = pool_size[2] - 2 if pool_size[2] % 2 == 1 else pool_size[2] - 1
pad = (w_pad, h_pad, d_pad)
elif padding == 'valid':
pad = (0, 0, 0)
else:
raise ValueError('Invalid padding:', padding)
if data_format == 'channels_last':
x = x.dimshuffle((0, 4, 1, 2, 3))
if pool_mode == 'max':
pool_out = pool.pool_3d(x, ws=pool_size, stride=strides,
ignore_border=True,
pad=pad,
mode='max')
elif pool_mode == 'avg':
pool_out = pool.pool_3d(x, ws=pool_size, stride=strides,
ignore_border=True,
pad=pad,
mode='average_exc_pad')
else:
raise ValueError('Invalid pooling mode:', pool_mode)
if padding == 'same':
expected_width = (x.shape[2] + strides[0] - 1) // strides[0]
expected_height = (x.shape[3] + strides[1] - 1) // strides[1]
expected_depth = (x.shape[4] + strides[2] - 1) // strides[2]
pool_out = pool_out[:, :,
: expected_width,
: expected_height,
: expected_depth]
if data_format == 'channels_last':
pool_out = pool_out.dimshuffle((0, 2, 3, 4, 1))
return pool_out
Example #4
| Source File: theano_backend.py From DeepLearning_Wavelet-LSTM with MIT License | 4 votes |
|
def pool3d(x, pool_size, strides=(1, 1, 1), padding='valid',
data_format=None, pool_mode='max'):
if data_format is None:
data_format = image_data_format()
if data_format not in {'channels_first', 'channels_last'}:
raise ValueError('Unknown data_format:', data_format)
if padding == 'same':
w_pad = pool_size[0] - 2 if pool_size[0] % 2 == 1 else pool_size[0] - 1
h_pad = pool_size[1] - 2 if pool_size[1] % 2 == 1 else pool_size[1] - 1
d_pad = pool_size[2] - 2 if pool_size[2] % 2 == 1 else pool_size[2] - 1
pad = (w_pad, h_pad, d_pad)
elif padding == 'valid':
pad = (0, 0, 0)
else:
raise ValueError('Invalid padding:', padding)
if data_format == 'channels_last':
x = x.dimshuffle((0, 4, 1, 2, 3))
if pool_mode == 'max':
pool_out = pool.pool_3d(x, ws=pool_size, stride=strides,
ignore_border=True,
pad=pad,
mode='max')
elif pool_mode == 'avg':
pool_out = pool.pool_3d(x, ws=pool_size, stride=strides,
ignore_border=True,
pad=pad,
mode='average_exc_pad')
else:
raise ValueError('Invalid pooling mode:', pool_mode)
if padding == 'same':
expected_width = (x.shape[2] + strides[0] - 1) // strides[0]
expected_height = (x.shape[3] + strides[1] - 1) // strides[1]
expected_depth = (x.shape[4] + strides[2] - 1) // strides[2]
pool_out = pool_out[:, :,
: expected_width,
: expected_height,
: expected_depth]
if data_format == 'channels_last':
pool_out = pool_out.dimshuffle((0, 2, 3, 4, 1))
return pool_out
Example #5
| Source File: theano_backend.py From DeepLearning_Wavelet-LSTM with MIT License | 4 votes |
|
def pool3d(x, pool_size, strides=(1, 1, 1), padding='valid',
data_format=None, pool_mode='max'):
if data_format is None:
data_format = image_data_format()
if data_format not in {'channels_first', 'channels_last'}:
raise ValueError('Unknown data_format:', data_format)
if padding == 'same':
w_pad = pool_size[0] - 2 if pool_size[0] % 2 == 1 else pool_size[0] - 1
h_pad = pool_size[1] - 2 if pool_size[1] % 2 == 1 else pool_size[1] - 1
d_pad = pool_size[2] - 2 if pool_size[2] % 2 == 1 else pool_size[2] - 1
pad = (w_pad, h_pad, d_pad)
elif padding == 'valid':
pad = (0, 0, 0)
else:
raise ValueError('Invalid padding:', padding)
if data_format == 'channels_last':
x = x.dimshuffle((0, 4, 1, 2, 3))
if pool_mode == 'max':
pool_out = pool.pool_3d(x, ws=pool_size, stride=strides,
ignore_border=True,
pad=pad,
mode='max')
elif pool_mode == 'avg':
pool_out = pool.pool_3d(x, ws=pool_size, stride=strides,
ignore_border=True,
pad=pad,
mode='average_exc_pad')
else:
raise ValueError('Invalid pooling mode:', pool_mode)
if padding == 'same':
expected_width = (x.shape[2] + strides[0] - 1) // strides[0]
expected_height = (x.shape[3] + strides[1] - 1) // strides[1]
expected_depth = (x.shape[4] + strides[2] - 1) // strides[2]
pool_out = pool_out[:, :,
: expected_width,
: expected_height,
: expected_depth]
if data_format == 'channels_last':
pool_out = pool_out.dimshuffle((0, 2, 3, 4, 1))
return pool_out
Example #6
| Source File: theano_backend.py From DeepLearning_Wavelet-LSTM with MIT License | 4 votes |
|
def pool3d(x, pool_size, strides=(1, 1, 1), padding='valid',
data_format=None, pool_mode='max'):
if data_format is None:
data_format = image_data_format()
if data_format not in {'channels_first', 'channels_last'}:
raise ValueError('Unknown data_format:', data_format)
if padding == 'same':
w_pad = pool_size[0] - 2 if pool_size[0] % 2 == 1 else pool_size[0] - 1
h_pad = pool_size[1] - 2 if pool_size[1] % 2 == 1 else pool_size[1] - 1
d_pad = pool_size[2] - 2 if pool_size[2] % 2 == 1 else pool_size[2] - 1
pad = (w_pad, h_pad, d_pad)
elif padding == 'valid':
pad = (0, 0, 0)
else:
raise ValueError('Invalid padding:', padding)
if data_format == 'channels_last':
x = x.dimshuffle((0, 4, 1, 2, 3))
if pool_mode == 'max':
pool_out = pool.pool_3d(x, ws=pool_size, stride=strides,
ignore_border=True,
pad=pad,
mode='max')
elif pool_mode == 'avg':
pool_out = pool.pool_3d(x, ws=pool_size, stride=strides,
ignore_border=True,
pad=pad,
mode='average_exc_pad')
else:
raise ValueError('Invalid pooling mode:', pool_mode)
if padding == 'same':
expected_width = (x.shape[2] + strides[0] - 1) // strides[0]
expected_height = (x.shape[3] + strides[1] - 1) // strides[1]
expected_depth = (x.shape[4] + strides[2] - 1) // strides[2]
pool_out = pool_out[:, :,
: expected_width,
: expected_height,
: expected_depth]
if data_format == 'channels_last':
pool_out = pool_out.dimshuffle((0, 2, 3, 4, 1))
return pool_out
Example #7
| Source File: theano_backend.py From DeepLearning_Wavelet-LSTM with MIT License | 4 votes |
|
def pool3d(x, pool_size, strides=(1, 1, 1), padding='valid',
data_format=None, pool_mode='max'):
if data_format is None:
data_format = image_data_format()
if data_format not in {'channels_first', 'channels_last'}:
raise ValueError('Unknown data_format:', data_format)
if padding == 'same':
w_pad = pool_size[0] - 2 if pool_size[0] % 2 == 1 else pool_size[0] - 1
h_pad = pool_size[1] - 2 if pool_size[1] % 2 == 1 else pool_size[1] - 1
d_pad = pool_size[2] - 2 if pool_size[2] % 2 == 1 else pool_size[2] - 1
pad = (w_pad, h_pad, d_pad)
elif padding == 'valid':
pad = (0, 0, 0)
else:
raise ValueError('Invalid padding:', padding)
if data_format == 'channels_last':
x = x.dimshuffle((0, 4, 1, 2, 3))
if pool_mode == 'max':
pool_out = pool.pool_3d(x, ws=pool_size, stride=strides,
ignore_border=True,
pad=pad,
mode='max')
elif pool_mode == 'avg':
pool_out = pool.pool_3d(x, ws=pool_size, stride=strides,
ignore_border=True,
pad=pad,
mode='average_exc_pad')
else:
raise ValueError('Invalid pooling mode:', pool_mode)
if padding == 'same':
expected_width = (x.shape[2] + strides[0] - 1) // strides[0]
expected_height = (x.shape[3] + strides[1] - 1) // strides[1]
expected_depth = (x.shape[4] + strides[2] - 1) // strides[2]
pool_out = pool_out[:, :,
: expected_width,
: expected_height,
: expected_depth]
if data_format == 'channels_last':
pool_out = pool_out.dimshuffle((0, 2, 3, 4, 1))
return pool_out
Example #8
| Source File: theano_backend.py From DeepLearning_Wavelet-LSTM with MIT License | 4 votes |
|
def pool3d(x, pool_size, strides=(1, 1, 1), padding='valid',
data_format=None, pool_mode='max'):
if data_format is None:
data_format = image_data_format()
if data_format not in {'channels_first', 'channels_last'}:
raise ValueError('Unknown data_format:', data_format)
if padding == 'same':
w_pad = pool_size[0] - 2 if pool_size[0] % 2 == 1 else pool_size[0] - 1
h_pad = pool_size[1] - 2 if pool_size[1] % 2 == 1 else pool_size[1] - 1
d_pad = pool_size[2] - 2 if pool_size[2] % 2 == 1 else pool_size[2] - 1
pad = (w_pad, h_pad, d_pad)
elif padding == 'valid':
pad = (0, 0, 0)
else:
raise ValueError('Invalid padding:', padding)
if data_format == 'channels_last':
x = x.dimshuffle((0, 4, 1, 2, 3))
if pool_mode == 'max':
pool_out = pool.pool_3d(x, ws=pool_size, stride=strides,
ignore_border=True,
pad=pad,
mode='max')
elif pool_mode == 'avg':
pool_out = pool.pool_3d(x, ws=pool_size, stride=strides,
ignore_border=True,
pad=pad,
mode='average_exc_pad')
else:
raise ValueError('Invalid pooling mode:', pool_mode)
if padding == 'same':
expected_width = (x.shape[2] + strides[0] - 1) // strides[0]
expected_height = (x.shape[3] + strides[1] - 1) // strides[1]
expected_depth = (x.shape[4] + strides[2] - 1) // strides[2]
pool_out = pool_out[:, :,
: expected_width,
: expected_height,
: expected_depth]
if data_format == 'channels_last':
pool_out = pool_out.dimshuffle((0, 2, 3, 4, 1))
return pool_out
Example #9
| Source File: theano_backend.py From deepQuest with BSD 3-Clause "New" or "Revised" License | 4 votes |
|
def pool3d(x, pool_size, strides=(1, 1, 1), padding='valid',
data_format=None, pool_mode='max'):
if data_format is None:
data_format = image_data_format()
if data_format not in {'channels_first', 'channels_last'}:
raise ValueError('Unknown data_format:', data_format)
if padding == 'same':
w_pad = pool_size[0] - 2 if pool_size[0] % 2 == 1 else pool_size[0] - 1
h_pad = pool_size[1] - 2 if pool_size[1] % 2 == 1 else pool_size[1] - 1
d_pad = pool_size[2] - 2 if pool_size[2] % 2 == 1 else pool_size[2] - 1
padding = (w_pad, h_pad, d_pad)
elif padding == 'valid':
padding = (0, 0, 0)
else:
raise ValueError('Invalid padding:', padding)
if data_format == 'channels_last':
x = x.dimshuffle((0, 4, 1, 2, 3))
if pool_mode == 'max':
pool_out = pool.pool_3d(x, ws=pool_size, stride=strides,
ignore_border=True,
pad=padding,
mode='max')
elif pool_mode == 'avg':
pool_out = pool.pool_3d(x, ws=pool_size, stride=strides,
ignore_border=True,
pad=padding,
mode='average_exc_pad')
else:
raise ValueError('Invalid pooling mode:', pool_mode)
if padding == 'same':
expected_width = (x.shape[2] + strides[0] - 1) // strides[0]
expected_height = (x.shape[3] + strides[1] - 1) // strides[1]
expected_depth = (x.shape[4] + strides[2] - 1) // strides[2]
pool_out = pool_out[:, :,
: expected_width,
: expected_height,
: expected_depth]
if data_format == 'channels_last':
pool_out = pool_out.dimshuffle((0, 2, 3, 4, 1))
return pool_out
Example #10
| Source File: theano_backend.py From keras-lambda with MIT License | 4 votes |
|
def pool3d(x, pool_size, strides=(1, 1, 1), padding='valid',
data_format=None, pool_mode='max'):
if data_format is None:
data_format = image_data_format()
if data_format not in {'channels_first', 'channels_last'}:
raise ValueError('Unknown data_format:', data_format)
if padding == 'same':
w_pad = pool_size[0] - 2 if pool_size[0] % 2 == 1 else pool_size[0] - 1
h_pad = pool_size[1] - 2 if pool_size[1] % 2 == 1 else pool_size[1] - 1
d_pad = pool_size[2] - 2 if pool_size[2] % 2 == 1 else pool_size[2] - 1
padding = (w_pad, h_pad, d_pad)
elif padding == 'valid':
padding = (0, 0, 0)
else:
raise ValueError('Invalid padding:', padding)
if data_format == 'channels_last':
x = x.dimshuffle((0, 4, 1, 2, 3))
if pool_mode == 'max':
pool_out = pool.pool_3d(x, ws=pool_size, stride=strides,
ignore_border=True,
pad=padding,
mode='max')
elif pool_mode == 'avg':
pool_out = pool.pool_3d(x, ws=pool_size, stride=strides,
ignore_border=True,
pad=padding,
mode='average_exc_pad')
else:
raise ValueError('Invalid pooling mode:', pool_mode)
if padding == 'same':
expected_width = (x.shape[2] + strides[0] - 1) // strides[0]
expected_height = (x.shape[3] + strides[1] - 1) // strides[1]
expected_depth = (x.shape[4] + strides[2] - 1) // strides[2]
pool_out = pool_out[:, :,
: expected_width,
: expected_height,
: expected_depth]
if data_format == 'channels_last':
pool_out = pool_out.dimshuffle((0, 2, 3, 4, 1))
return pool_out
