Hi Pascal,
in maxpool3d.py
I tried op = pool.Pool(ignore_border=False, mode='max', openmp=None)(input,
ws=(ds[1],ds[2]))
instead of op = pool.Pool((ds[1],ds[2]), ignore_border) that worked in the
previous Theano version.
This is the output :
Python 2.7.12 |Anaconda custom (64-bit)| (default, Jul 2 2016, 17:42:40)
[GCC 4.4.7 20120313 (Red Hat 4.4.7-1)] on linux2
Type "help", "copyright", "credits" or "license" for more information.
Anaconda is brought to you by Continuum Analytics.
Please check out: http://continuum.io/thanks and https://anaconda.org
>>> runfile('/home/luca/data/
DeepLearningTutorials/Theano-3D-ConvNet-master/convnet3d/core/run_multi_conv_t.py',
wdir='/home/luca/data/DeepLearningTutorials/Theano-3D-ConvNet-master/convnet3d/core')
Using gpu device 0: GeForce 840M (CNMeM is disabled, cuDNN 5103)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File
"/home/luca/anaconda2/lib/python2.7/site-packages/spyderlib/widgets/externalshell/sitecustomize.py",
line 714, in runfile
execfile(filename, namespace)
File
"/home/luca/anaconda2/lib/python2.7/site-packages/spyderlib/widgets/externalshell/sitecustomize.py",
line 81, in execfile
builtins.execfile(filename, *where)
File
"/home/luca/data/DeepLearningTutorials/Theano-3D-ConvNet-master/convnet3d/core/run_multi_conv_t.py",
line 32, in <module>
run_experiments()
File
"/home/luca/data/DeepLearningTutorials/Theano-3D-ConvNet-master/convnet3d/core/run_multi_conv_t.py",
line 25, in run_experiments
Learning_rate=0.001
File "mpr_convnet_class_t.py", line 176, in __init__
self.pool_layer_dim))
File "convnet3d.py", line 255, in __init__
out = max_pool_3d(input,pool_shape)
File "maxpool3d.py", line 53, in max_pool_3d
op = Pool(ignore_border=False, mode='max', openmp=None)(input,
ws=(ds[1],ds[2]))
File "/home/luca/data/Theano-master/theano/gof/op.py", line 602, in
__call__
node = self.make_node(*inputs, **kwargs)
File "/home/luca/data/Theano-master/theano/tensor/signal/pool.py", line
293, in make_node
raise TypeError()
TypeError
Many thanks
Luca
--
---
You received this message because you are subscribed to the Google Groups
"theano-users" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
For more options, visit https://groups.google.com/d/optout.
""" Max pooling spatio-temporal inputs for Theano """
from theano import tensor
from theano.tensor.signal.downsample import DownsampleFactorMax
#it was originally ignore_border=False and then corrected as suggested by Pascal
'''Pascal update on ignore_border'''
def max_pool_3d(input, ds, ignore_border=True):
"""
Takes as input a N-D tensor, where N >= 3. It downscales the input video by
the specified factor, by keeping only the maximum value of non-overlapping
patches of size (ds[0],ds[1],ds[2]) (time, height, width)
:type input: N-D theano tensor of input images.
:param input: input images. Max pooling will be done over the 3 last dimensions.
:type ds: tuple of length 3
:param ds: factor by which to downscale. (2,2,2) will halve the video in each dimension.
:param ignore_border: boolean value. When True, (5,5,5) input with ds=(2,2,2) will generate a
(2,2,2) output. (3,3,3) otherwise.
"""
if input.ndim < 3:
raise NotImplementedError('max_pool_3d requires a dimension >= 3')
# extract nr dimensions
vid_dim = input.ndim
# max pool in two different steps, so we can use the 2d implementation of
# downsamplefactormax. First maxpool frames as usual.
# Then maxpool the time dimension. Shift the time dimension to the third
# position, so rows and cols are in the back
# extract dimensions
frame_shape = input.shape[-2:]
# count the number of "leading" dimensions, store as dmatrix
# tensor.prod: product of every term in x along axis
batch_size = tensor.prod(input.shape[:-2])
# Reshape x by right padding the shape with n_ones 1s.
batch_size = tensor.shape_padright(batch_size,1)
# store as 4D tensor with shape: (batch_size,1,height,width)
#tensor.cast
# Cast any tensor x to a Tensor of the same shape, but with a different numerical type dtype.
new_shape = tensor.cast(tensor.join(0, batch_size,
tensor.as_tensor([1,]),
frame_shape), 'int32')
input_4D = tensor.reshape(input, new_shape, ndim=4)
# downsample mini-batch of videos in rows and cols
op = DownsampleFactorMax((ds[1],ds[2]), ignore_border)
output = op(input_4D)
# restore to original shape
outshape = tensor.join(0, input.shape[:-2], output.shape[-2:])
out = tensor.reshape(output, outshape, ndim=input.ndim)
# now maxpool time
# output (time, rows, cols), reshape so that time is in the back
shufl = (list(range(vid_dim-3)) + [vid_dim-2]+[vid_dim-1]+[vid_dim-3])
input_time = out.dimshuffle(shufl)
# reset dimensions
vid_shape = input_time.shape[-2:]
# count the number of "leading" dimensions, store as dmatrix
batch_size = tensor.prod(input_time.shape[:-2])
batch_size = tensor.shape_padright(batch_size,1)
# store as 4D tensor with shape: (batch_size,1,width,time)
new_shape = tensor.cast(tensor.join(0, batch_size,
tensor.as_tensor([1,]),
vid_shape), 'int32')
input_4D_time = tensor.reshape(input_time, new_shape, ndim=4)
# downsample mini-batch of videos in time
op = DownsampleFactorMax((1,ds[0]), ignore_border)
outtime = op(input_4D_time)
# output
# restore to original shape (xxx, rows, cols, time)
outshape = tensor.join(0, input_time.shape[:-2], outtime.shape[-2:])
shufl = (list(range(vid_dim-3)) + [vid_dim-1]+[vid_dim-3]+[vid_dim-2])
return tensor.reshape(outtime, outshape, ndim=input.ndim).dimshuffle(shufl)
