Hi Fred,
I installed the Theano version that contains "Adding an AbstractConv3d
interface #4862" https://github.com/Theano/Theano/pull/4862
<https://www.google.com/url?q=https%3A%2F%2Fgithub.com%2FTheano%2FTheano%2Fpull%2F4862&sa=D&sntz=1&usg=AFQjCNFQrOrtn25ECqWBKo3SBerQDq46cA>
but now it doesn't work because in the previous Theano version, class Pool
had these parameters: ds, ignore_border, st, padding, mode,openmp
in the latest Theano version class Pool there is no ds: only
ignore_border, mode,openmp.
In maxpool3d.py I was calling op = DownsampleFactorMax((ds[1],ds[2]),
ignore_border) where DownsampleFactorMax = pool.Pool
I tried Pool(mode=..., ...)(input, ws=ws) but it doesn't work.
How can I call Pool passing (ds[1],ds[2]) ?
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)
