do you want 2d or 3d pooling? We merged (today I think) a good interface for pool 3d: theano.tensor.signal.pool.pool_3d()
that would be better then using the 2d pooling to mimic 3d pooling. On Wed, Oct 12, 2016 at 8:12 AM, <luca.wagner.0...@gmail.com> wrote: > Hi Pascal, > Input dimension is 5; > problem fixed: I use pool_2d code > thanks > > On Tuesday, October 11, 2016 at 4:43:58 PM UTC+2, Pascal Lamblin wrote: >> >> Hi, >> >> The code throwing the exception is: >> > if x.type.ndim != 4: >> > raise TypeError() >> >> What is the number of dimensions of 'input' in your case? >> >> Usually, the `pool_2d` helper function takes care of reshaping the input >> if necessary, and passing correctly ws/ds to the underlying Op. Is there >> any reason in particular you are calling Pool directly? >> >> Also, please note that if you edit your post in the web interface, it >> sends a new message to the list each time. >> >> On Tue, Oct 11, 2016, luca.wag...@gmail.com wrote: >> > >> > 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 theano-users...@googlegroups.com. >> > 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) >> >> -- >> Pascal >> > -- > > --- > 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 theano-users+unsubscr...@googlegroups.com. > For more options, visit https://groups.google.com/d/optout. > -- --- 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 theano-users+unsubscr...@googlegroups.com. For more options, visit https://groups.google.com/d/optout.
