Hi again!
I'm not sure, but it seems that the "translation" provided an error later
in the code, because I obtained a mismatching in the shapes and size with
the following message:
*$~/VoxNet/voxnet/scripts$ python train.py config/shapenet10.py
shapenet10_train.tar*
*Using cuDNN version 5105 on context None*
*Preallocating 11583/12192 Mb (0.950000) on cuda*
*Mapped name None to device cuda: TITAN X (Pascal) (0000:02:00.0)*
*2018-05-08 09:16:36,738 INFO| Metrics will be saved to metrics.jsonl*
*2018-05-08 09:16:36,738 INFO| Compiling theano functions...*
*2018-05-08 09:16:48,771 INFO| Training...*
*Traceback (most recent call last):*
* File "train.py", line 184, in <module>*
* main(args)*
* File "train.py", line 152, in main*
* lv = tfuncs['update_iter'](bi)*
* File
"/home/anaconda2/lib/python2.7/site-packages/theano/compile/function_module.py",
line 917, in __call__*
* storage_map=getattr(self.fn, 'storage_map', None))*
* File "/home/anaconda2/lib/python2.7/site-packages/theano/gof/link.py",
line 325, in raise_with_op*
* reraise(exc_type, exc_value, exc_trace)*
* File
"/home/anaconda2/lib/python2.7/site-packages/theano/compile/function_module.py",
line 903, in __call__*
* self.fn() if output_subset is None else\*
* File "pygpu/blas.pyx", line 47, in pygpu.blas.pygpu_blas_rgemm*
*pygpu.gpuarray.GpuArrayException: ('mismatched shapes', 2)*
*Apply node that caused the error: GpuDot22(GpuReshape{2}.0, fc1.W)*
*Toposort index: 130*
*Inputs types: [GpuArrayType<None>(float32, matrix),
GpuArrayType<None>(float32, matrix)]*
*Inputs shapes: [(32, 32000), (6912, 128)]*
*Inputs strides: [(128000, 4), (512, 4)]*
*Inputs values: ['not shown', 'not shown']*
*Inputs type_num: [11, 11]*
*Outputs clients: [[GpuElemwise{Add}[(0, 0)]<gpuarray>(GpuDot22.0,
InplaceGpuDimShuffle{x,0}.0)]]*
*Backtrace when the node is created(use Theano flag traceback.limit=N to
make it longer):*
* File "train.py", line 184, in <module>*
* main(args)*
* File "train.py", line 135, in main*
* tfuncs, tvars = make_training_functions(cfg, model)*
* File "train.py", line 31, in make_training_functions*
* out = lasagne.layers.get_output(l_out, X)*
* File
"/home/anaconda2/lib/python2.7/site-packages/lasagne/layers/helper.py",
line 197, in get_output*
* all_outputs[layer] = layer.get_output_for(layer_inputs, **kwargs)*
* File
"/home/anaconda2/lib/python2.7/site-packages/lasagne/layers/dense.py", line
121, in get_output_for*
* activation = T.dot(input, self.W)*
* File "train.py", line 184, in <module>*
* main(args)*
* File "train.py", line 135, in main*
* tfuncs, tvars = make_training_functions(cfg, model)*
* File "train.py", line 31, in make_training_functions*
* out = lasagne.layers.get_output(l_out, X)*
* File
"/home/anaconda2/lib/python2.7/site-packages/lasagne/layers/helper.py",
line 197, in get_output*
* all_outputs[layer] = layer.get_output_for(layer_inputs, **kwargs)*
* File
"/home/anaconda2/lib/python2.7/site-packages/lasagne/layers/dense.py", line
121, in get_output_for*
* activation = T.dot(input, self.W)*
Do you think it is a different error?
Thank you again for any suggestion.
Il giorno giovedì 3 maggio 2018 10:12:51 UTC+2, Antonio95100 ha scritto:
>
> Hi all,
> I'm trying to train the VoxNet
> <https://github.com/dimatura/voxnet>3D/Volumetric
> Convolutional Neural Networks, based on Theano+Lasagne.
> Since I have installed Theano 1.01 and I don't want to downgrade to Theano
> 0.8.2, I modified the "max_pool_3d
> <https://github.com/dimatura/voxnet/blob/master/voxnet/max_pool_3d.py>"
> original code 'cause the *DownsampleFactorMax *module changed name in the
> latest Theano version. So I replaced the following rows:
>
> *op = T.signal.downsample.DownsampleFactorMax((ds[1], ds[2]),
> ignore_border)*
> *output = op(input_4D)*
>
> with these:
>
> *op = T.signal.pool.Pool(ignore_border)(input, ws=(ds[1],ds[2]))*
> *output = op(input_4D)*
>
> and I receive the following error message:
>
>
> *File "/home//VoxNet/voxnet/voxnet/max_pool_3d.py", line 78, in
> max_pool_3d*
> * output = op(input_4D)*
> *TypeError: 'TensorVariable' object is not callable*
>
> What is wrong in my update?
> Thank you in advance for any suggestion.
> Cheers.
>
--
---
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.
