Hi
I have solved my problem, my issue was in the way I read images. I created
an empty list and I appended the values of images; now, I save the memory,
I reate a zero numpy arrays of the size of the output and I save in each
vector of the matrix the value of the image. I need to do the same with
labels.
I do not know why in this way it works and appending does not work. But
maybe it could help to anyone.
El lunes, 7 de noviembre de 2016, 20:58:31 (UTC+1), Beatriz G. escribió:
>
> Hi eveyone.
>
>
> I am having the popular error TypeError: Cannot convert Type TensorType. I
> am not able to solve it using the help in other posts.
>
> I am using my own database and I am using the LENET architecture.
>
>
> This is my data. I read it in a different function image per image:
>
> croped_Scale = frame[arr:abj, izq:dcha]
> image = cv2.resize(croped_Scale, (128, 128))
> aux_vect = np.ravel(image)
> aux_X.append(aux_vect)
>
>
>
>
> And then I use it in LENET:
>
> train_set_x = theano.shared(numpy.array(train_set_x))
> test_set_x = theano.shared(numpy.array(test_set_x))
> train_set_y = theano.shared(numpy.array(y_train))
> test_set_y = theano.shared(numpy.array(y_test))
> valid_set_x = theano.shared(numpy.array(valid_set_x))
> valid_set_y = theano.shared(numpy.array(y_val))
>
>
>
> whose shape is:
>
>
> (2324, 49152) (664, 49152) (332, 49152) For samples (training, test and
> validation)
> (2324,) (664,) (332,) and for labels (training, test and validation)
>
>
>
> Here is my error: TypeError: Cannot convert Type TensorType(uint8, matrix)
> (of Variable Subtensor{int64:int64:}.0) into Type TensorType(float64,
> matrix). You can try to manually convert Subtensor{int64:int64:}.0 into a
> TensorType(float64, matrix).
> And the line where it is produced is in: y: test_set_y[index *
> batch_size: (index + 1) * batch_size]
>
>
> If use the flatten function in that way:
>
> train_set_x = theano.shared(numpy.array(train_set_x).flatten())
> test_set_x = theano.shared(numpy.array(test_set_x).flatten())
> train_set_y = theano.shared(numpy.array(y_train).flatten())
> test_set_y = theano.shared(numpy.array(y_test).flatten())
> valid_set_x = theano.shared(numpy.array(valid_set_x).flatten())
> valid_set_y = theano.shared(numpy.array(y_val).flatten())
>
>
> I get the following error:TypeError: Cannot convert Type TensorType(uint8,
> vector) (of Variable Subtensor{int64:int64:}.0) into Type TensorType(float64,
> matrix). You can try to manually convert Subtensor{int64:int64:}.0 into a
> TensorType(float64, matrix).
>
>
>
> If I force the samples to be float64 and the labels to be int32 it works,
> but I do not want to do that because it would not work with GPU because of
> the line in theanorc: floatX = float32
>
> I have been reading in the forum I have not get the solution.
>
> Anyone could help me? I would like to run the code in GPU
>
> Regards.
>
>
--
---
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.
