-
Hey, I'm getting an error in the convolutional autoencoder on the line tf.nn.deconv2d
"AttributeError: 'module' object has no attribute 'deconv2d'"
Also it isn't in the docs.
https://www.tensorflow.…
-
Are there any plans for implementing unpooling layers for convolutional autoencoders or FCN's, like the ones described in section 3.2.1 in Hoh - "Learning Deconvolution Network for Semantic Segmentati…
-
I believe that there is an error when using `phase` in the `default_scope` coupled with `batch_normalize=True`.
Basically it looks like this:
``` python
def encoder(self, inputs, latent_size, a…
-
Is it possible to set y equal to a 2D array for DataIterator? Based on the documentation, it looks like DataIterator expects a #ofexamples x 1 array for y.
I am looking to have a #ofexamples x 8 x 24…
-
Can this be used to predict what is written in an image? If so, how would I do that?
Thanks.
-
Hi viorik,
If I want to get a better performance, I should add more conv layers, right? Can you show me how to do this to encoder and decoder?
Thanks,
Yingjun
-
Is any way to connect an Affine layer to a Deconv layer? Like though a reshape layer or something? There seems to be issues with Affine layers not having a third dimension.
Thanks!
-
@viorik I was able to install the package (added installation instructions to the Wiki) and I am now trying to test it on a simple example, which is an adaptation of this example:
https://github.com/t…
-
A Lasagne user found a problem with nondeterministic results for a convolutional autoencoder (discussion at https://groups.google.com/d/msg/lasagne-users/bfPPuQBBzmM/TatY1IuZBAAJ).
He provided a demo…
-
Hello there!
I'm trying your (needless to say) awesome, codebase, and i wonder just 2 things :
- Why omitting the batch norm layer at the end in your models? it seems you put batch normalization bef…