-
Notifications
You must be signed in to change notification settings - Fork 74.6k
Adds conv3d_transpose operation (3D "deconvolution") #3049
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
…ropInputV2 and Conv3DBackpropFilterV2.
Can one of the admins verify this patch? |
Thanks for your pull request. It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). 📝 Please visit https://cla.developers.google.com/ to sign. Once you've signed, please reply here (e.g.
|
I signed the CLA. |
CLAs look good, thanks! |
@ops.RegisterGradient("Conv3DBackpropInputV2") | ||
def _Conv3DBackpropInputGrad(op, grad): | ||
return [None, | ||
nn_ops.conv3d_backprop_filter_v2(grad, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
weird indentation here, should be aligned with [
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hi,
I've been looking for some useful stuff and found an interesting site with useful advices, please take a look http://agree.pumpjuice.com/e4ann
ziney2y
very nice! just a few minor comments and then we can test. |
Thanks, done. |
Thanks! |
has this been tested and verified? |
There's a test to validate correctness, yes. If you think there's a bug in the implementation, please feel free to file an issue. Thanks! |
I'm having a difficult time updating Tensorflow to include this code. I noticed that the function is in source code in the nn_ops.py file, but when I run the pip --upgrade it isn't included. Could I simply copy the function into my existing code, or does it include other dependencies? |
You could try one of the nightlies that might have this change in it: https://github.com/tensorflow/tensorflow#installation Alternatively, you could build from sources at HEAD as well. You could copy the contents of the files too, though it might be easy to get wrong. |
that had it, thanks! |
Can we fix the issue where after a transpose, the dimensions are always <?,?, ?, ?, n_classes> -- can we get rid of the question marks and make them show the actual dimension value? |
@vrv it isn't included in the Mac OSX nightly build or the build currently posted to the main install page. Is there any other way I can get it installed on my mac? I ask because of this issue on both of my linux machines *** Error in 'python': free(): invalid pointer outlined in this SO post: http://stackoverflow.com/questions/38129441/tensorflow-conv3d-transpose-error-in-python-free-invalid-pointer |
looks like no mac builds have been created for a while -- pinging @caisq who might know more. |
@vrv Do you think this a bug with the latest build, or with the development of |
I have no idea -- conv3d_transpose is just a wrapper calling an existing function that already likely worked. I think filing a bug with a reproducible small example would help (small being the clear word here -- it should be a single call to conv3d_transpose that triggers the bug, ideally). |
I opened a new issue: #3128 I wrote a small network to reproduce the issue -- I hope it was concise enough |
@vrv Mac OS nightly build still hasn't been updated -- over a month old |
I guess there's a stale link somewhere. Try these? http://ci.tensorflow.org/view/Nightly/job/nightly-matrix-cpu/156/ |
Is this feature implemented for GPU?
|
@juanprietob I'm not sure this is in production at the moment. I installed from a nightly build. See the links for nightly builds in an above comment. |
This pull request contains the following changes:
Fixes #3012 #150