-
Notifications
You must be signed in to change notification settings - Fork 282
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
Problems with running simple autoencoder in R keras #1037
Comments
Hi. The result (the same loss 0.69) for R and Python is the same on my OS. Can you find out from R and Python the version of Python
R
|
I have the following: Python
and R
I also checked on another OS (macOS with fresh R installation) with exactly the same result -- python version works, R version does not |
Ah, I see some catch:
and got imported the keras 2.3.1 package. While R seems to use the following:
That is the keras within tensorflow, with another version. Hmm. |
Ok, for myself I solved the problem:
uses
This is strange, though -- seems the default tensorflow keras implementation (at least in 2.0.0 tensorflow) is incompatible with tensorflow... I also notice one difference between the models created with two versions of keras. The "good" one (from keras 2.3.1) looks like:
while the "bad" one (with keras 2.2.4) looks like
I I don't know what it means, but there are brackets around Output shape of the Input layer in the "bad" vesion. |
Rose the issue in tensorflow -- it turns out to be a problem with different defaults for learning rate for Adadelta optimizer between tensorflow and standalow keras versions: |
Hello, I am trying to create a simple autoencoder.
The python version from https://blog.keras.io/building-autoencoders-in-keras.html works perfectly.
However, the version in R (see also #228 )
produces just noise in the decoded image. Also, during the fit step the loss is always ~0.69, and does not fall like in the Python version.
Any idea what the bug it may be?
I use R 3.6.3 with keras 2.2.5.0, with default tensorflow 2.0 installed via conda environment.
The first classification example from https://keras.rstudio.com/articles/getting_started.html works, by the way.
Any help would be appreciated.
The text was updated successfully, but these errors were encountered: