-
For support and discussions, please use our [Discourse forums](https://discourse.mozilla.org/c/deep-speech).
If you've found a bug, or have a feature request, then please create an issue with the f…
-
As we mentioned in #814 #867 , I download 2 weights:
72ea669da5f491458cb5dfc44a80f0e760a9df71a8d0690b185822de49e00cb3.txt
af3c6e330b932c97b0e517ac7db544d37fe1d18184f101d4b0340ff02f51ce88.txt
And…
-
when you comput Q Algorithm 1 in your paper, did you use the normalization technique? because the Q seems to be very small.
lxtGH updated
6 years ago
-
### Describe the problem
It is a feature request, and should be very related to the current high memory cost of tensorflow.
In my case, I am building a graph which I should be able to compute g…
bobye updated
6 years ago
-
There was discussion in slack about trying different loss functions. I pasted the conversation below but here are the ideas mentioned
1. @activatedgeek suggested using fully connected layer with on…
jlewi updated
5 years ago
-
Hi,
I am reading you code and try to understand any single piece. For backward, I got confused on calculating the gradient respect to binary weight. What is the definition of gradient to the discre…
-
Hello,
Thank you a lot for your work.
I'm wondering your network learns also features vector of each superpixel or it just learn the superpixels.
If yes, how can l get them otherwise you keep j…
-
Issue created by migration from Trac.
Original creator: anton
Original creation time: 2009-02-19 11:40:27
Assignee: ipopt-team
Version: 3.5
I have written an interface to Ipopt, which enables its…
-
In this build, we should have only LandIce and DemoPDEs enabled, as the option is not guaranteed to work with other physics. A good candidate for such a build is Albany64BitClang which, starting toni…
-
In graph mode, if I re-evaluate a random variable, I get a new sample. If I update a variable parameter, I get a new sample with that parameter:
```python
import tensorflow as tf
import tensorflo…