-
Hello,
I am a researcher in optimization and I trying to write a custom optimizer. I have come across a problem.
Take any optimizer code, say just copy SGD. In the beginning of get_updates, y…
-
現在`portfolio.yml`の`skill_levels`のしたにある`elements`の中に`title`がありますが、`structure.yml`と比べると`element`が方がもっと正しいと思いますが、確認お願いします。
```yml
# before
- title: C言語
level: 1
years: 1
explanation: |
…
-
https://github.com/amunmt/marian/blob/master/src/training/graph_group.h line 73
Should we put cudaStreamSynchronize(0) here? I believe Cuda operations do not block CPU, thus you will finish the pu…
afaji updated
7 years ago
-
I want to ask something about this part in policy network example:
```
loss = -tf.reduce_mean((tf.log(input_y - probability)) * advantages)
newGrads = tf.gradients(loss,tvars)
adam = tf.train.AdamO…
-
I stucked with this problem. I want to check if gradients or variables are NaN before applying them. Print conditionally the name of the variable and a value for both gradient and variable.
### Envir…