-
Normally in Tensorflow, if I wanted to prevent my processes from using as much vram as they should consume I would do something like:
`opts = tf.GPUOptions(per_process_gpu_memory_fraction=0.5) `
`…
-
Need to add Y410 in vaCreateImage and vaPutImage.
When decode a hevc 444 10bit stream by gst-vaapi, will reproduce this issue:
root@icl_vpg_kernel:~/media# gst-launch-1.0 filesrc location=Main4…
-
```
from garage.experiment import LocalRunner, run_experiment
from garage.np.baselines import LinearFeatureBaseline
from garage.tf.algos import TRPO
from garage.tf.envs import TfEnv
from garage.t…
-
On this page: https://spinningup.openai.com/en/latest/spinningup/rl_intro2.html
More specifically in this diagram: https://spinningup.openai.com/en/latest/_images/rl_algorithms_9_15.svg
I am sur…
-
We see that media driver (https://github.com/intel/media-driver/blob/master/README.md ) should support WHL (Whiskey Lake) platform. But we cannot have video playback work on WHL and got below error me…
-
Hello,
I was looking at network architecture for the VPG code. Upon receiving the logits I saw the line:
```
pi = tf.squeeze(tf.multinomial(logits,1), axis=1)
```
According to me, this sam…
-
I found out today that if you try to use a list or a map with a conditional, you get the error:
```
* At column 3, line 1: conditional operator cannot be used with list values in:
```
It turns…
-
Hi @jachiam , thanks for making this public ! I'm using this code to learn how to implement VPG and I noticed that you use reward to go as your batch advantage, but shouldn't advantage be the differen…
-
1. check if ground coordinates are correct.
2. optimize code - currently 0.01s, still too slow - should be faster than lane_extension_for_MultiNet!
3. Integrating all code into a single python code;…
-
Check if there's content replication between staging and prod.
anvmn updated
5 years ago