wassname/attentive-neural-processes
1
0
Fork 0
mirror of https://github.com/wassname/attentive-neural-processes.git synced 2026-06-27 18:22:31 +08:00
Code Issues Packages Projects Releases Wiki Activity

baseline image

Browse Source
This commit is contained in:
wassname
2019-11-04 10:48:28 +08:00
parent 679ffcbc6d
commit c8f7f7f5c7
3 changed files with 4 additions and 3152 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/lstm_with_context.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 38 KiB

readme.md
+4
View File
@@ -38,6 +38,10 @@ I chose an test set example the deviates from the previous pattern. Given 3 days
![](docs/19.png)
Compare this to a quick LSTM baseline, which didn't predict this divergance from the pattern. (Bear in mind that I didn't tweak this model as much). The uncertainty and prediction are also less smooth.
![](docs/lstm_with_context.png)
## Code
This is based on the code listed in the next section, with some changes. The most notable ones add stability, others are to make sure it can handle predicting into the future:
smartmeters-lstm_baseline.ipynb
-3152
View File
File diff suppressed because one or more lines are too long