wassname/attentive-neural-processes
1
0
Fork 0
mirror of https://github.com/wassname/attentive-neural-processes.git synced 2026-06-27 16:44:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

replication docs

Browse Source
This commit is contained in:
wassname
2020-02-01 20:38:33 +08:00
parent 38de61e2a3
commit 0834fd4e77
3 changed files with 12 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/deepmind1.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 16 KiB

docs/replicate2.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 12 KiB

readme.md
+12
View File
@@ -71,6 +71,18 @@ Changes for stability:
- use batchnorm and dropout on channel dimensions
- check and skip nonfinite values because for extreme inputs we can still get nan's
## Replicating tensorflow behaviour
I put some work into replicating the behaviour shown in the [original deepmind tensorflow notebook](https://github.com/deepmind/neural-processes/blob/master/attentive_neural_process.ipynb).
Compare deepmind:
- ![](docs/deepmind1.png)
And this repo (anp_1d_regression.ipynb)
- ![](docs/replicate2.png)
It's just a qualitative comparison but we see the same kind of overfitting with uncertainty being tight where lots of data points exist, and wide where they do not. However this repo seems to miss points occasionally.
## See also: