Updated version of libraries leads to decline in accuracy.
Open
- Dominant language
- Jupyter Notebook
- Stars
- 25.6k
- Forks
- 12.7k
- PR merge metrics
- No merged PRs in 30d
Description
I ran extra_capsnets.ipynb about 2 months ago 2/3/19 on google colab and the accuracies were coming as mentioned. But when I ran the same code today 5/5/19, the accuracy came down to (9.8200%). I believe, this might be due to an update in the version of libraries in Google colab.
Below is current version of libraries in google colab that i am using :-
TF: 1.13.1
Python: sys.version_info(major=3, minor=6, micro=7, releaselevel='final', serial=0)
NumPy: 1.16.3
The Answer: 42
GPU: False
Could you please let me know, which version update is causing this issue.
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.