This repository has been archived by the owner on Aug 14, 2021. It is now read-only.

Splitting the input training pairs into train-test #10

Open

soumendrak opened this issue Nov 22, 2019 · 0 comments

Assignees

Labels

good first issue

Milestone

Feb-20/02/2020 re...

Owner

soumendrak commented Nov 22, 2019 •

edited

Loading

What?
The finalized input pairs need to be further split into Train-Test pairs.
May be we will start with 80% train and 20% test pairs.

Why?
This is needed to evaluate the translation accuracy by the model itself before going to live. To let us know where do we stand.

Blocked by: Issue #9

soumendrak self-assigned this

soumendrak added this to the Feb-02/02/2020 release milestone

soumendrak added the good first issue label

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.