Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Trim training 101

This commit is contained in:
Matthew Honnibal 2020-07-26 13:43:22 +02:00
parent e6a7deb7cc
commit fb5dbe30b5
1 changed files with 1 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
website/docs/usage/101/_training.md
View File

@ -38,7 +38,4 @@ it's learning the right things, you don't only need **training data** – you'll
also need **evaluation data**. If you only test the model with the data it was also need **evaluation data**. If you only test the model with the data it was
trained on, you'll have no idea how well it's generalizing. If you want to train trained on, you'll have no idea how well it's generalizing. If you want to train
a model from scratch, you usually need at least a few hundred examples for both a model from scratch, you usually need at least a few hundred examples for both
training and evaluation. A good rule of thumb is that you should have 10 training and evaluation.
samples for each significant figure of accuracy you report.
If you only have 100 samples and your model predicts 92 of them correctly, you
would report accuracy of 0.9 rather than 0.92.