[GitHub] [incubator-mxnet] thomelane commented on a change in pull request #15197: Updated Image Augmentation tutorial to use Gluon Transforms.

[GitBox <gi...@apache.org>]

thomelane commented on a change in pull request #15197: Updated Image Augmentation tutorial to use Gluon Transforms.
URL: https://github.com/apache/incubator-mxnet/pull/15197#discussion_r293509477
 
 

 ##########
 File path: docs/tutorials/gluon/data_augmentation.md
 ##########
 @@ -15,102 +15,220 @@
 <!--- specific language governing permissions and limitations -->
 <!--- under the License. -->
 
-# Methods of applying data augmentation (Gluon API)
+# Image Augmentation
 
-Data Augmentation is a regularization technique that's used to avoid overfitting when training Machine Learning models. Although the technique can be applied in a variety of domains, it's very common in Computer Vision. Adjustments are made to the original images in the training dataset before being used in training. Some example adjustments include translating, cropping, scaling, rotating, changing brightness and contrast. We do this to reduce the dependence of the model on spurious characteristics; e.g. training data may only contain faces that fill 1/4 of the image, so the model trained without data augmentation might unhelpfully learn that faces can only be of this size.
+Augmentation is the process of randomly adjusting samples of your dataset to create new samples that can also be used for neural network training. It increases the variety of samples seen during training and this helps the network avoid overfitting and using spurious characteristics of the dataset.
 
 Review comment:
   rephrased this whole section.

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services