Adding a CNN-based classifier for the task of entries/other classification #5
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
benlaurie
reviewed
Mar 2, 2018
classification/model.py
Outdated
| model.add(Activation('relu')) | ||
| model.add(Conv2D(32, (3, 3))) | ||
| model.add(BatchNormalization()) | ||
| model.add(Activation('relu')) |
There was a problem hiding this comment.
Why is indentation change not causing Python to vomit?
There was a problem hiding this comment.
Oh well. Not sure how I missed it :(
Fixed it now
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Addresses issue #2
I've implemented a small, basic CNN for this task of classification. Images have been resized to a convenient shape, with their colors stripped off. I've added measures to take care of the small amount of data as well as the variations in it; using batch normalization, low learning rates.
In addition to this, I've also used a class-balanced error while training (to account for the class imbalance).
Using the classifier at my end, I achieved a test accuracy of 86.55% and no over-fitting.