Practical Weak Supervision by Wee Hyong Tok & Amit Bahree & Senja Filipi

Practical Weak Supervision by Wee Hyong Tok & Amit Bahree & Senja Filipi

Author:Wee Hyong Tok & Amit Bahree & Senja Filipi [Wee Hyong Tok]
Language: eng
Format: epub
Publisher: O'Reilly Media, Inc.
Published: 2021-10-06T16:00:00+00:00


accuracy = label_model.score(L_valid, Y_valid, metrics=["accuracy"]) {'accuracy': 0.75377}

Given that our image classifiers used for the labeling functions were trained on small sets of data, and the fact that we were only looking for the words outdoor or indoor among the tags returned by the Computer Vision API, for the other two labeling functions an accuracy of 75% is pretty good.

It would not be hard to improve upon it following the same principles and build simpler image classifiers with more data or add more labeling functions that look for more tags related to outdoor and indoor, among other tags returned from the Computer Vision API.



Download



Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.