Jinwoo Hwang jinuhwang
tetebueno
/ google_photos_takeout_metadata_resolver.py
Created
February 18, 2021 13:39
Google Photos Takeout archive holds a JSON file with photo/video metadata, thing is that the naming for this JSON file is not always so obvious. This takes care of resolving the name with all the variants I found so far.
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
| import re as _re | |
| import json as _json | |
| JSON_EXTENSION = '.json' | |
| def find_json_for_file(file: Path): | |
| try: | |
| if file.with_name(file.name + JSON_EXTENSION).is_file(): | |
| # file.jpg -> file.jpg.json | |
| the_json_path = file.with_name(file.name + JSON_EXTENSION) |
wassname
/ jaccard_coef_loss.py
Last active
January 30, 2024 15:45
jaccard_coef_loss for keras. This loss is usefull when you have unbalanced classes within a sample such as segmenting each pixel of an image. For example you are trying to predict if each pixel is cat, dog, or background. You may have 80% background, 10% dog, and 10% cat. Should a model that predicts 100% background be 80% right, or 30%? Categor…
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
| from keras import backend as K | |
| def jaccard_distance_loss(y_true, y_pred, smooth=100): | |
| """ | |
| Jaccard = (|X & Y|)/ (|X|+ |Y| - |X & Y|) | |
| = sum(|A*B|)/(sum(|A|)+sum(|B|)-sum(|A*B|)) | |
| The jaccard distance loss is usefull for unbalanced datasets. This has been | |
| shifted so it converges on 0 and is smoothed to avoid exploding or disapearing | |
| gradient. |