Benjamin_Loison/Robust_image_source_identification_on_modern_smartphones
1
0
Fork 0
Code Issues 69 Pull Requests Packages Projects Releases 1 Wiki Activity

Precise purpose of a part of code

Browse Source
This commit is contained in:
Benjamin Loison
2024-05-13 03:13:58 +02:00
parent 3f7b6bf21a
commit 6ed57bc477
1 changed files with 1 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
datasets/raise/attribute_source_camera.py
View File

@@ -96,8 +96,7 @@ returnSingleColorChannelImage = lambda singleColorChannelImage, _minColor, _maxC
# - the second one is about estimating better and better the PRNU of each camera, as consider more and more training images and measuring the resulting attribution of cameras # - the second one is about estimating better and better the PRNU of each camera, as consider more and more training images and measuring the resulting attribution of cameras
for computeExtremes in tqdm(([True] if minColor is None or maxColor is None else []) + [False], 'Compute extremes'): for computeExtremes in tqdm(([True] if minColor is None or maxColor is None else []) + [False], 'Compute extremes'):
rescaleIfNeeded = returnSingleColorChannelImage if computeExtremes else rescaleRawImageForDenoiser rescaleIfNeeded = returnSingleColorChannelImage if computeExtremes else rescaleRawImageForDenoiser
# As the second loop firstly compute noises of testing images. # As the second loop firstly if the denoiser is not `MEAN` or if `MEAN` predicts only on the whole training set, then compute noises of testing images.
# What about `MEAN` denoiser condition?
if not computeExtremes: if not computeExtremes:
print(f'{minColor=} {maxColor=}') print(f'{minColor=} {maxColor=}')
if DENOISER != Denoiser.MEAN or PREDICT_ONLY_ON_WHOLE_TRAINING_SET: if DENOISER != Denoiser.MEAN or PREDICT_ONLY_ON_WHOLE_TRAINING_SET: