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

#72: Verify actual data type pointer

Browse Source
This commit is contained in:
Benjamin Loison
2024-05-13 16:10:11 +02:00
parent 50058d5d2e
commit 54178c1101
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
datasets/raise/attribute_source_camera.py
View File

@@ -32,7 +32,7 @@ for camera in IMAGES_CAMERAS_FOLDER:
random.shuffle(imagesCamerasFileNames[camera]) random.shuffle(imagesCamerasFileNames[camera])
# Limit number of images per camera with the one having the less images. # Limit number of images per camera with the one having the less images.
minimumNumberOfImagesCameras = min([len(imagesCamerasFileNames[camera]) for camera in IMAGES_CAMERAS_FOLDER]) minimumNumberOfImagesCameras = 4#min([len(imagesCamerasFileNames[camera]) for camera in IMAGES_CAMERAS_FOLDER])
for camera in IMAGES_CAMERAS_FOLDER: for camera in IMAGES_CAMERAS_FOLDER:
imagesCamerasFileNames[camera] = imagesCamerasFileNames[camera][:minimumNumberOfImagesCameras] imagesCamerasFileNames[camera] = imagesCamerasFileNames[camera][:minimumNumberOfImagesCameras]
print(camera, imagesCamerasFileNames[camera]) print(camera, imagesCamerasFileNames[camera])
@@ -143,11 +143,11 @@ for computeExtremes in tqdm(([True] if minColor is None or maxColor is None else
cameraIterativeMean.add(imagePrnuEstimateNpArray) cameraIterativeMean.add(imagePrnuEstimateNpArray)
else: else:
# Still use `cameraIterativeMean` to simplify the implementation. # Still use `cameraIterativeMean` to simplify the implementation.
# TODO: cameraIterativeMean.mean = mean([image_training_j_camera - cameraIterativeMean.mean for j in range(l)]) cameraIterativeMean.mean = np.mean([cameraTrainingImage - mergeSingleColorChannelImagesAccordingToBayerFilter({color: cameraColorMeans[camera][color].mean for color in Color}) for cameraTrainingImage in [multipleColorsImage]], axis = 0)#[:cameraTrainingImageIndex + 1]])
cameraIterativeMean.mean = 42
print(f'{cameraIterativeMean.mean = }') print(f'{cameraIterativeMean.mean = }')
print(f'{camerasIterativeMean[camera].mean = }') print(f'{camerasIterativeMean[camera].mean = }')
exit(1) if cameraIterativeMean.mean[0, 0] != 0:
exit(1)
# If we are considering the last camera and (not `PREDICT_ONLY_ON_WHOLE_TRAINING_SET` or we are considering the last training image), then we proceeded an additional image for all cameras and we can predict the accuracy at this learning step. # If we are considering the last camera and (not `PREDICT_ONLY_ON_WHOLE_TRAINING_SET` or we are considering the last training image), then we proceeded an additional image for all cameras and we can predict the accuracy at this learning step.
if cameraIndex == numberOfCameras - 1 and (not PREDICT_ONLY_ON_WHOLE_TRAINING_SET or cameraTrainingImageIndex == numberOfTrainingImages - 1): if cameraIndex == numberOfCameras - 1 and (not PREDICT_ONLY_ON_WHOLE_TRAINING_SET or cameraTrainingImageIndex == numberOfTrainingImages - 1):
numberOfTrainingImagesAccuracy = 0 numberOfTrainingImagesAccuracy = 0