diff --git a/datasets/raise/attribute_source_camera.py b/datasets/raise/attribute_source_camera.py
index f8408c3..e4efb97 100755
--- a/datasets/raise/attribute_source_camera.py
+++ b/datasets/raise/attribute_source_camera.py
@@ -159,7 +159,7 @@ for computeExtremes in tqdm(([True] if minColor is None or maxColor is None else
                 minColor, maxColor = updateExtremes(multipleColorsImage, minColor, maxColor)
                 continue
 
-            if DENOISER == Denoiser.MEAN:
+            if DENOISER == Denoiser.MEAN and not PREDICT_ONLY_ON_WHOLE_TRAINING_SET:
                 for color in Color:
                     cameraColorMeans[camera][color].add(singleColorChannelImages[color])
             imagePrnuEstimateNpArray = getImagePrnuEstimateNpArray(singleColorChannelImages, multipleColorsImage, camera)
diff --git a/datasets/raise/utils.py b/datasets/raise/utils.py
index 60c802f..a3eb311 100644
--- a/datasets/raise/utils.py
+++ b/datasets/raise/utils.py
@@ -205,7 +205,7 @@ def getColorMeans(imagesFileNames, colors, singleColorChannelCropResolution = No
     for color in colors:
         colorIterativeMean = iterativeMean()
         for imageFileName in tqdm(imagesFileNames, f'Computing mean of {str(color).replace("_", " ")} colored images'):
-            imageNpArray = getImageNpArray(imageFileName, False, color, Denoiser.MEAN)
+            imageNpArray, minColor_, maxColor_ = getImageNpArray(imageFileName, False, color, Denoiser.MEAN, None, None)
             if singleColorChannelCropResolution is not None:
                 imageNpArray = getImageCrop(imageNpArray, singleColorChannelCropResolution)
             imageNpArray = gaussian_filter(imageNpArray, sigma = 5)