Closed AlexanderLeipnitz closed 5 years ago
I use the same value because I think it would not affect much. What I want to do is to let the RGB value range between [-128~128].
I think you can use the same value when training on your own dataset.
If you use the tf.Dataset api
to load your own dataset, you can try to use this function, it will be much more convenient when pre-processing.
Hello, I have some questions regarding the mean value subtraction:
IMG_MEAN = np.array((103.939, 116.779, 123.68), dtype=np.float32)
coming from and why is it the same for the Cityscapes and ADE20K dataset?img = tf.image.per_image_standardization(img)
and instead use the fixed MEAN value?