I am training a neural network that takes an input
(H, W, 3) and has the output of size
(H', W', C). Now, to augment my dataset, since I only have 45k images, I am using the following in my custom data generator
def Generator(): img=cv2.imread(trainDir+'\'+imgpath) img=tf.keras.preprocessing.image.random_rotation(img,20m,row_axis=0,col_axis=1,channel_axis=2) output_mask=np.load(trainDir+'\'+maskpath) yield(img/255-.5,output_mask)
Since I am rotating my input images and the output_masks are generated from information about the input (specifically, heat maps around the joint locations) do I also need to rotate the masks as well?