I have a function
def preprocess(image):
image = cv2.cvtColor(image, cv2.COLOR_RGB2YUV)
image = cv2.GaussianBlur(image, (3, 3), 0)
image = cv2.resize(image, (200, 66))
return image
I want to use this function in a Lambda layer of a NN like this
model=Sequential()
model.add(Lambda(preprocess,input_shape=(160,320,3)))
#model.add(Lambda(lambda x: (x / 255.0) - 0.5, input_shape=(160,320,3)))
model.add(Lambda(lambda x: (x / 255.0) - 0.5))
model.add(Cropping2D(cropping=((60,25), (0,0))))
However I got the error
model = nvidia_model()
print(model.summary())
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-11-9f6554917809> in <module>()
----> 1 model = nvidia_model()
2 print(model.summary())
6 frames
<ipython-input-9-5e5ec9bc70c2> in preprocess(image)
1 def preprocess(image):
2
----> 3 image = cv2.cvtColor(image, cv2.COLOR_RGB2YUV)
4 image = cv2.GaussianBlur(image, (3, 3), 0)
5 image = cv2.resize(image, (200, 66))
TypeError: Expected Ptr<cv::UMat> for argument '%s'
How can I use this function as a layer of the NN?? (note that just using the lambda x:(x/255.0) works well.
Note: I don't want to do this externally. (Because I already did, it works fine, but now I am trying to do it internally)
