Reshape on train_data is mixing the pixels!

[giordand]

The reshape to the train data and also to the screen grabbed on testing model is mixing the pixels in the screen:

the solution is to change width by height in every line where is a reshape, as in

pygta5/2. train_model.py

Line 88 in d9375c1

X = np.array([i[0] for i in train]).reshape(-1,WIDTH,HEIGHT,3)

X = np.array([i[0] for i in train]).reshape(-1,WIDTH,HEIGHT,3)

by:

X = np.array([i[0] for i in train]).reshape(-1,HEIGHT,WIDTH,3)

and now reshape is OK:

[germanmarky]

Confirmed issue and fix.

[Eric-Ryan]

prev = cv2.resize(screen, (WIDTH,HEIGHT))

screen = cv2.resize(screen, (WIDTH,HEIGHT))

prediction = model.predict([screen.reshape(WIDTH,HEIGHT,3)])[0]

Within '3.test_model.py' should I change these lines too? Did this fix the issue of only going straight?

[giordand]

This fix is no related with #62 ...at least with 25k examples for training, balanced....

[germanmarky]

@giordand I haven't had a chance to test, but good to know.

@Eric-Ryan do not change the resize functions as they are working as intended.

[DevJhns]

@giordand how you get reshaped img?