Self-Driving-Car | Convolutional Neural Network for end-to-end driving | Machine Learning library

This is my code:

How to prevent a lazy Convolutional Neural Network? I end with a ‘lazy CNN’ after training it with KERAS. Whatever the input is, the output is constant. What do you think the problem is?

I try to repeat an experiment of NVIDIA’s End to End Learning for Self-Driving Cars the paper. Absolutely, I do not have a real car but a Udacity’s simulator . The simulator generates figures about the foreground of a car.

A CNN receives the figure, and it gives the steering angle to keep the car in the track. The rule of the game is to keep the simulated car runs in the track safely. It is not very difficult.

The strange thing is sometimes I end with a lazy CNN after training it with KERAS, which gives constant steering angles. The simulated car will go off the trick, but the output of the CNN has no change. Especially the layer gets deeper, e.g. the CNN in the paper.

If I use a CNN like this, I can get a useful model after training.

in udacity self driving https://github.com/udacity/self-driving-car/tree/master/vehicle-detection/u-net the method get_mask_seg(img, bb_boxes_f) gives slice indices must be integers or none or have an index method