donkey keras imu integration

keras_imu.py

import os
import numpy as np
import keras
import donkeycar as dk
from donkeycar.parts.keras import KerasPilot

class KerasIMU(KerasPilot):
    def __init__(self, model=None, num_outputs=None, *args, **kwargs):
        super(KerasIMU, self).__init__(*args, **kwargs)
        self.model = default_imu(2)
        
    def load(self, model_path):
        self.model = keras.models.load_model(model_path)

    def shutdown(self):
        pass
        
    def run(self, img_arr, accel_x, accel_y, accel_z, gyr_x, gyr_y, gyr_z, temp):
        img_arr = img_arr.reshape((1,) + img_arr.shape)
        imu_arr = np.array([accel_x, accel_y, accel_z, gyr_x, gyr_y, gyr_z, temp]).reshape(None,7)
        outputs = self.model.predict([img_arr, imu_arr])
        steering = outputs[0]
        throttle = outputs[1]
        return steering[0][0], throttle[0][0]

def default_imu(num_outputs):
    from keras.layers import Input, Dense
    from keras.models import Model
    from keras.layers import Convolution2D, MaxPooling2D, Reshape, BatchNormalization
    from keras.layers import Activation, Dropout, Flatten, Cropping2D, Lambda
    from keras.layers.merge import concatenate
    
    img_in = Input(shape=(120,160,3), name='img_in')
    imu_in = Input(shape=(7,), name="imu_in")
    
    x = img_in
    x = Cropping2D(cropping=((60,0), (0,0)))(x) #trim 60 pixels off top
    #x = Lambda(lambda x: x/127.5 - 1.)(x) # normalize and re-center
    x = Convolution2D(24, (5,5), strides=(2,2), activation='relu')(x)
    x = Convolution2D(32, (5,5), strides=(2,2), activation='relu')(x)
    x = Convolution2D(64, (3,3), strides=(2,2), activation='relu')(x)
    x = Convolution2D(64, (3,3), strides=(1,1), activation='relu')(x)
    x = Convolution2D(64, (3,3), strides=(1,1), activation='relu')(x)
    x = Flatten(name='flattened')(x)
    x = Dense(100, activation='relu')(x)
    x = Dropout(.1)(x)
    
    y = imu_in
    y = Dense(14, activation='relu')(y)
    y = Dense(14, activation='relu')(y)
    y = Dense(14, activation='relu')(y)
    
    z = concatenate([x, y])
    z = Dense(50, activation='relu')(z)
    z = Dropout(.1)(z)
    z = Dense(50, activation='relu')(z)
    z = Dropout(.1)(z)

    outputs = [] 
    
    for i in range(num_outputs):
        outputs.append(Dense(1, activation='linear', name='n_outputs' + str(i))(z))
        
    model = Model(inputs=[img_in, imu_in], outputs=outputs)
    
    
    model.compile(optimizer='adam',
                  loss='mse')
    
    #print(model.summary())

    return model