通过 Apache MXNet，为您的自动驾驶车辆应用行为克隆技术

   $ rsync -rva --progress -e "ssh -i /path/to/key/DonkeyKP-us-east-1.pem" /home/pi/d2// ec2-user@ec2-your-ip.compute-1.amazonaws.com:~/d2/data/

   $ python ~/d2/manage.py train --model /path/to/myfirstpilot

   $: rsync -rva --progress -e "ssh -i /path/to/key/DonkeyKP-us-east-1.pem" ec2-user@ec2-your-ip.compute-1.amazonaws.com:~/d2/models/ /home/pi/d2/models/

import mxnet as mximport numpy as np
data = mx.symbol.Variable(name="data")
body = mx.sym.Convolution(data=data, num_filter=24,  kernel=(5, 5), stride=(2,2)) body = mx.sym.Activation(data=body, act_type='relu', name='relu1')body = mx.symbol.Pooling(data=body, kernel=(2, 2), stride=(2,2), pool_type='max')
body = mx.sym.Convolution(data=body, num_filter=32,  kernel=(5, 5), stride=(2,2))body = mx.sym.Activation(data=body, act_type='relu')body = mx.symbol.Pooling(data=body, kernel=(2, 2), stride=(2,2), pool_type='max')
flatten = mx.symbol.Flatten(data=body)
body = mx.symbol.FullyConnected(data=flatten, name='fc0', num_hidden=32)body = mx.sym.Activation(data=body, act_type='relu', name='relu6')body = mx.sym.Dropout(data=body, p=0.1)
body = mx.symbol.FullyConnected(data=body, name='fc1', num_hidden=16)body = mx.sym.Activation(data=body, act_type='relu', name='relu7')
out = mx.symbol.FullyConnected(data=body, name='fc2', num_hidden=1)out = mx.symbol.LinearRegressionOutput(data=out, name="softmax")

# Get Iterators
def get_iterators(batch_size, data_shape=(3, 120, 160)):    train = mx.io.ImageRecordIter(        path_imgrec         = 'train.rec',         data_name           = 'data',        label_name          = 'softmax_label',        batch_size          = batch_size,        data_shape          = data_shape,        shuffle             = True,        rand_crop           = True,        rand_mirror         = True)    val = mx.io.ImageRecordIter(        path_imgrec         = 'valid.rec',        data_name           = 'data',        label_name          = 'softmax_label',        batch_size          = batch_size,        data_shape          = data_shape,        rand_crop           = False,        rand_mirror         = False)    return (train, val)
batch_size = 16train_iter, val_iter = get_iterators(batch_size)
#Training
batch_size = 8num_gpus = 1num_epoch = 10mod = mx.mod.Module(out, context=[mx.gpu(i) for i in range(num_gpus)])mod.fit(train_data=train_iter,         eval_data=val_iter,         eval_metric='mae',         optimizer='adam',        optimizer_params={'learning_rate': 0.0001},        num_epoch=num_epoch,        batch_end_callback = mx.callback.Speedometer(batch_size, 100),               )

import os  import time%matplotlib inlinefrom IPython import displayimport matplotlib.patches as patches
PATH = 'trainingdata/'all_files = sorted(os.listdir(PATH))sym, arg_params, aux_params = mx.model.load_checkpoint('my-car', num_epoch)mod = mx.mod.Module(symbol=sym) fig, ax = plt.subplots(1)for fname in all_files:    org_img = Image.open(PATH + fname)        img = np.array(org_img)    img = np.swapaxes(img, 0, 2)    img = np.swapaxes(img, 1, 2)     img = img[np.newaxis, :]     mod.forward(Batch(data=[mx.nd.array(img)]))    exp = mod.get_outputs()[0].asnumpy()[0]    angle = 180*exp    left = 80 * exp + 80    rect = patches.Rectangle((left, 85),20,30, angle=angle,                             linewidth=2,edgecolor='r',facecolor='none')    patch = ax.add_patch(rect)    display.clear_output(wait=True)    display.display(plt.gcf())    plt.imshow(org_img)    time.sleep(0.1)    patch.remove()