def get_model_by_type(model_type, cfg):
from donkeycar.parts.keras import KerasRNN_LSTM, KerasBehavioral, KerasCategorical, KerasIMU, KerasLinear, Keras3D_CNN
if model_type is None:
model_type = "categorical"
input_shape = (cfg.IMAGE_H, cfg.IMAGE_W, cfg.IMAGE_DEPTH)
if model_type == "behavior" or cfg.TRAIN_BEHAVIORS:
kl = KerasBehavioral(num_outputs=2,
num_behavior_inputs=len(cfg.BEHAVIOR_LIST),
input_shape=input_shape)
elif model_type == "imu":
kl = KerasIMU(num_outputs=2, num_imu_inputs=6, input_shape=input_shape)
elif model_type == "linear":
kl = KerasLinear(input_shape=input_shape)
elif model_type == "3d":
kl = Keras3D_CNN(image_w=cfg.IMAGE_W,
image_h=cfg.IMAGE_H,
image_d=cfg.IMAGE_DEPTH,
seq_length=cfg.SEQUENCE_LENGTH)
elif model_type == "rnn":
kl = KerasRNN_LSTM(seq_length=cfg.SEQUENCE_LENGTH,
input_shape=input_shape)
elif model_type == "categorical":
kl = KerasCategorical(input_shape=input_shape)
else:
raise Exception("unknown model type: %s" % model_type)
return kl
def get_model_by_type(model_type, cfg):
from donkeycar.parts.keras import KerasRNN_LSTM, KerasBehavioral, KerasCategorical, KerasIMU, KerasLinear, Keras3D_CNN, KerasLocalizer, KerasLatent
if model_type is None:
model_type = "categorical"
input_shape = (cfg.IMAGE_H, cfg.IMAGE_W, cfg.IMAGE_DEPTH)
roi_crop = (cfg.ROI_CROP_TOP, cfg.ROI_CROP_BOTTOM)
if model_type == "localizer" or cfg.TRAIN_LOCALIZER:
kl = KerasLocalizer(num_outputs=2, num_behavior_inputs=len(cfg.BEHAVIOR_LIST), num_locations=cfg.NUM_LOCATIONS, input_shape=input_shape)
elif model_type == "behavior" or cfg.TRAIN_BEHAVIORS:
kl = KerasBehavioral(num_outputs=2, num_behavior_inputs=len(cfg.BEHAVIOR_LIST), input_shape=input_shape)
elif model_type == "imu":
kl = KerasIMU(num_outputs=2, num_imu_inputs=6, input_shape=input_shape)
elif model_type == "linear":
kl = KerasLinear(input_shape=input_shape, roi_crop=roi_crop)
elif model_type == "3d":
kl = Keras3D_CNN(image_w=cfg.IMAGE_W, image_h=cfg.IMAGE_H, image_d=cfg.IMAGE_DEPTH, seq_length=cfg.SEQUENCE_LENGTH)
elif model_type == "rnn":
kl = KerasRNN_LSTM(image_w=cfg.IMAGE_W, image_h=cfg.IMAGE_H, image_d=cfg.IMAGE_DEPTH, seq_length=cfg.SEQUENCE_LENGTH)
elif model_type == "categorical":
kl = KerasCategorical(input_shape=input_shape, throttle_range=cfg.MODEL_CATEGORICAL_MAX_THROTTLE_RANGE, roi_crop=roi_crop)
elif model_type == "latent":
kl = KerasLatent(input_shape=input_shape)
else:
raise Exception("unknown model type: %s" % model_type)
return kl
def get_model_by_type(model_type, cfg):
'''
given the string model_type and the configuration settings in cfg
create a Keras model and return it.
'''
from donkeycar.parts.keras import KerasRNN_LSTM, KerasBehavioral, KerasCategorical, KerasIMU, KerasLinear, Keras3D_CNN, KerasLocalizer, KerasLatent
from donkeycar.parts.tflite import TFLitePilot
if model_type is None:
model_type = cfg.DEFAULT_MODEL_TYPE
print("\"get_model_by_type\" model Type is: {}".format(model_type))
input_shape = (cfg.IMAGE_H, cfg.IMAGE_W, cfg.IMAGE_DEPTH)
roi_crop = (cfg.ROI_CROP_TOP, cfg.ROI_CROP_BOTTOM)
if model_type == "tflite_linear":
kl = TFLitePilot()
elif model_type == "localizer" or cfg.TRAIN_LOCALIZER:
kl = KerasLocalizer(num_outputs=2,
num_behavior_inputs=len(cfg.BEHAVIOR_LIST),
num_locations=cfg.NUM_LOCATIONS,
input_shape=input_shape)
elif model_type == "behavior" or cfg.TRAIN_BEHAVIORS:
kl = KerasBehavioral(num_outputs=2,
num_behavior_inputs=len(cfg.BEHAVIOR_LIST),
input_shape=input_shape)
elif model_type == "imu":
kl = KerasIMU(num_outputs=2, num_imu_inputs=6, input_shape=input_shape)
elif model_type == "linear":
kl = KerasLinear(input_shape=input_shape, roi_crop=roi_crop)
elif model_type == "tensorrt_linear":
# Aggressively lazy load this. This module imports pycuda.autoinit which causes a lot of unexpected things
# to happen when using TF-GPU for training.
from donkeycar.parts.tensorrt import TensorRTLinear
kl = TensorRTLinear(cfg=cfg)
elif model_type == "3d":
kl = Keras3D_CNN(image_w=cfg.IMAGE_W,
image_h=cfg.IMAGE_H,
image_d=cfg.IMAGE_DEPTH,
seq_length=cfg.SEQUENCE_LENGTH)
elif model_type == "rnn":
kl = KerasRNN_LSTM(image_w=cfg.IMAGE_W,
image_h=cfg.IMAGE_H,
image_d=cfg.IMAGE_DEPTH,
seq_length=cfg.SEQUENCE_LENGTH)
elif model_type == "categorical":
kl = KerasCategorical(
input_shape=input_shape,
throttle_range=cfg.MODEL_CATEGORICAL_MAX_THROTTLE_RANGE,
roi_crop=roi_crop)
elif model_type == "latent":
kl = KerasLatent(input_shape=input_shape)
else:
raise Exception("unknown model type: %s" % model_type)
return kl
def sequence_train(cfg, tub_names, model_name, transfer_model, model_type, continuous, aug):
'''
use the specified data in tub_names to train an artifical neural network
saves the output trained model as model_name
trains models which take sequence of images
'''
assert(not continuous)
print("sequence of images training")
if model_type == "rnn":
kl = KerasRNN_LSTM(image_w=cfg.IMAGE_W,
image_h=cfg.IMAGE_H,
image_d=cfg.IMAGE_DEPTH,
seq_length=cfg.SEQUENCE_LENGTH, num_outputs=2)
elif model_type == "3d":
kl = Keras3D_CNN(image_w=cfg.IMAGE_W,
image_h=cfg.IMAGE_H,
image_d=cfg.IMAGE_DEPTH,
seq_length=cfg.SEQUENCE_LENGTH,
num_outputs=2)
else:
raise Exception("unknown model type: %s" % model_type)
tubs = gather_tubs(cfg, tub_names)
records = []
for tub in tubs:
record_paths = glob.glob(os.path.join(tub.path, 'record_*.json'))
print("Tub:", tub.path, "has", len(record_paths), 'records')
record_paths.sort(key=get_record_index)
records += record_paths
print('collating records')
gen_records = {}
for record_path in records:
with open(record_path, 'r') as fp:
json_data = json.load(fp)
basepath = os.path.dirname(record_path)
image_filename = json_data["cam/image_array"]
image_path = os.path.join(basepath, image_filename)
sample = { 'record_path' : record_path, "image_path" : image_path, "json_data" : json_data }
sample["tub_path"] = basepath
sample["index"] = get_image_index(image_filename)
angle = float(json_data['user/angle'])
throttle = float(json_data["user/throttle"])
sample['target_output'] = np.array([angle, throttle])
sample['img_data'] = None
key = make_key(sample)
gen_records[key] = sample
print('collating sequences')
sequences = []
for k, sample in gen_records.items():
seq = []
for i in range(cfg.SEQUENCE_LENGTH):
key = make_next_key(sample, i)
if key in gen_records:
seq.append(gen_records[key])
else:
continue
if len(seq) != cfg.SEQUENCE_LENGTH:
continue
sequences.append(seq)
#shuffle and split the data
train_data, val_data = train_test_split(sequences, shuffle=True, test_size=(1 - cfg.TRAIN_TEST_SPLIT))
def generator(data, batch_size=cfg.BATCH_SIZE):
num_records = len(data)
while True:
#shuffle again for good measure
data = shuffle(data)
for offset in range(0, num_records, batch_size):
batch_data = data[offset:offset+batch_size]
if len(batch_data) != batch_size:
break
b_inputs_img = []
b_labels = []
for seq in batch_data:
inputs_img = []
labels = []
for record in seq:
#get image data if we don't already have it
if record['img_data'] is None:
img_arr = load_scaled_image_arr(record['image_path'], cfg)
if img_arr is None:
break
if aug:
img_arr = augment_image(img_arr)
if cfg.CACHE_IMAGES:
record['img_data'] = img_arr
else:
img_arr = record['img_data']
inputs_img.append(img_arr)
if img_arr is None:
continue
labels.append(seq[-1]['target_output'])
b_inputs_img.append(inputs_img)
b_labels.append(labels)
X = [np.array(b_inputs_img).reshape(batch_size,\
cfg.SEQUENCE_LENGTH, cfg.IMAGE_H, cfg.IMAGE_W, cfg.IMAGE_DEPTH)]
y = np.array(b_labels).reshape(batch_size, 2)
yield X, y
train_gen = generator(train_data)
val_gen = generator(val_data)
model_path = os.path.expanduser(model_name)
total_records = len(sequences)
total_train = len(train_data)
total_val = len(val_data)
print('train: %d, validation: %d' %(total_train, total_val))
steps_per_epoch = total_train // cfg.BATCH_SIZE
print('steps_per_epoch', steps_per_epoch)
if steps_per_epoch < 2:
raise Exception("Too little data to train. Please record more records.")
kl.train(train_gen,
val_gen,
saved_model_path=model_path,
steps=steps_per_epoch,
train_split=cfg.TRAIN_TEST_SPLIT,
use_early_stop = cfg.USE_EARLY_STOP)
def run(self, args):
'''
Start a websocket SocketIO server to talk to a donkey simulator
'''
import socketio
from donkeycar.parts.simulation import SteeringServer
from donkeycar.parts.keras import KerasCategorical, KerasLinear,\
Keras3D_CNN, KerasRNN_LSTM
args, parser = self.parse_args(args)
cfg = load_config(args.config)
if cfg is None:
return
#TODO: this logic should be in a pilot or model handler part.
if args.type == "categorical":
kl = KerasCategorical()
elif args.type == "linear":
kl = KerasLinear(num_outputs=2)
elif args.type == "rnn":
kl = KerasRNN_LSTM(image_w=cfg.IMAGE_W,
image_h=cfg.IMAGE_H,
image_d=cfg.IMAGE_DEPTH,
seq_length=cfg.SEQUENCE_LENGTH,
num_outputs=2)
elif args.type == "3d":
kl = Keras3D_CNN(image_w=cfg.IMAGE_W,
image_h=cfg.IMAGE_H,
image_d=cfg.IMAGE_DEPTH,
seq_length=cfg.SEQUENCE_LENGTH,
num_outputs=2)
else:
print("didn't recognize type:", args.type)
return
#can provide an optional image filter part
img_stack = None
#load keras model
kl.load(args.model)
#start socket server framework
sio = socketio.Server()
top_speed = float(args.top_speed)
#start sim server handler
ss = SteeringServer(sio,
kpart=kl,
top_speed=top_speed,
image_part=img_stack)
#register events and pass to server handlers
@sio.on('telemetry')
def telemetry(sid, data):
ss.telemetry(sid, data)
@sio.on('connect')
def connect(sid, environ):
ss.connect(sid, environ)
ss.go(('0.0.0.0', 9090))
def get_model_by_type(model_type: str, cfg: 'Config') -> 'KerasPilot':
'''
given the string model_type and the configuration settings in cfg
create a Keras model and return it.
'''
from donkeycar.parts.keras import KerasCategorical, KerasLinear, \
KerasInferred, KerasIMU, KerasMemory, KerasBehavioral, KerasLocalizer, \
KerasLSTM, Keras3D_CNN
from donkeycar.parts.interpreter import KerasInterpreter, TfLite, TensorRT
if model_type is None:
model_type = cfg.DEFAULT_MODEL_TYPE
logger.info(f'get_model_by_type: model type is: {model_type}')
input_shape = (cfg.IMAGE_H, cfg.IMAGE_W, cfg.IMAGE_DEPTH)
if 'tflite_' in model_type:
interpreter = TfLite()
used_model_type = model_type.replace('tflite_', '')
elif 'tensorrt_' in model_type:
interpreter = TensorRT()
used_model_type = model_type.replace('tensorrt_', '')
else:
interpreter = KerasInterpreter()
used_model_type = model_type
used_model_type = EqMemorizedString(used_model_type)
if used_model_type == "linear":
kl = KerasLinear(interpreter=interpreter, input_shape=input_shape)
elif used_model_type == "categorical":
kl = KerasCategorical(
interpreter=interpreter,
input_shape=input_shape,
throttle_range=cfg.MODEL_CATEGORICAL_MAX_THROTTLE_RANGE)
elif used_model_type == 'inferred':
kl = KerasInferred(interpreter=interpreter, input_shape=input_shape)
elif used_model_type == "imu":
kl = KerasIMU(interpreter=interpreter, input_shape=input_shape)
elif used_model_type == "memory":
mem_length = getattr(cfg, 'SEQUENCE_LENGTH', 3)
mem_depth = getattr(cfg, 'MEM_DEPTH', 0)
kl = KerasMemory(interpreter=interpreter,
input_shape=input_shape,
mem_length=mem_length,
mem_depth=mem_depth)
elif used_model_type == "behavior":
kl = KerasBehavioral(
interpreter=interpreter,
input_shape=input_shape,
throttle_range=cfg.MODEL_CATEGORICAL_MAX_THROTTLE_RANGE,
num_behavior_inputs=len(cfg.BEHAVIOR_LIST))
elif used_model_type == 'localizer':
kl = KerasLocalizer(interpreter=interpreter,
input_shape=input_shape,
num_locations=cfg.NUM_LOCATIONS)
elif used_model_type == 'rnn':
kl = KerasLSTM(interpreter=interpreter,
input_shape=input_shape,
seq_length=cfg.SEQUENCE_LENGTH)
elif used_model_type == '3d':
kl = Keras3D_CNN(interpreter=interpreter,
input_shape=input_shape,
seq_length=cfg.SEQUENCE_LENGTH)
else:
known = [
k + u for k in ('', 'tflite_', 'tensorrt_')
for u in used_model_type.mem
]
raise ValueError(
f"Unknown model type {model_type}, supported types are"
f" { ', '.join(known)}")
return kl