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 sequence_train(cfg, tub_names, model_name, transfer_model, model_type,
continuous):
'''
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
'''
import sklearn
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.utils import shuffle
from PIL import Image
import json
assert (not continuous)
print(' ============================== ' + model_type)
print(" ==========================---- " + str(model_type == 'rnn'))
print("sequence of images training")
if model_type == "rnn":
print(" ========================== here")
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)
if model_type == "rnn_bin":
kl = KerasRNN_Categorical(image_w=cfg.IMAGE_W,
image_h=cfg.IMAGE_H,
image_d=cfg.IMAGE_DEPTH,
seq_length=cfg.SEQUENCE_LENGTH,
num_outputs=15)
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)
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"])
if (model_type == "rnn_bin"):
sample['target_output'] = dk.utils.linear_bin(angle)
else:
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
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)
record['img_data'] = img_arr
inputs_img.append(record['img_data'])
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)]
if (model_type == 'rnn_bin'):
y = np.array(b_labels).reshape(batch_size, 15)
else:
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)
history, save_best = 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)
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('model loss : %f' % save_best.best)
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.savefig(model_path + '_' + model_type +
'_loss_%f.png' % save_best.best)