def fit_specialists(fname_pretrain=None):
if fname_pretrain:
with open(fname_pretrain, 'rb') as f:
net_pretrain = pickle.load(f)
else:
net_pretrain = None
specialists = OrderedDict()
for setting in SPECIALIST_SETTINGS:
cols = setting['columns']
X, y = load2d(cols=cols)
model = clone(net8)
model.output_num_units = y.shape[1]
model.batch_iterator_train.flip_indices = setting['flip_indices']
# set number of epochs relative to number of training examples:
model.max_epochs = int(1e7 / y.shape[0])
if 'kwargs' in setting:
# an option 'kwargs' in the settings list may be used to
# set any other parameter of the net:
vars(model).update(setting['kwargs'])
if net_pretrain is not None:
# if a pretrain model was given, use it to initialize the
# weights of our new specialist model:
model.load_params_from(net_pretrain)
print("Training model for columns {} for {} epochs".format(
cols, model.max_epochs))
model.fit(X, y)
specialists[cols] = model
from pickle import dump
with open("fit-specialists_{0}.pickle".format(sys.argv[1]), 'wb') as f:
# this time we're persisting a dictionary with all models:
dump(specialists, f, -1)
('hidden5', layers.DenseLayer),
('output', layers.DenseLayer)
],
input_shape=(None, 1, 96, 96),
conv1_num_filters=32, conv1_filter_size=(3, 3), pool1_pool_size=(2, 2),
conv2_num_filters=64, conv2_filter_size=(2, 2), pool2_pool_size=(2, 2),
conv3_num_filters=128, conv3_filter_size=(2, 2), pool3_pool_size=(2, 2),
hidden4_num_units=500,
hidden5_num_units=500,
output_num_units=30,
output_nonlinearity=None,
update_learning_rate=0.01,
update_momentum=0.9,
regression=True,
batch_iterator_train=FlipBatchIterator(batch_size=128),
max_epochs=3000,
verbose=1
)
X, y = load2d() # load 2D data
net3.fit(X, y)
# Training for 3000 epochs will take a while. We'll pickle the
# trained model so that we can load it back later:
from pickle import dump
with open("net3_{0}.pickle".format(sys.argv[1]), 'wb') as f:
dump(net3, f, -1)
import matplotlib.pyplot as pyplot from kfkd import load2d, plot_sample X, y = load2d() X_flipped = X[:, :, :, ::-1] # simple slice to flip all images # plot two images fig = pyplot.figure(figsize=(6, 3)) ax = fig.add_subplot(1, 2, 1, xticks=[], yticks=[]) plot_sample(X[1], y[1], ax) ax = fig.add_subplot(1, 2, 2, xticks=[], yticks=[]) plot_sample(X_flipped[1], y[1], ax) pyplot.show()
import matplotlib.pyplot as pyplot from kfkd import load, load2d, plot_loss, plot_sample from net1 import net1 from net2 import net2 # X1, y1 = load() # net1.fit(X1, y1) # X2, y2 = load2d() # load 2D data # net2.fit(X2, y2) sample1 = load(test=True)[0][6:7] sample2 = load2d(test=True)[0][6:7] y_pred1 = net1.predict(sample1)[0] y_pred2 = net2.predict(sample2)[0] fig = pyplot.figure(figsize=(6, 3)) ax = fig.add_subplot(1, 2, 1, xticks=[], yticks=[]) plot_sample(sample1[0], y_pred1, ax) ax = fig.add_subplot(1, 2, 2, xticks=[], yticks=[]) plot_sample(sample1[0], y_pred2, ax) pyplot.show()
return opts
opts = parseOptions()
#
# logging
#
head = '%(asctime)-15s - %(message)s'
logging.basicConfig(level=logging.DEBUG, format=head)
#
# Load data
#
FTRAIN = os.path.join(opts.dataDir, 'training.csv')
FTEST = os.path.join(opts.dataDir, 'test.csv')
X, y, = load2d(FTRAIN=FTRAIN, FTEST=FTEST)
if opts.augment:
print "Augmenting data"
X, y = augment(X, y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state = 42)
trainIter = mx.io.NDArrayIter(data = X_train, label = y_train, batch_size = 64)
valIter = mx.io.NDArrayIter(data = X_test , label = y_test , batch_size = 64)
#
# Select model
#
if opts.model=='mlp':
net = mlp()
elif opts.model=='lenet2':
net = lenet2()