layer_params = layer.get_params(trainable=True)
if name in ['new_output', 'fc6', 'fc7']:
layer_lr = learning_rate
else:
layer_lr = learning_rate / 10
if name != 'fc8':
layer_updates = lasagne.updates.nesterov_momentum(
loss, layer_params, learning_rate=layer_lr, momentum=0.9)
updates.update(layer_updates)
# Compile functions for training, validation and prediction
train_fn = theano.function([X_sym, y_sym], [loss, acc], updates=updates)
val_fn = theano.function([X_sym, y_sym], [loss, acc])
pred_fn = theano.function([X_sym], prediction)
X_train, y_train, ids_train = load_train_data()
X_test, ids_test = load_test_data(img_start_ix=0, max_img=1000)
y_pseudo = load_pseudo_labels()
pos = np.array(range(4777))
X, y, ids = np.concatenate((X_train, X_test)), np.concatenate(
(y_train, y_pseudo)), np.concatenate((ids_train, ids_test))
X, y, ids, pos = sklearn.utils.shuffle(X, y, ids, pos, random_state=0)
new_pseudo_label_pos = []
for i in range(3777, 4777):
k = np.where(pos == i)
new_pseudo_label_pos.append(int(k[0]))
# generator splitting an iterable into chunks of maximum length N
def batches(iterable, N):
for name, layer in net.items():
layer_params = layer.get_params(trainable=True)
if name in ['new_output', 'fc6', 'fc7']:
layer_lr = learning_rate
else:
layer_lr = learning_rate / 10
if name != 'fc8':
layer_updates = lasagne.updates.nesterov_momentum(loss, layer_params, learning_rate=layer_lr, momentum=0.9)
updates.update(layer_updates)
# Compile functions for training, validation and prediction
train_fn = theano.function([X_sym, y_sym], [loss, acc], updates=updates)
val_fn = theano.function([X_sym, y_sym], [loss, acc])
pred_fn = theano.function([X_sym], prediction)
X, y, ids = load_train_data()
X, y, ids = sklearn.utils.shuffle(X, y, ids, random_state=0)
# generator splitting an iterable into chunks of maximum length N
def batches(iterable, N):
chunk = []
for item in iterable:
chunk.append(item)
if len(chunk) == N:
yield chunk
chunk = []
if chunk:
yield chunk
# We need a fairly small batch size to fit a large network like this in GPU memory
BATCH_SIZE = 12