def main_rain():
trX, teX, trY, teY = mnist(onehot=True)
trX = trX.reshape(-1, 1, 28, 28)
teX = teX.reshape(-1, 1, 28, 28)
X = T.ftensor4()
Y = T.fmatrix()
w = init_weights((32, 1, 3, 3))
w2 = init_weights((64, 32, 3, 3))
w3 = init_weights((128, 64, 3, 3))
w4 = init_weights((128 * 3 * 3, 625))
w_o = init_weights((625, 10))
params = [w, w2, w3, w4, w_o]
noise_l1, noise_l2, noise_l3, noise_l4, noise_py_x = model(X, params, 0.2, 0.5)
l1, l2, l3, l4, py_x = model(X, params, 0., 0.)
y_x = T.argmax(py_x, axis=1)
cost = T.mean(T.nnet.categorical_crossentropy(noise_py_x, Y))
updates = RMSprop(cost, params, lr=0.001)
train = theano.function(inputs=[X, Y], outputs=cost, updates=updates, allow_input_downcast=True)
predict = theano.function(inputs=[X], outputs=y_x, allow_input_downcast=True)
for i in range(100):
for start, end in zip(range(0, len(trX), 128), range(128, len(trX), 128)):
cost = train(trX[start:end], trY[start:end])
print np.mean(np.argmax(teY, axis=1) == predict(teX))
if i % 10 == 0:
name = 'media/model/conv-{0}.model'.format(str(i))
save_model(name, params)
name = 'media/model/conv-final.model'
save_model(name, params)
def main_train():
trX, teX, trY, teY = mnist(onehot=True)
X = T.fmatrix()
Y = T.fmatrix()
w_h = init_weights((784, 625))
w_o = init_weights((625, 10))
params = [w_h, w_o]
py_x = model(X, params)
y_x = T.argmax(py_x, axis=1)
cost = T.mean(T.nnet.categorical_crossentropy(py_x, Y))
updates = sgd(cost, params)
train = theano.function(inputs=[X, Y],
outputs=cost,
updates=updates,
allow_input_downcast=True)
predict = theano.function(inputs=[X],
outputs=y_x,
allow_input_downcast=True)
for i in range(100):
for start, end in zip(range(0, len(trX), 128),
range(128, len(trX), 128)):
cost = train(trX[start:end], trY[start:end])
print np.mean(np.argmax(teY, axis=1) == predict(teX))
if i % 10 == 0:
name = 'media/model/net-{0}.model'.format(str(i))
save_model(name, params)
name = 'media/model/net-final.model'
save_model(name, params)
def main_train():
trX, teX, trY, teY = mnist(onehot=True)
X = T.fmatrix()
Y = T.fmatrix()
w_h = init_weights((784, 625))
w_h2 = init_weights((625, 625))
w_o = init_weights((625, 10))
params = [w_h, w_h2, w_o]
noise_h, noise_h2, noise_py_x = model(X, params, 0.2, 0.5)
h, h2, py_x = model(X, params, 0., 0.)
y_x = T.argmax(py_x, axis=1)
cost = T.mean(T.nnet.categorical_crossentropy(noise_py_x, Y))
updates = RMSprop(cost, params, lr=0.001)
train = theano.function(inputs=[X, Y], outputs=cost, updates=updates, allow_input_downcast=True)
predict = theano.function(inputs=[X], outputs=y_x, allow_input_downcast=True)
for i in range(100):
for start, end in zip(range(0, len(trX), 128), range(128, len(trX), 128)):
cost = train(trX[start:end], trY[start:end])
print np.mean(np.argmax(teY, axis=1) == predict(teX))
if i % 10 == 0:
name = 'media/model/modnet-{0}.model'.format(str(i))
save_model(name, params)
name = 'media/model/modnet-final.model'
save_model(name, params)
action='store',
default=0.001,
type=float)
hyper_param.add_argument('-u',
'--hidden_units',
default=3136,
dest='u',
type=int)
hyper_param.add_argument('-e', '--epochs', dest='e', default=8, type=int)
args = parser.parse_args()
data_d = args.inputDirectory
architec = args.arch
lr = args.l
hidden_units = args.u
epochs = args.e
gpu = args.gpu
path = args.save_dir
train_image_datasets, test_image_data_sets, valid_image_datasets, trainloaders, testloaders, validloaders = load.arg_inputdir(
args.inputDirectory)
pretrained_model, output_size, i = model.arch(architec)
pretrained_model, criterion, optimizer = model.classifier(
pretrained_model, output_size, i, lr, hidden_units)
load.training_model(pretrained_model, criterion, optimizer, epochs, gpu)
load.validation_test(pretrained_model, testloaders)
complete_path = load.set_checkpoint_path(path)
load.save_model(pretrained_model, complete_path, architec)
load.model(architec)
# pretrained_model = load.load_model(pretrained_model,'checkpoint.pth')