def main():
# First, let's create a simple feedforward MLP with one hidden layer as a Prototype.
mlp = Prototype()
mlp.add(
Dense(input_size=28 * 28,
output_size=1000,
activation='rectifier',
noise='dropout'))
mlp.add(SoftmaxLayer(output_size=10))
# Now, we get to choose what values we want to monitor, and what datasets we would like to monitor on!
# Each Model (in our case, the Prototype), has a get_monitors method that will return a useful
# dictionary of {string_name: monitor_theano_expression} for various computations of the model we might
# care about. By default, this method returns an empty dictionary - it was the model creator's job to
# include potential monitor values.
mlp_monitors = mlp.get_monitors()
mlp_channel = MonitorsChannel(name="error")
for name, expression in mlp_monitors.items():
mlp_channel.add(
Monitor(name=name,
expression=expression,
train=True,
valid=True,
test=True))
# create some monitors for statistics about the hidden and output weights!
# let's look at the mean, variance, and standard deviation of the weights matrices.
weights_channel = MonitorsChannel(name="weights")
hiddens_1 = mlp[0].get_params()[0]
hiddens1_mean = T.mean(hiddens_1)
weights_channel.add(
Monitor(name="hiddens_mean", expression=hiddens1_mean, train=True))
hiddens_2 = mlp[1].get_params()[0]
hiddens2_mean = T.mean(hiddens_2)
weights_channel.add(
Monitor(name="out_mean", expression=hiddens2_mean, train=True))
# create our plot object to do live plotting!
plot = Plot(bokeh_doc_name="Monitor Tutorial",
monitor_channels=[mlp_channel, weights_channel],
open_browser=True)
# use SGD optimizer
optimizer = SGD(model=mlp,
dataset=MNIST(concat_train_valid=False),
epochs=500,
save_freq=100,
batch_size=600,
learning_rate=.01,
lr_decay=False,
momentum=.9,
nesterov_momentum=True)
# train, with the plot!
optimizer.train(plot=plot)
def main():
# First, let's create a simple feedforward MLP with one hidden layer as a Prototype.
mlp = Prototype()
mlp.add(Dense(input_size=28*28, output_size=1000, activation='rectifier', noise='dropout'))
mlp.add(SoftmaxLayer(output_size=10))
# Now, we get to choose what values we want to monitor, and what datasets we would like to monitor on!
# Each Model (in our case, the Prototype), has a get_monitors method that will return a useful
# dictionary of {string_name: monitor_theano_expression} for various computations of the model we might
# care about. By default, this method returns an empty dictionary - it was the model creator's job to
# include potential monitor values.
mlp_monitors = mlp.get_monitors()
mlp_channel = MonitorsChannel(name="error")
for name, expression in mlp_monitors.items():
mlp_channel.add(Monitor(name=name, expression=expression, train=True, valid=True, test=True))
# create some monitors for statistics about the hidden and output weights!
# let's look at the mean, variance, and standard deviation of the weights matrices.
weights_channel = MonitorsChannel(name="weights")
hiddens_1 = mlp[0].get_params()[0]
hiddens1_mean = T.mean(hiddens_1)
weights_channel.add(Monitor(name="hiddens_mean", expression=hiddens1_mean, train=True))
hiddens_2 = mlp[1].get_params()[0]
hiddens2_mean = T.mean(hiddens_2)
weights_channel.add(Monitor(name="out_mean", expression=hiddens2_mean, train=True))
# create our plot object to do live plotting!
plot = Plot(bokeh_doc_name="Monitor Tutorial", monitor_channels=[mlp_channel, weights_channel], open_browser=True)
# use SGD optimizer
optimizer = SGD(model=mlp,
dataset=MNIST(concat_train_valid=False),
epochs=500,
save_freq=100,
batch_size=600,
learning_rate=.01,
lr_decay=False,
momentum=.9,
nesterov_momentum=True)
# train, with the plot!
optimizer.train(plot=plot)
def testAutoEncoder(self):
try:
s = (None, 3)
x = matrix('xs')
e = Dense(inputs=(s, x), outputs=int(s[1]*2), activation='sigmoid')
W = e.get_param("W")
d = Dense(inputs=e, outputs=s[1], params={'W': W.T}, activation='sigmoid')
ae = Prototype([e, d])
x2 = matrix('xs1')
W2 = d.get_param("W")
e2 = Dense(inputs=(s, x2), outputs=int(s[1]*2), params={"W": W2.T, "b": e.get_param('b')}, activation='sigmoid')
W3 = e2.get_param("W")
d2 = Dense(inputs=e2, outputs=s[1], params={"W": W3.T, 'b': d.get_param('b')}, activation='sigmoid')
ae2 = Prototype([e2, d2])
aerun1 = ae.run(np.array([[.1,.5,.9]], dtype='float32'))
ae2run1 = ae.run(np.array([[.1,.5,.9]], dtype='float32'))
self.assertTrue(np.array_equal(aerun1, ae2run1))
data = np.ones((10,3), dtype='float32')*.1
data = np.vstack([data, np.ones((10,3), dtype='float32')*.2])
data = np.vstack([data, np.ones((10,3), dtype='float32')*.3])
data = np.vstack([data, np.ones((10,3), dtype='float32')*.4])
data = np.vstack([data, np.ones((10,3), dtype='float32')*.5])
data = np.vstack([data, np.ones((10,3), dtype='float32')*.6])
data = np.vstack([data, np.ones((10,3), dtype='float32')*.7])
data = np.vstack([data, np.ones((10,3), dtype='float32')*.8])
data = np.vstack([data, np.ones((10,3), dtype='float32')*.9])
data = np.vstack([data, np.ones((10,3), dtype='float32')*0])
dataset = NumpyDataset(data)
sgd = SGD(dataset=dataset, model=ae, loss=BinaryCrossentropy(inputs=ae.get_outputs(), targets=x), epochs=5)
sgd.train()
aerun2 = ae.run(np.array([[.1,.5,.9]], dtype='float32'))
ae2run2 = ae2.run(np.array([[.1,.5,.9]], dtype='float32'))
self.assertFalse(np.array_equal(aerun2, aerun1))
self.assertFalse(np.array_equal(ae2run2, ae2run1))
self.assertTrue(np.array_equal(aerun2, ae2run2))
sgd2 = SGD(dataset=dataset, model=ae2, loss=BinaryCrossentropy(inputs=ae2.get_outputs(), targets=x2), epochs=5)
sgd2.train()
aerun3 = ae.run(np.array([[.1,.5,.9]], dtype='float32'))
ae2run3 = ae2.run(np.array([[.1,.5,.9]], dtype='float32'))
self.assertFalse(np.array_equal(aerun3, aerun2))
self.assertFalse(np.array_equal(ae2run3, ae2run2))
self.assertTrue(np.array_equal(aerun3, ae2run3))
finally:
del x, e, d, ae, x2, e2, d2, ae2
output_size=512,
activation='rectifier',
noise='dropout')
hidden2 = Dense(inputs_hook=(512, hidden1.get_outputs()),
output_size=512,
activation='rectifier',
noise='dropout')
class_layer = SoftmaxLayer(inputs_hook=(512, hidden2.get_outputs()),
output_size=10)
mlp = Prototype([hidden1, hidden2, class_layer])
return mlp
if __name__ == '__main__':
mlp = sequential_add_layers()
data = MNIST(concat_train_valid=True)
print data.train_inputs.shape
print data.valid_inputs.shape
print data.test_inputs.shape
optimizer = SGD(model=mlp,
dataset=data,
epochs=500,
batch_size=600,
learning_rate=.01,
momentum=.9,
nesterov_momentum=True)
optimizer.train()
def testLeNet(self):
try:
# quick and dirty way to create a model from arbitrary layers
lenet = Prototype(outdir=None)
# our input is going to be 4D tensor of images with shape (batch_size, 1, 28, 28)
x = ((None, 1, 28, 28), ftensor4('x'))
# our first convolutional layer
lenet.add(
Conv2D(inputs=x, n_filters=20, filter_size=(5, 5),
outdir=None))
# our first pooling layer, automatically hooking inputs to the previous convolutional outputs
lenet.add(Pool2D, size=(2, 2))
# our second convolutional layer
lenet.add(Conv2D, n_filters=50, filter_size=(5, 5), outdir=None)
# our second pooling layer
lenet.add(Pool2D, size=(2, 2))
# now we need to flatten the 4D convolution outputs into 2D matrix (just flatten the trailing dimensions)
lenet.add(Flatten, ndim=2)
# one dense hidden layer
lenet.add(Dense, outputs=500, activation='tanh', outdir=None)
# hook a softmax classification layer, outputting the probabilities.
lenet.add(Softmax, outputs=10, out_as_probs=True, outdir=None)
# Grab the MNIST dataset
data = MNIST(path="../../../datasets/{!s}".format(mnist_name),
concat_train_valid=False,
flatten=False)
# define our loss to optimize for the model (and the target variable)
# targets from MNIST are int64 numbers 0-9
y = lvector('y')
loss = Neg_LL(inputs=lenet.get_outputs(), targets=y, one_hot=False)
# monitor
error_monitor = Monitor(
name='error',
expression=mean(neq(lenet.models[-1].y_pred, y)),
valid=True,
test=True,
out_service=FileService('outputs/lenet_error.txt'))
# optimize our model to minimize loss given the dataset using SGD
optimizer = SGD(model=lenet,
dataset=data,
loss=loss,
epochs=10,
batch_size=128,
learning_rate=.1,
momentum=False)
print("Training LeNet...")
optimizer.train(monitor_channels=error_monitor)
def test_subset(filename, expected, conf=0.001):
with open(filename, 'r') as f:
errs = [float(err) for err in f]
for i, (err, exp) in enumerate(zip(errs, expected)):
if i == 0:
c = conf * 10
else:
c = conf
self.assertTrue(
exp - c < round(err, 4) < exp + c,
"Errors: {!s} and Expected: {!s} -- Error at {!s} and {!s}"
.format(errs, expected, err, exp))
test_subset('outputs/lenet_error_train.txt', [
.0753, .0239, .0159, .0113, .0088, .0064, .0050, .0037, .0026,
.0019
])
test_subset('outputs/lenet_error_valid.txt', [
.0283, .0209, .0170, .0151, .0139, .0129, .0121, .0118, .0112,
.0113
])
test_subset('outputs/lenet_error_test.txt', [
.0319, .0213, .0167, .0134, .0122, .0119, .0116, .0107, .0104,
.0105
])
shutil.rmtree('outputs/')
finally:
if 'lenet' in locals():
del lenet
if 'data' in locals():
del data
if 'y' in locals():
del y
if 'x' in locals():
del x
if 'loss' in locals():
del loss
if 'optimizer' in locals():
del optimizer
return lenet
if __name__ == '__main__':
# Grab the MNIST dataset
data = MNIST(concat_train_valid=False)
# we need to convert the (784,) flat example from MNIST to (1, 28, 28) for a 2D greyscale image
process_mnist = lambda img: np.reshape(img, (1, 28, 28))
# we can do this by using ModifyStreams over the inputs!
data.train_inputs = ModifyStream(data.train_inputs, process_mnist)
data.valid_inputs = ModifyStream(data.valid_inputs, process_mnist)
data.test_inputs = ModifyStream(data.test_inputs, process_mnist)
# now build the actual model
lenet = build_lenet()
# define our loss to optimize for the model (and the target variable)
# targets from MNIST are int64 numbers 0-9
y = lvector('y')
loss = Neg_LL(inputs=lenet.get_outputs(), targets=y, one_hot=False)
error_monitor = Monitor(name='error', expression=mean(neq(lenet.models[-1].y_pred, y)), valid=True, test=True)
# optimize our model to minimize loss given the dataset using SGD
optimizer = SGD(model=lenet,
dataset=data,
loss=loss,
epochs=200,
batch_size=500,
learning_rate=.1,
momentum=False)
optimizer.train(monitor_channels=error_monitor)
# Grab the MNIST dataset
data = MNIST(concat_train_valid=False)
# we need to convert the (784,) flat example from MNIST to (1, 28, 28) for a 2D greyscale image
process_mnist = lambda img: np.reshape(img, (1, 28, 28))
# we can do this by using ModifyStreams over the inputs!
data.train_inputs = ModifyStream(data.train_inputs, process_mnist)
data.valid_inputs = ModifyStream(data.valid_inputs, process_mnist)
data.test_inputs = ModifyStream(data.test_inputs, process_mnist)
# now build the actual model
lenet = build_lenet()
# define our loss to optimize for the model (and the target variable)
# targets from MNIST are int64 numbers 0-9
y = lvector('y')
loss = Neg_LL(inputs=lenet.get_outputs(), targets=y, one_hot=False)
error_monitor = Monitor(name='error',
expression=mean(neq(lenet.models[-1].y_pred, y)),
valid=True,
test=True,
out_service=FileService('outputs/lenet_error.txt'))
# optimize our model to minimize loss given the dataset using SGD
optimizer = SGD(model=lenet,
dataset=data,
loss=loss,
epochs=200,
batch_size=128,
learning_rate=.1,
momentum=False)
optimizer.train(monitor_channels=error_monitor)
def testAutoEncoder(self):
try:
s = (None, 3)
x = matrix('xs')
e = Dense(inputs=(s, x),
outputs=int(s[1] * 2),
activation='sigmoid')
W = e.get_param("W")
d = Dense(inputs=e,
outputs=s[1],
params={'W': W.T},
activation='sigmoid')
ae = Prototype([e, d])
x2 = matrix('xs1')
W2 = d.get_param("W")
e2 = Dense(inputs=(s, x2),
outputs=int(s[1] * 2),
params={
"W": W2.T,
"b": e.get_param('b')
},
activation='sigmoid')
W3 = e2.get_param("W")
d2 = Dense(inputs=e2,
outputs=s[1],
params={
"W": W3.T,
'b': d.get_param('b')
},
activation='sigmoid')
ae2 = Prototype([e2, d2])
aerun1 = ae.run(np.array([[.1, .5, .9]], dtype='float32'))
ae2run1 = ae.run(np.array([[.1, .5, .9]], dtype='float32'))
self.assertTrue(np.array_equal(aerun1, ae2run1))
data = np.ones((10, 3), dtype='float32') * .1
data = np.vstack([data, np.ones((10, 3), dtype='float32') * .2])
data = np.vstack([data, np.ones((10, 3), dtype='float32') * .3])
data = np.vstack([data, np.ones((10, 3), dtype='float32') * .4])
data = np.vstack([data, np.ones((10, 3), dtype='float32') * .5])
data = np.vstack([data, np.ones((10, 3), dtype='float32') * .6])
data = np.vstack([data, np.ones((10, 3), dtype='float32') * .7])
data = np.vstack([data, np.ones((10, 3), dtype='float32') * .8])
data = np.vstack([data, np.ones((10, 3), dtype='float32') * .9])
data = np.vstack([data, np.ones((10, 3), dtype='float32') * 0])
dataset = NumpyDataset(data)
sgd = SGD(dataset=dataset,
model=ae,
loss=BinaryCrossentropy(inputs=ae.get_outputs(),
targets=x),
epochs=5)
sgd.train()
aerun2 = ae.run(np.array([[.1, .5, .9]], dtype='float32'))
ae2run2 = ae2.run(np.array([[.1, .5, .9]], dtype='float32'))
self.assertFalse(np.array_equal(aerun2, aerun1))
self.assertFalse(np.array_equal(ae2run2, ae2run1))
self.assertTrue(np.array_equal(aerun2, ae2run2))
sgd2 = SGD(dataset=dataset,
model=ae2,
loss=BinaryCrossentropy(inputs=ae2.get_outputs(),
targets=x2),
epochs=5)
sgd2.train()
aerun3 = ae.run(np.array([[.1, .5, .9]], dtype='float32'))
ae2run3 = ae2.run(np.array([[.1, .5, .9]], dtype='float32'))
self.assertFalse(np.array_equal(aerun3, aerun2))
self.assertFalse(np.array_equal(ae2run3, ae2run2))
self.assertTrue(np.array_equal(aerun3, ae2run3))
finally:
del x, e, d, ae, x2, e2, d2, ae2
def testLeNet(self):
try:
# quick and dirty way to create a model from arbitrary layers
lenet = Prototype(outdir=None)
# our input is going to be 4D tensor of images with shape (batch_size, 1, 28, 28)
x = ((None, 1, 28, 28), ftensor4('x'))
# our first convolutional layer
lenet.add(
Conv2D(inputs=x, n_filters=20, filter_size=(5, 5), outdir=None)
)
# our first pooling layer, automatically hooking inputs to the previous convolutional outputs
lenet.add(
Pool2D, size=(2, 2)
)
# our second convolutional layer
lenet.add(
Conv2D, n_filters=50, filter_size=(5, 5), outdir=None
)
# our second pooling layer
lenet.add(
Pool2D, size=(2, 2)
)
# now we need to flatten the 4D convolution outputs into 2D matrix (just flatten the trailing dimensions)
lenet.add(
Flatten, ndim=2
)
# one dense hidden layer
lenet.add(
Dense, outputs=500, activation='tanh', outdir=None
)
# hook a softmax classification layer, outputting the probabilities.
lenet.add(
Softmax, outputs=10, out_as_probs=True, outdir=None
)
# Grab the MNIST dataset
data = MNIST(path="../../../datasets/{!s}".format(mnist_name), concat_train_valid=False, flatten=False)
# define our loss to optimize for the model (and the target variable)
# targets from MNIST are int64 numbers 0-9
y = lvector('y')
loss = Neg_LL(inputs=lenet.get_outputs(), targets=y, one_hot=False)
# monitor
error_monitor = Monitor(name='error', expression=mean(neq(lenet.models[-1].y_pred, y)), valid=True,
test=True, out_service=FileService('outputs/lenet_error.txt'))
# optimize our model to minimize loss given the dataset using SGD
optimizer = SGD(model=lenet,
dataset=data,
loss=loss,
epochs=10,
batch_size=128,
learning_rate=.1,
momentum=False)
print("Training LeNet...")
optimizer.train(monitor_channels=error_monitor)
def test_subset(filename, expected, conf=0.001):
with open(filename, 'r') as f:
errs = [float(err) for err in f]
for i, (err, exp) in enumerate(zip(errs, expected)):
if i == 0:
c = conf*10
else:
c = conf
self.assertTrue(exp-c < round(err, 4) < exp+c,
"Errors: {!s} and Expected: {!s} -- Error at {!s} and {!s}".format(
errs, expected, err, exp)
)
test_subset('outputs/lenet_error_train.txt',
[.0753,
.0239,
.0159,
.0113,
.0088,
.0064,
.0050,
.0037,
.0026,
.0019]
)
test_subset('outputs/lenet_error_valid.txt',
[.0283,
.0209,
.0170,
.0151,
.0139,
.0129,
.0121,
.0118,
.0112,
.0113]
)
test_subset('outputs/lenet_error_test.txt',
[.0319,
.0213,
.0167,
.0134,
.0122,
.0119,
.0116,
.0107,
.0104,
.0105]
)
shutil.rmtree('outputs/')
finally:
if 'lenet' in locals():
del lenet
if 'data' in locals():
del data
if 'y' in locals():
del y
if 'x' in locals():
del x
if 'loss' in locals():
del loss
if 'optimizer' in locals():
del optimizer
