def main():
# First, let's create a simple feedforward MLP with one hidden layer as a Prototype.
mlp = Prototype()
mlp.add(
BasicLayer(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),
n_epoch=500,
save_frequency=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(BasicLayer(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),
n_epoch=500,
save_frequency=100,
batch_size=600,
learning_rate=.01,
lr_decay=False,
momentum=.9,
nesterov_momentum=True)
# train, with the plot!
optimizer.train(plot=plot)
def run_mlp():
# # define the model layers
# layer1 = Dense(input_size=784, output_size=1000, activation='rectifier')
# layer2 = Dense(inputs_hook=(1000, layer1.get_outputs()), output_size=1000, activation='rectifier')
# classlayer3 = SoftmaxLayer(inputs_hook=(1000, layer2.get_outputs()), output_size=10, out_as_probs=False)
# # add the layers to the prototype
# mlp = Prototype(layers=[layer1, layer2, classlayer3])
# test the new way to automatically fill in inputs_hook for models
mlp = Prototype()
mlp.add(Dense(input_size=784, output_size=1000, activation='rectifier', noise='dropout'))
mlp.add(Dense(output_size=1500, activation='tanh', noise='dropout'))
mlp.add(SoftmaxLayer(output_size=10))
mnist = MNIST()
optimizer = AdaDelta(model=mlp, dataset=mnist, epochs=10)
optimizer.train()
test_data, test_labels = mnist.test_inputs, mnist.test_targets
test_data = test_data[:25]
test_labels = test_labels[:25]
# use the run function!
yhat = mlp.run(test_data)
print('-------')
print('Prediction: %s' % str(yhat))
print('Actual: %s' % str(test_labels.astype('int32')))
def run_mlp():
# # define the model layers
# layer1 = BasicLayer(input_size=784, output_size=1000, activation='rectifier')
# layer2 = BasicLayer(inputs_hook=(1000, layer1.get_outputs()), output_size=1000, activation='rectifier')
# classlayer3 = SoftmaxLayer(inputs_hook=(1000, layer2.get_outputs()), output_size=10, out_as_probs=False)
# # add the layers to the prototype
# mlp = Prototype(layers=[layer1, layer2, classlayer3])
# test the new way to automatically fill in inputs_hook for models
mlp = Prototype()
mlp.add(BasicLayer(input_size=784, output_size=1000, activation="rectifier", noise="dropout"))
mlp.add(BasicLayer(output_size=1500, activation="tanh", noise="dropout"))
mlp.add(SoftmaxLayer(output_size=10))
mnist = MNIST()
optimizer = AdaDelta(model=mlp, dataset=mnist, n_epoch=10)
optimizer.train()
test_data, test_labels = mnist.getSubset(subset=TEST)
test_data = test_data[:25].eval()
test_labels = test_labels[:25].eval()
# use the run function!
yhat = mlp.run(test_data)
print("-------")
print("Prediction: %s" % str(yhat))
print("Actual: %s" % str(test_labels.astype("int32")))
def build_model():
# add layers one-by-one to a Prototype container to build neural net
# inputs_hook created automatically by Prototype; thus, no need to specify
mlp = Prototype()
mlp.add(BasicLayer(input_size=28*28, output_size=512, activation='rectifier', noise='dropout'))
mlp.add(BasicLayer(output_size=512, activation='rectifier', noise='dropout'))
mlp.add(SoftmaxLayer(output_size=10))
return mlp
def sequential_add_layers():
# This method is to demonstrate adding layers one-by-one to a Prototype container.
# As you can see, inputs_hook are created automatically by Prototype so we don't need to specify!
mlp = Prototype()
mlp.add(BasicLayer(input_size=28*28, output_size=1000, activation='rectifier', noise='dropout', noise_level=0.5))
mlp.add(BasicLayer(output_size=512, activation='rectifier', noise='dropout', noise_level=0.5))
mlp.add(SoftmaxLayer(output_size=10))
return mlp
def sequential_add_layers():
# This method is to demonstrate adding layers one-by-one to a Prototype container.
# As you can see, inputs_hook are created automatically by Prototype so we don't need to specify!
mlp = Prototype()
mlp.add(
BasicLayer(input_size=28 * 28,
output_size=1000,
activation='rectifier',
noise='dropout',
noise_level=0.5))
mlp.add(
BasicLayer(output_size=512,
activation='rectifier',
noise='dropout',
noise_level=0.5))
mlp.add(SoftmaxLayer(output_size=10))
return mlp
