Microsoft Cognitive Toolkit 简明教程

sudo apt update
sudo apt upgrade

wget -0 anaconda-installer.sh url SHAPE \* MERGEFORMAT
     y



	             f


      x

|                     }

sh ./anaconda-installer.sh

sh cuda_9.0.176_384.81_linux-run

export PATH=/usr/local/cuda-9.0/bin${PATH:+:${PATH}}
export LD_LIBRARY_PATH=/usr/local/cuda-9.0/lib64\
${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}
Installing

import sys
import os
from cntk import Trainer, Axis
from cntk.io import MinibatchSource, CTFDeserializer, StreamDef, StreamDefs,\
   INFINITELY_REPEAT
from cntk.learners import sgd, learning_parameter_schedule_per_sample
from cntk import input_variable, cross_entropy_with_softmax, \
   classification_error, sequence
from cntk.logging import ProgressPrinter
from cntk.layers import Sequential, Embedding, Recurrence, LSTM, Dense
def create_reader(path, is_training, input_dim, label_dim):
   return MinibatchSource(CTFDeserializer(path, StreamDefs(
      features=StreamDef(field='x', shape=input_dim, is_sparse=True),
      labels=StreamDef(field='y', shape=label_dim, is_sparse=False)
   )), randomize=is_training,
   max_sweeps=INFINITELY_REPEAT if is_training else 1)
def LSTM_sequence_classifier_net(input, num_output_classes, embedding_dim,
LSTM_dim, cell_dim):
   lstm_classifier = Sequential([Embedding(embedding_dim),
      Recurrence(LSTM(LSTM_dim, cell_dim)),
      sequence.last,
      Dense(num_output_classes)])
return lstm_classifier(input)
def train_sequence_classifier():
   input_dim = 2000
   cell_dim = 25
   hidden_dim = 25
   embedding_dim = 50
   num_output_classes = 5
   features = sequence.input_variable(shape=input_dim, is_sparse=True)
   label = input_variable(num_output_classes)
   classifier_output = LSTM_sequence_classifier_net(
   features, num_output_classes, embedding_dim, hidden_dim, cell_dim)
   ce = cross_entropy_with_softmax(classifier_output, label)
   pe =      classification_error(classifier_output, label)
   rel_path = ("../../../Tests/EndToEndTests/Text/" +
      "SequenceClassification/Data/Train.ctf")
   path = os.path.join(os.path.dirname(os.path.abspath(__file__)), rel_path)
   reader = create_reader(path, True, input_dim, num_output_classes)
input_map = {
   features: reader.streams.features,
   label: reader.streams.labels
}
lr_per_sample = learning_parameter_schedule_per_sample(0.0005)
progress_printer = ProgressPrinter(0)
trainer = Trainer(classifier_output, (ce, pe),
sgd(classifier_output.parameters, lr=lr_per_sample),progress_printer)
minibatch_size = 200
for i in range(255):
   mb = reader.next_minibatch(minibatch_size, input_map=input_map)
trainer.train_minibatch(mb)
   evaluation_average = float(trainer.previous_minibatch_evaluation_average)
   loss_average = float(trainer.previous_minibatch_loss_average)
return evaluation_average, loss_average
if __name__ == '__main__':
   error, _ = train_sequence_classifier()
   print(" error: %f" % error)

average  since  average  since  examples
loss     last   metric   last
------------------------------------------------------
1.61    1.61    0.886     0.886     44
1.61     1.6    0.714     0.629    133
 1.6    1.59     0.56     0.448    316
1.57    1.55    0.479      0.41    682
1.53     1.5    0.464     0.449   1379
1.46     1.4    0.453     0.441   2813
1.37    1.28     0.45     0.447   5679
 1.3    1.23    0.448     0.447  11365

error: 0.333333

X1 = 3.0
X2 = -2.0
X3 = 1.0

W1 = 0.65, W2 = 1.75, W3 = 2.05 and b = 0.33

Z = (X1*W1)+(X2*W2)+(X3+W3)+b
i.e. Z = (3.0)*(0.65) + (-2.0)*(1.75) + (1.0)*(2.05) + 0.33
= 0.83

P = 1.0/(1.0 + exp(-0.83)
= 0.6963

import numpy as np
import cntk as C
   def main():
print("Using CNTK version = " + str(C.__version__) + "\n")
data_file = ".\\dataLRmodel.txt" # provide the name and the location of data file
print("Loading data from " + data_file + "\n")
features_mat = np.loadtxt(data_file, dtype=np.float32, delimiter=",", skiprows=0, usecols=[0,1])
labels_mat = np.loadtxt(data_file, dtype=np.float32, delimiter=",", skiprows=0, usecols=[2], ndmin=2)
features_dim = 2
labels_dim = 1
X = C.ops.input_variable(features_dim, np.float32)
y = C.input_variable(labels_dim, np.float32)
W = C.parameter(shape=(features_dim, 1)) # trainable cntk.Parameter
b = C.parameter(shape=(labels_dim))
z = C.times(X, W) + b
p = 1.0 / (1.0 + C.exp(-z))
model = p
ce_error = C.binary_cross_entropy(model, y) # CE a bit more principled for LR
fixed_lr = 0.010
learner = C.sgd(model.parameters, fixed_lr)
trainer = C.Trainer(model, (ce_error), [learner])
max_iterations = 4000
np.random.seed(4)
N = len(features_mat)
for i in range(0, max_iterations):
row = np.random.choice(N,1) # pick a random row from training items
trainer.train_minibatch({ X: features_mat[row], y: labels_mat[row] })
if i % 1000 == 0 and i > 0:
mcee = trainer.previous_minibatch_loss_average
print(str(i) + " Cross-entropy error on curr item = %0.4f " % mcee)
np.set_printoptions(precision=4, suppress=True)
print("Model weights: ")
print(W.value)
print("Model bias:")
print(b.value)
if __name__ == "__main__":
  main()

Using CNTK version = 2.7
1000 cross entropy error on curr item = 0.1941
2000 cross entropy error on curr item = 0.1746
3000 cross entropy error on curr item = 0.0563
Model weights:
[-0.2049]
   [0.9666]]
Model bias:
[-2.2846]

import numpy as np
def main():
data_file = ".\\dataLRmodel.txt" # provide the name and the location of data file
features_mat = np.loadtxt(data_file, dtype=np.float32, delimiter=",",
skiprows=0, usecols=(0,1))
labels_mat = np.loadtxt(data_file, dtype=np.float32, delimiter=",",
skiprows=0, usecols=[2], ndmin=2)
print("Setting weights and bias values \n")
weights = np.array([0.0925, 1.1722], dtype=np.float32)
bias = np.array([-4.5400], dtype=np.float32)
N = len(features_mat)
features_dim = 2
print("item pred_prob pred_label act_label result")
for i in range(0, N): # each item
   x = features_mat[i]
   z = 0.0
   for j in range(0, features_dim):
     z += x[j] * weights[j]
   z += bias[0]
   pred_prob = 1.0 / (1.0 + np.exp(-z))
   pred_label = 0 if pred_prob < 0.5 else 1
   act_label = labels_mat[i]
   pred_str = ‘correct’ if np.absolute(pred_label - act_label) < 1.0e-5 \
     else ‘WRONG’
  print("%2d %0.4f %0.0f %0.0f %s" % \ (i, pred_prob, pred_label, act_label, pred_str))
x = np.array([9.5, 4.5], dtype=np.float32)
print("\nPredicting class for age, education = ")
print(x)
z = 0.0
for j in range(0, features_dim):
   z += x[j] * weights[j]
z += bias[0]
p = 1.0 / (1.0 + np.exp(-z))
print("Predicted p = " + str(p))
if p < 0.5: print("Predicted class = 0")
else: print("Predicted class = 1")
if __name__ == "__main__":
  main()

Item  pred_prob  pred_label  act_label  result
0   0.3640         0             0     correct
1   0.7254         1             0      WRONG
2   0.2019         0             0     correct
3   0.3562         0             0     correct
4   0.0493         0             0     correct
5   0.1005         0             0     correct
6   0.7892         1             1     correct
7   0.8564         1             1     correct
8   0.9654         1             1     correct
9   0.7587         1             1     correct
10  0.3040         0             1      WRONG
11  0.7129         1             1     correct
Predicting class for age, education =
[9.5 4.5]
Predicting p = 0.526487952
Predicting class = 1

from cntk.layers import Dense

from cntk import input_variable

feature = input_variable(100)

layer = Dense(40)(feature)

from cntk.layers import Dense
from cntk import input_variable
feature= input_variable(100)
layer = Dense(40)(feature)

from cntk.layers import Dense

from cntk.ops import sigmoid

from cntk.initializer import glorot_uniform

layer = Dense(50, activation = sigmoid, init = glorot_uniform)

label= input_variable(3)
loss = cross_entropy_with_softmax(z, label)

from cntk.learners import sgd

from cntk.train.trainer import Trainer

learner = sgd(z.parametrs, 0.01)

trainer = Trainer(z, (loss, error_rate), [learner])

from cntk.learners import sgd
from cntk.train.trainer import Trainer
learner = sgd(z.parametrs, 0.01)
trainer = Trainer(z, (loss, error_rate), [learner])

from import pandas as pd

df_source = pd.read_csv(‘iris.csv’, names = [‘sepal_length’, ‘sepal_width’,
‘petal_length’, ‘petal_width’, index_col=False)

x = df_source.iloc[:, :4].values

x = df_source[‘species’].values

label_mapping = {‘Iris-Setosa’ : 0, ‘Iris-Versicolor’ : 1, ‘Iris-Virginica’ : 2}

def one_hot(index, length):
result = np.zeros(length)
result[index] = 1
return result

y = np.array([one_hot(label_mapping[v], 3) for v in y])

from sklearn.model_selection import train_test_split

x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0-2,
stratify=y)

label_mapping = {‘Iris-Setosa’ : 0, ‘Iris-Versicolor’ : 1, ‘Iris-Virginica’ : 2}

trainer.train_minibatch({ features: X_train, label: y_train})

for _epoch in range(10):
trainer.train_minbatch ({ feature: X_train, label: y_train})
print(‘Loss: {}, Acc: {}’.format(
trainer.previous_minibatch_loss_average,
trainer.previous_minibatch_evaluation_average))

from import pandas as pd
df_source = pd.read_csv(‘iris.csv’, names = [‘sepal_length’, ‘sepal_width’, ‘petal_length’, ‘petal_width’, index_col=False)
x = df_source.iloc[:, :4].values
x = df_source[‘species’].values
label_mapping = {‘Iris-Setosa’ : 0, ‘Iris-Versicolor’ : 1, ‘Iris-Virginica’ : 2}
def one_hot(index, length):
result = np.zeros(length)
result[index] = 1
return result
y = np.array([one_hot(label_mapping[v], 3) for v in y])
from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0-2, stratify=y)
label_mapping = {‘Iris-Setosa’ : 0, ‘Iris-Versicolor’ : 1, ‘Iris-Virginica’ : 2}
trainer.train_minibatch({ features: X_train, label: y_train})
for _epoch in range(10):
trainer.train_minbatch ({ feature: X_train, label: y_train})
print(‘Loss: {}, Acc: {}’.format(
trainer.previous_minibatch_loss_average,
trainer.previous_minibatch_evaluation_average))

sample_index = np.random.choice(X_test.shape[0])
sample = X_test[sample_index]
inverted_mapping = {
   1:’Iris-setosa’,
   2:’Iris-versicolor’,
   3:’Iris-virginica’
}
prediction = z(sample)
predicted_label = inverted_mapping[np.argmax(prediction)]
print(predicted_label)

import numpy as np
num_samples = 20000

label_mapping = np.eye(2)

y = label_mapping[np.random.choice(2,num_samples)].astype(np.float32)

x = np.random.random(size=(num_samples, 4)).astype(np.float32)

from cntk.layers import Dense, Sequential

from cntk import input_variable, default_options
from cntk.ops import sigmoid

from cntk.losses import binary_cross_entropy

with default_options(activation=sigmoid):
model = Sequential([Dense(6),Dense(2)])

features = input_variable(4)

z = model(features)

from cntk.learners import sgd

from cntk.logging import ProgressPrinter
progress_writer = ProgressPrinter(0)

labels = input_variable(2)

loss = binary_cross_entropy(z, labels)

learner = sgd(z.parameters, lr=0.1)

training_summary=loss.train((x,y),parameter_learners=[learner],callbacks=[progress_writer])

import numpy as np
num_samples = 20000
label_mapping = np.eye(2)
y = label_mapping[np.random.choice(2,num_samples)].astype(np.float32)
x = np.random.random(size=(num_samples, 4)).astype(np.float32)
from cntk.layers import Dense, Sequential
from cntk import input_variable, default_options
from cntk.ops import sigmoid
from cntk.losses import binary_cross_entropy
with default_options(activation=sigmoid):
   model = Sequential([Dense(6),Dense(2)])
features = input_variable(4)
z = model(features)
from cntk.learners import sgd
from cntk.logging import ProgressPrinter
progress_writer = ProgressPrinter(0)
labels = input_variable(2)
loss = binary_cross_entropy(z, labels)
learner = sgd(z.parameters, lr=0.1)
training_summary=loss.train((x,y),parameter_learners=[learner],callbacks=[progress_writer])

Build info:
     Built time: *** ** **** 21:40:10
     Last modified date: *** *** ** 21:08:46 2019
     Build type: Release
     Build target: CPU-only
     With ASGD: yes
     Math lib: mkl
     Build Branch: HEAD
     Build SHA1:ae9c9c7c5f9e6072cc9c94c254f816dbdc1c5be6 (modified)
     MPI distribution: Microsoft MPI
     MPI version: 7.0.12437.6
-------------------------------------------------------------------
average   since   average   since examples
loss      last    metric    last
------------------------------------------------------
Learning rate per minibatch: 0.1
1.52      1.52      0         0     32
1.51      1.51      0         0     96
1.48      1.46      0         0    224
1.45      1.42      0         0    480
1.42       1.4      0         0    992
1.41      1.39      0         0   2016
1.4       1.39      0         0   4064
1.39      1.39      0         0   8160
1.39      1.39      0         0  16352

from cntk.layers import Dense, Sequential
from cntk import input_variable, default_options
from cntk.ops import sigmoid, log_softmax
from cntk.losses import binary_cross_entropy
model = Sequential([
Dense(4, activation=sigmoid),
Dense(3, activation=log_softmax)
])
features = input_variable(4)
z = model(features)

import numpy as np
import pandas as pd

df_source = pd.read_csv(‘iris.csv’, names = [‘sepal_length’, ‘sepal_width’,
 ‘petal_length’, ‘petal_width’, ‘species’], index_col=False)

label_mapping = {‘Iris-Setosa’ : 0, ‘Iris-Versicolor’ : 1, ‘Iris-Virginica’ : 2}

x = df_source.iloc[:, :4].values

y = df_source[‘species’].values

y = np.array([one_hot(label_mapping[v], 3) for v in y])

x= x.astype(np.float32)
y= y.astype(np.float32)

def one_hot(index, length):
result = np.zeros(length)
result[index] = index
return result

from cntk.losses import binary_cross_entropy_with_softmax

from cntk.learners import sgd

from cntk.logging import ProgressPrinter
progress_writer = ProgressPrinter(0)

labels = input_variable(3)

loss = binary_cross_entropy_with_softmax (z, labels)

learner = sgd(z.parameters, 0.1)

training_summary=loss.train((x,y),parameter_learners=[learner],callbacks=
[progress_writer],minibatch_size=16,max_epochs=5)

from cntk.layers import Dense, Sequential
from cntk import input_variable, default_options
from cntk.ops import sigmoid, log_softmax
from cntk.losses import binary_cross_entropy
model = Sequential([
Dense(4, activation=sigmoid),
Dense(3, activation=log_softmax)
])
features = input_variable(4)
z = model(features)
import numpy as np
import pandas as pd
df_source = pd.read_csv(‘iris.csv’, names = [‘sepal_length’, ‘sepal_width’, ‘petal_length’, ‘petal_width’, ‘species’], index_col=False)
label_mapping = {‘Iris-Setosa’ : 0, ‘Iris-Versicolor’ : 1, ‘Iris-Virginica’ : 2}
x = df_source.iloc[:, :4].values
y = df_source[‘species’].values
y = np.array([one_hot(label_mapping[v], 3) for v in y])
x= x.astype(np.float32)
y= y.astype(np.float32)
def one_hot(index, length):
result = np.zeros(length)
result[index] = index
return result
from cntk.losses import binary_cross_entropy_with_softmax
from cntk.learners import sgd
from cntk.logging import ProgressPrinter
progress_writer = ProgressPrinter(0)
labels = input_variable(3)
loss = binary_cross_entropy_with_softmax (z, labels)
learner = sgd(z.parameters, 0.1)
training_summary=loss.train((x,y),parameter_learners=[learner],callbacks=[progress_writer],minibatch_size=16,max_epochs=5)

Build info:
     Built time: *** ** **** 21:40:10
     Last modified date: *** *** ** 21:08:46 2019
     Build type: Release
     Build target: CPU-only
     With ASGD: yes
     Math lib: mkl
     Build Branch: HEAD
     Build SHA1:ae9c9c7c5f9e6072cc9c94c254f816dbdc1c5be6 (modified)
     MPI distribution: Microsoft MPI
     MPI version: 7.0.12437.6
-------------------------------------------------------------------
average    since    average   since   examples
loss        last     metric   last
------------------------------------------------------
Learning rate per minibatch: 0.1
1.1         1.1        0       0      16
0.835     0.704        0       0      32
1.993      1.11        0       0      48
1.14       1.14        0       0     112
[………]

from cntk.io import StreamDef, StreamDefs, MinibatchSource, CTFDeserializer,
 INFINITY_REPEAT

labels_stream = StreamDef(field=’labels’, shape=3, is_sparse=False)

feature_stream = StreamDef(field=’features’, shape=4, is_sparse=False)

deserializer = CTFDeserializer(‘iris.ctf’, StreamDefs(labels=
label_stream, features=features_stream)

Minibatch_source = MinibatchSource(deserializer, randomize=True)

from cntk.io import StreamDef, StreamDefs, MinibatchSource, CTFDeserializer, INFINITY_REPEAT
labels_stream = StreamDef(field=’labels’, shape=3, is_sparse=False)
feature_stream = StreamDef(field=’features’, shape=4, is_sparse=False)
deserializer = CTFDeserializer(‘iris.ctf’, StreamDefs(labels=label_stream, features=features_stream)
Minibatch_source = MinibatchSource(deserializer, randomize=True)

import pandas as pd
import numpy as np

df_source = pd.read_csv(‘iris.csv’, names = [‘sepal_length’, ‘sepal_width’, ‘petal_length’, ‘petal_width’, ‘species’], index_col=False)

features = df_source.iloc[: , :4].values
labels = df_source[‘species’].values

label_mapping = {‘Iris-Setosa’ : 0, ‘Iris-Versicolor’ : 1, ‘Iris-Virginica’ : 2}

labels = [one_hot(label_mapping[v], 3) for v in labels]

def one_hot(index, length):
result = np.zeros(length)
result[index] = 1
return result

With open(‘iris.ctf’, ‘w’) as output_file:
for index in range(0, feature.shape[0]):
feature_values = ‘ ‘.join([str(x) for x in np.nditer(features[index])])
label_values = ‘ ‘.join([str(x) for x in np.nditer(labels[index])])
output_file.write(‘features {} | labels {} \n’.format(feature_values, label_values))

import pandas as pd
import numpy as np
df_source = pd.read_csv(‘iris.csv’, names = [‘sepal_length’, ‘sepal_width’, ‘petal_length’, ‘petal_width’, ‘species’], index_col=False)
features = df_source.iloc[: , :4].values
labels = df_source[‘species’].values
label_mapping = {‘Iris-Setosa’ : 0, ‘Iris-Versicolor’ : 1, ‘Iris-Virginica’ : 2}
labels = [one_hot(label_mapping[v], 3) for v in labels]
def one_hot(index, length):
result = np.zeros(length)
result[index] = 1
return result
With open(‘iris.ctf’, ‘w’) as output_file:
for index in range(0, feature.shape[0]):
feature_values = ‘ ‘.join([str(x) for x in np.nditer(features[index])])
label_values = ‘ ‘.join([str(x) for x in np.nditer(labels[index])])
output_file.write(‘features {} | labels {} \n’.format(feature_values, label_values))

from cntk.logging import ProgressPrinter

from cntk.train import Trainer,

minbatch_size = 16
samples_per_epoch = 150
num_epochs = 30

input_map = {
     features: minibatch.source.streams.features,
     labels: minibatch.source.streams.features
}

progress_writer = ProgressPrinter(0)

train_history = loss.train(minibatch_source,
parameter_learners=[learner],
  model_inputs_to_streams=input_map,
callbacks=[progress_writer],
epoch_size=samples_per_epoch,
max_epochs=num_epochs)

from cntk.logging import ProgressPrinter
from cntk.train import Trainer, training_session
minbatch_size = 16
samples_per_epoch = 150
num_epochs = 30
input_map = {
   features: minibatch.source.streams.features,
   labels: minibatch.source.streams.features
}
progress_writer = ProgressPrinter(0)
train_history = loss.train(minibatch_source,
parameter_learners=[learner],
model_inputs_to_streams=input_map,
callbacks=[progress_writer],
epoch_size=samples_per_epoch,
max_epochs=num_epochs)

-------------------------------------------------------------------
average   since   average   since  examples
loss      last     metric   last
------------------------------------------------------
Learning rate per minibatch: 0.1
1.21      1.21      0        0       32
1.15      0.12      0        0       96
[………]

from sklearn.datasets import load_iris
iris = load_iris()
X = iris.data
y = iris.target
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=1)
# Here above test_size = 0.2 represents that we provided 20% of the data as test data.
from sklearn.neighbors import KNeighborsClassifier
from sklearn import metrics
classifier_knn = KNeighborsClassifier(n_neighbors=3)
classifier_knn.fit(X_train, y_train)
y_pred = classifier_knn.predict(X_test)
# Providing sample data and the model will make prediction out of that data
sample = [[5, 5, 3, 2], [2, 4, 3, 5]]
preds = classifier_knn.predict(sample)
pred_species = [iris.target_names[p] for p in preds] print("Predictions:", pred_species)

Predictions: ['versicolor', 'virginica']

from numpy import array
from sklearn.model_selection import KFold
data = array([0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0])
kfold = KFold(5, True, 1)
for train, test in kfold.split(data):
   print('train: %s, test: %s' % (data[train],(data[test]))

train: [0.1 0.2 0.4 0.5 0.6 0.7 0.8 0.9], test: [0.3 1. ]
train: [0.1 0.2 0.3 0.4 0.6 0.8 0.9 1. ], test: [0.5 0.7]
train: [0.2 0.3 0.5 0.6 0.7 0.8 0.9 1. ], test: [0.1 0.4]
train: [0.1 0.3 0.4 0.5 0.6 0.7 0.9 1. ], test: [0.2 0.8]
train: [0.1 0.2 0.3 0.4 0.5 0.7 0.8 1. ], test: [0.6 0.9]

Import numpy as np
Import cntk as C
def create_reader(path, input_dim, output_dim, rnd_order, sweeps):
x_strm = C.io.StreamDef(field='attribs', shape=input_dim, is_sparse=False)
y_strm = C.io.StreamDef(field='species', shape=output_dim, is_sparse=False)
streams = C.io.StreamDefs(x_src=x_strm, y_src=y_strm)
deserial = C.io.CTFDeserializer(path, streams)
mb_src = C.io.MinibatchSource(deserial, randomize=rnd_order, max_sweeps=sweeps)
return mb_src
def main():
print("Using CNTK version = " + str(C.__version__) + "\n")
input_dim = 4
hidden_dim = 5
output_dim = 3
train_file = ".\\...\\" #provide the name of the training file(120 data items)
test_file = ".\\...\\" #provide the name of the test file(30 data items)
X = C.ops.input_variable(input_dim, np.float32)
Y = C.ops.input_variable(output_dim, np.float32)
with C.layers.default_options(init=C.initializer.uniform(scale=0.01, seed=1)):
hLayer = C.layers.Dense(hidden_dim, activation=C.ops.tanh, name='hidLayer')(X)
oLayer = C.layers.Dense(output_dim, activation=None, name='outLayer')(hLayer)
nnet = oLayer
model = C.ops.softmax(nnet)
tr_loss = C.cross_entropy_with_softmax(nnet, Y)
tr_clas = C.classification_error(nnet, Y)
max_iter = 2000
batch_size = 10
learn_rate = 0.01
learner = C.sgd(nnet.parameters, learn_rate)
trainer = C.Trainer(nnet, (tr_loss, tr_clas), [learner])
max_iter = 2000
batch_size = 10
lr_schedule = C.learning_parameter_schedule_per_sample([(1000, 0.05), (1, 0.01)])
mom_sch = C.momentum_schedule([(100, 0.99), (0, 0.95)], batch_size)
learner = C.fsadagrad(nnet.parameters, lr=lr_schedule, momentum=mom_sch)
trainer = C.Trainer(nnet, (tr_loss, tr_clas), [learner])
rdr = create_reader(train_file, input_dim, output_dim, rnd_order=True, sweeps=C.io.INFINITELY_REPEAT)
iris_input_map = { X : rdr.streams.x_src, Y : rdr.streams.y_src }
for i in range(0, max_iter):
curr_batch = rdr.next_minibatch(batch_size, input_map=iris_input_map) trainer.train_minibatch(curr_batch)
if i % 500 == 0:
mcee = trainer.previous_minibatch_loss_average
macc = (1.0 - trainer.previous_minibatch_evaluation_average) * 100
print("batch %4d: mean loss = %0.4f, accuracy = %0.2f%% " \ % (i, mcee, macc))
print("\nEvaluating test data \n")
rdr = create_reader(test_file, input_dim, output_dim, rnd_order=False, sweeps=1)
iris_input_map = { X : rdr.streams.x_src, Y : rdr.streams.y_src }
num_test = 30
all_test = rdr.next_minibatch(num_test, input_map=iris_input_map) acc = (1.0 - trainer.test_minibatch(all_test)) * 100
print("Classification accuracy = %0.2f%%" % acc)
np.set_printoptions(precision = 1, suppress=True)
unknown = np.array([[7.0, 3.2, 4.7, 1.4]], dtype=np.float32)
print("\nPredicting species for input features: ")
print(unknown[0])
pred_prob = model.eval(unknown)
np.set_printoptions(precision = 4, suppress=True)
print("Prediction probabilities: ")
print(pred_prob[0])
if __name__== ”__main__”:
main()

Using CNTK version = 2.7
batch 0: mean loss = 1.0986, mean accuracy = 40.00%
batch 500: mean loss = 0.6677, mean accuracy = 80.00%
batch 1000: mean loss = 0.5332, mean accuracy = 70.00%
batch 1500: mean loss = 0.2408, mean accuracy = 100.00%
Evaluating test data
Classification accuracy = 94.58%
Predicting species for input features:
[7.0 3.2 4.7 1.4]
Prediction probabilities:
[0.0847 0.736 0.113]

def create_reader(path, input_dim, output_dim, rnd_order, sweeps):
x_strm = C.io.StreamDef(field='stats', shape=input_dim, is_sparse=False)
y_strm = C.io.StreamDef(field='forgery', shape=output_dim, is_sparse=False)
streams = C.io.StreamDefs(x_src=x_strm, y_src=y_strm)
deserial = C.io.CTFDeserializer(path, streams)
mb_src = C.io.MinibatchSource(deserial, randomize=rnd_order, max_sweeps=sweeps)
return mb_src
def main():
print("Using CNTK version = " + str(C.__version__) + "\n")
input_dim = 4
hidden_dim = 10
output_dim = 2
train_file = ".\\...\\" #provide the name of the training file
test_file = ".\\...\\" #provide the name of the test file
X = C.ops.input_variable(input_dim, np.float32)
Y = C.ops.input_variable(output_dim, np.float32)
withC.layers.default_options(init=C.initializer.uniform(scale=0.01, seed=1)):
hLayer = C.layers.Dense(hidden_dim, activation=C.ops.tanh, name='hidLayer')(X)
oLayer = C.layers.Dense(output_dim, activation=None, name='outLayer')(hLayer)
nnet = oLayer
model = C.ops.softmax(nnet)
tr_loss = C.cross_entropy_with_softmax(nnet, Y)
tr_clas = C.classification_error(nnet, Y)
max_iter = 500
batch_size = 10
learn_rate = 0.01
learner = C.sgd(nnet.parameters, learn_rate)
trainer = C.Trainer(nnet, (tr_loss, tr_clas), [learner])
rdr = create_reader(train_file, input_dim, output_dim, rnd_order=True, sweeps=C.io.INFINITELY_REPEAT)
banknote_input_map = { X : rdr.streams.x_src, Y : rdr.streams.y_src }
for i in range(0, max_iter):
curr_batch = rdr.next_minibatch(batch_size, input_map=iris_input_map) trainer.train_minibatch(curr_batch)
if i % 500 == 0:
mcee = trainer.previous_minibatch_loss_average
macc = (1.0 - trainer.previous_minibatch_evaluation_average) * 100
print("batch %4d: mean loss = %0.4f, accuracy = %0.2f%% " \ % (i, mcee, macc))
print("\nEvaluating test data \n")
rdr = create_reader(test_file, input_dim, output_dim, rnd_order=False, sweeps=1)
banknote_input_map = { X : rdr.streams.x_src, Y : rdr.streams.y_src }
num_test = 20
all_test = rdr.next_minibatch(num_test, input_map=iris_input_map) acc = (1.0 - trainer.test_minibatch(all_test)) * 100
print("Classification accuracy = %0.2f%%" % acc)
np.set_printoptions(precision = 1, suppress=True)
unknown = np.array([[0.6, 1.9, -3.3, -0.3]], dtype=np.float32)
print("\nPredicting Banknote authenticity for input features: ")
print(unknown[0])
pred_prob = model.eval(unknown)
np.set_printoptions(precision = 4, suppress=True)
print("Prediction probabilities are: ")
print(pred_prob[0])
if pred_prob[0,0] < pred_prob[0,1]:
print(“Prediction: authentic”)
else:
print(“Prediction: fake”)
if __name__== ”__main__”:
main()

Using CNTK version = 2.7
batch 0: mean loss = 0.6928, accuracy = 80.00%
batch 50: mean loss = 0.6877, accuracy = 70.00%
batch 100: mean loss = 0.6432, accuracy = 80.00%
batch 150: mean loss = 0.4978, accuracy = 80.00%
batch 200: mean loss = 0.4551, accuracy = 90.00%
batch 250: mean loss = 0.3755, accuracy = 90.00%
batch 300: mean loss = 0.2295, accuracy = 100.00%
batch 350: mean loss = 0.1542, accuracy = 100.00%
batch 400: mean loss = 0.1581, accuracy = 100.00%
batch 450: mean loss = 0.1499, accuracy = 100.00%
Evaluating test data
Classification accuracy = 84.58%
Predicting banknote authenticity for input features:
[0.6 1.9 -3.3 -0.3]
Prediction probabilities are:
[0.7847 0.2536]
Prediction: fake

import numpy as np
import cntk as C
def create_reader(path, input_dim, output_dim, rnd_order, sweeps):
x_strm = C.io.StreamDef(field='stats', shape=input_dim, is_sparse=False)
y_strm = C.io.StreamDef(field='forgery', shape=output_dim, is_sparse=False)
streams = C.io.StreamDefs(x_src=x_strm, y_src=y_strm)
deserial = C.io.CTFDeserializer(path, streams)
mb_src = C.io.MinibatchSource(deserial, randomize=rnd_order, max_sweeps=sweeps)
return mb_src
def class_acc(mb, x_var, y_var, model):
num_correct = 0; num_wrong = 0
x_mat = mb[x_var].asarray()
y_mat = mb[y_var].asarray()
for i in range(mb[x_var].shape[0]):
  p = model.eval(x_mat[i]
  y = y_mat[i]
  if p[0,0] < 0.5 and y[0,0] == 0.0 or p[0,0] >= 0.5 and y[0,0] == 1.0:
  num_correct += 1
 else:
  num_wrong += 1
return (num_correct * 100.0)/(num_correct + num_wrong)
def main():
print("Using CNTK version = " + str(C.__version__) + "\n")
input_dim = 4
hidden_dim = 10
output_dim = 1
train_file = ".\\...\\" #provide the name of the training file
test_file = ".\\...\\" #provide the name of the test file
X = C.ops.input_variable(input_dim, np.float32)
Y = C.ops.input_variable(output_dim, np.float32)
with C.layers.default_options(init=C.initializer.uniform(scale=0.01, seed=1)):
hLayer = C.layers.Dense(hidden_dim, activation=C.ops.tanh, name='hidLayer')(X)
oLayer = C.layers.Dense(output_dim, activation=None, name='outLayer')(hLayer)
model = oLayer
tr_loss = C.cross_entropy_with_softmax(model, Y)
max_iter = 1000
batch_size = 10
learn_rate = 0.01
learner = C.sgd(model.parameters, learn_rate)
trainer = C.Trainer(model, (tr_loss), [learner])
rdr = create_reader(train_file, input_dim, output_dim, rnd_order=True, sweeps=C.io.INFINITELY_REPEAT)
banknote_input_map = {X : rdr.streams.x_src, Y : rdr.streams.y_src }
for i in range(0, max_iter):
curr_batch = rdr.next_minibatch(batch_size, input_map=iris_input_map) trainer.train_minibatch(curr_batch)
if i % 100 == 0:
mcee=trainer.previous_minibatch_loss_average
ca = class_acc(curr_batch, X,Y, model)
print("batch %4d: mean loss = %0.4f, accuracy = %0.2f%% " \ % (i, mcee, ca))
print("\nEvaluating test data \n")
rdr = create_reader(test_file, input_dim, output_dim, rnd_order=False, sweeps=1)
banknote_input_map = { X : rdr.streams.x_src, Y : rdr.streams.y_src }
num_test = 20
all_test = rdr.next_minibatch(num_test, input_map=iris_input_map)
acc = class_acc(all_test, X,Y, model)
print("Classification accuracy = %0.2f%%" % acc)
np.set_printoptions(precision = 1, suppress=True)
unknown = np.array([[0.6, 1.9, -3.3, -0.3]], dtype=np.float32)
print("\nPredicting Banknote authenticity for input features: ")
print(unknown[0])
pred_prob = model.eval({X:unknown})
print("Prediction probability: ")
print(“%0.4f” % pred_prob[0,0])
if pred_prob[0,0] < 0.5:
  print(“Prediction: authentic”)
else:
  print(“Prediction: fake”)
if __name__== ”__main__”:
   main()

Using CNTK version = 2.7
batch 0: mean loss = 0.6936, accuracy = 10.00%
batch 100: mean loss = 0.6882, accuracy = 70.00%
batch 200: mean loss = 0.6597, accuracy = 50.00%
batch 300: mean loss = 0.5298, accuracy = 70.00%
batch 400: mean loss = 0.4090, accuracy = 100.00%
batch 500: mean loss = 0.3790, accuracy = 90.00%
batch 600: mean loss = 0.1852, accuracy = 100.00%
batch 700: mean loss = 0.1135, accuracy = 100.00%
batch 800: mean loss = 0.1285, accuracy = 100.00%
batch 900: mean loss = 0.1054, accuracy = 100.00%
Evaluating test data
Classification accuracy = 84.00%
Predicting banknote authenticity for input features:
[0.6 1.9 -3.3 -0.3]
Prediction probability:
0.8846
Prediction: fake

import numpy as np
import cntk as C
def create_reader(path, input_dim, output_dim, rnd_order, sweeps):
x_strm = C.io.StreamDef(field='predictors', shape=input_dim, is_sparse=False)
y_strm = C.io.StreamDef(field='medval', shape=output_dim, is_sparse=False)
streams = C.io.StreamDefs(x_src=x_strm, y_src=y_strm)
deserial = C.io.CTFDeserializer(path, streams)
mb_src = C.io.MinibatchSource(deserial, randomize=rnd_order, max_sweeps=sweeps)
return mb_src
def mb_accuracy(mb, x_var, y_var, model, delta):
num_correct = 0
num_wrong = 0
x_mat = mb[x_var].asarray()
y_mat = mb[y_var].asarray()
for i in range(mb[x_var].shape[0]):
   v = model.eval(x_mat[i])
   y = y_mat[i]
if np.abs(v[0,0] – y[0,0]) < delta:
   num_correct += 1
else:
   num_wrong += 1
return (num_correct * 100.0)/(num_correct + num_wrong)
def main():
print("Using CNTK version = " + str(C.__version__) + "\n")
input_dim = 5
hidden_dim = 20
output_dim = 1
train_file = ".\\...\\" #provide the name of the training file(80 data items)
test_file = ".\\...\\" #provide the name of the test file(20 data items)
X = C.ops.input_variable(input_dim, np.float32)
Y = C.ops.input_variable(output_dim, np.float32)
with C.layers.default_options(init=C.initializer.uniform(scale=0.01, seed=1)):
hLayer = C.layers.Dense(hidden_dim, activation=C.ops.tanh, name='hidLayer')(X)
oLayer = C.layers.Dense(output_dim, activation=None, name='outLayer')(hLayer)
model = C.ops.alias(oLayer)
tr_loss = C.squared_error(model, Y)
max_iter = 3000
batch_size = 5
base_learn_rate = 0.02
sch = C.learning_parameter_schedule([base_learn_rate, base_learn_rate/2], minibatch_size=batch_size, epoch_size=int((max_iter*batch_size)/2))
learner = C.sgd(model.parameters, sch)
trainer = C.Trainer(model, (tr_loss), [learner])
rdr = create_reader(train_file, input_dim, output_dim, rnd_order=True, sweeps=C.io.INFINITELY_REPEAT)
boston_input_map = { X : rdr.streams.x_src, Y : rdr.streams.y_src }
for i in range(0, max_iter):
curr_batch = rdr.next_minibatch(batch_size, input_map=boston_input_map) trainer.train_minibatch(curr_batch)
if i % int(max_iter/10) == 0:
   mcee = trainer.previous_minibatch_loss_average
   acc = mb_accuracy(curr_batch, X, Y, model, delta=3.00)
   print("batch %4d: mean squared error = %8.4f, accuracy = %5.2f%% " \ % (i, mcee, acc))
   print("\nEvaluating test data \n")
   rdr = create_reader(test_file, input_dim, output_dim, rnd_order=False, sweeps=1)
   boston_input_map = { X : rdr.streams.x_src, Y : rdr.streams.y_src }
   num_test = 20
all_test = rdr.next_minibatch(num_test, input_map=boston_input_map)
acc = mb_accuracy(all_test, X, Y, model, delta=3.00)
print("Prediction accuracy = %0.2f%%" % acc)
np.set_printoptions(precision = 2, suppress=True)
unknown = np.array([[0.09, 50.00, 4.5, 17.00, 350.00], dtype=np.float32)
print("\nPredicting median home value for feature/predictor values: ")
print(unknown[0])
pred_prob = model.eval({X: unknown)
print("\nPredicted value is: ")
print(“$%0.2f (x1000)” %pred_value[0,0])
if __name__== ”__main__”:
   main()

Using CNTK version = 2.7
batch 0: mean squared error = 385.6727, accuracy = 0.00%
batch 300: mean squared error = 41.6229, accuracy = 20.00%
batch 600: mean squared error = 28.7667, accuracy = 40.00%
batch 900: mean squared error = 48.6435, accuracy = 40.00%
batch 1200: mean squared error = 77.9562, accuracy = 80.00%
batch 1500: mean squared error = 7.8342, accuracy = 60.00%
batch 1800: mean squared error = 47.7062, accuracy = 60.00%
batch 2100: mean squared error = 40.5068, accuracy = 40.00%
batch 2400: mean squared error = 46.5023, accuracy = 40.00%
batch 2700: mean squared error = 15.6235, accuracy = 60.00%
Evaluating test data
Prediction accuracy = 64.00%
Predicting median home value for feature/predictor values:
[0.09 50. 4.5 17. 350.]
Predicted value is:
$21.02(x1000)

from sklearn.metrics import confusion_matrix
y_true = np.argmax(y_test, axis=1)
y_pred = np.argmax(z(X_test), axis=1)
matrix = confusion_matrix(y_true=y_true, y_pred=y_pred)
print(matrix)

[[10 0 0]
[ 0 1 9]
[ 0 0 10]]

import seaborn as sns
import matplotlib.pyplot as plt
g = sns.heatmap(matrix,
     annot=True,
     xticklabels=label_encoder.classes_.tolist(),
     yticklabels=label_encoder.classes_.tolist(),
     cmap='Blues')
g.set_yticklabels(g.get_yticklabels(), rotation=0)
plt.show()

loss.test([X_test, y_test])

{'metric': 0.36666666666, 'samples': 30}

{'metric': 0.83101488749, 'samples': 30}

from cntk import default_option, input_variable
from cntk.layers import Dense, Sequential
from cntk.ops import relu

with default_options(activation=relu):
model = Sequential([Dense(64),Dense(64),Dense(1,activation=None)])

features = input_variable(X.shape[1])

target = input_variable(1)
z = model(features)

from sklearn.preprocessing import StandardScalar

from sklearn.model_selection import train_test_split

x = df_cars.drop(columns=[‘mpg’]).values.astype(np.float32)
y=df_cars.iloc[: , 0].values.reshape(-1, 1).astype(np.float32)
scaler = StandardScaler()
X = scaler.fit_transform(x)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

target = input_variable(1)
z = model(features)

import cntk
def absolute_error(output, target):
   return cntk.ops.reduce_mean(cntk.ops.abs(output – target))
@ cntk.Function
def criterion_factory(output, target):
   loss = squared_error(output, target)
   metric = absolute_error(output, target)
   return loss, metric

from cntk.losses import squared_error
from cntk.learners import sgd
from cntk.logging import ProgressPrinter
progress_printer = ProgressPrinter(0)
loss = criterion_factory (z, target)
learner = sgd(z.parameters, 0.001)
training_summary=loss.train((x_train,y_train),parameter_learners=[learner],callbacks=[progress_printer],minibatch_size=16,max_epochs=10)

from cntk import default_option, input_variable
from cntk.layers import Dense, Sequential
from cntk.ops import relu
with default_options(activation=relu):
model = Sequential([Dense(64),Dense(64),Dense(1,activation=None)])
features = input_variable(X.shape[1])
target = input_variable(1)
z = model(features)
from sklearn.preprocessing import StandardScalar
from sklearn.model_selection import train_test_split
x = df_cars.drop(columns=[‘mpg’]).values.astype(np.float32)
y=df_cars.iloc[: , 0].values.reshape(-1, 1).astype(np.float32)
scaler = StandardScaler()
X = scaler.fit_transform(x)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
target = input_variable(1)
z = model(features)
import cntk
def absolute_error(output, target):
   return cntk.ops.reduce_mean(cntk.ops.abs(output – target))
@ cntk.Function
def criterion_factory(output, target):
loss = squared_error(output, target)
metric = absolute_error(output, target)
return loss, metric
from cntk.losses import squared_error
from cntk.learners import sgd
from cntk.logging import ProgressPrinter
progress_printer = ProgressPrinter(0)
loss = criterion_factory (z, target)
learner = sgd(z.parameters, 0.001)
training_summary=loss.train((x_train,y_train),parameter_learners=[learner],callbacks=[progress_printer],minibatch_size=16,max_epochs=10)

-------------------------------------------------------------------
average  since   average   since  examples
loss     last    metric    last
------------------------------------------------------
Learning rate per minibatch: 0.001
690       690     24.9     24.9       16
654       636     24.1     23.7       48
[………]

loss.test([X_test, y_test])

{'metric': 1.89679785619, 'samples': 79}

from cntk.io import StreamDef, StreamDefs, MinibatchSource, CTFDeserializer, INFINITY_REPEAT
def create_datasource(filename, limit =INFINITELY_REPEAT)
labels_stream = StreamDef(field=’labels’, shape=3, is_sparse=False)
feature_stream = StreamDef(field=’features’, shape=4, is_sparse=False)
deserializer = CTFDeserializer(filename, StreamDefs(labels=label_stream, features=features_stream)
Minibatch_source = MinibatchSource(deserializer, randomize=True, max_sweeps=limit)
return minibatch_source
training_source = create_datasource(‘Iris_train.ctf’)
test_source = create_datasource(‘Iris_test.ctf’, limit=1)
from cntk.logging import ProgressPrinter
from cntk.train import Trainer, training_session
minbatch_size = 16
samples_per_epoch = 150
num_epochs = 30
max_samples = samples_per_epoch * num_epochs
input_map = {
   features:   training_source.streams.features,
   labels: training_source.streams.labels
 }
progress_writer = ProgressPrinter(0)
trainer: training_source.streams.labels
session = training_session(trainer,
   mb_source=training_source,
   mb_size=minibatch_size,
   model_inputs_to_streams=input_map,
   max_samples=max_samples,
   test_config=test_config)
session.train()
from cntk.train import TestConfig
Test_config = TestConfig(test_source)

-------------------------------------------------------------------
average   since   average   since  examples
loss      last    metric    last
------------------------------------------------------
Learning rate per minibatch: 0.1
1.57      1.57     0.214    0.214   16
1.38      1.28     0.264    0.289   48
[………]
Finished Evaluation [1]: Minibatch[1-1]:metric = 69.65*30;

from cntk import default_options, input_variable
from cntk.layers import Dense, Sequential
from cntk.ops import log_softmax, relu, sigmoid
from cntk.learners import sgd
model = Sequential([
   Dense(4, activation=sigmoid),
   Dense(3, activation=log_softmax)
])
features = input_variable(4)
labels = input_variable(3)
z = model(features)
import cntk
from cntk.losses import cross_entropy_with_softmax, fmeasure
@cntk.Function
def criterion_factory(outputs, targets):
   loss = cross_entropy_with_softmax(outputs, targets)
   metric = fmeasure(outputs, targets, beta=1)
   return loss, metric
loss = criterion_factory(z, labels)
learner = sgd(z.parameters, 0.1)
label_mapping = {
   'Iris-setosa': 0,
   'Iris-versicolor': 1,
   'Iris-virginica': 2
}
import pandas as pd
import numpy as np
from cntk.logging import ProgressPrinter
from cntk.train import Trainer
progress_writer = ProgressPrinter(0)
trainer = Trainer(z, loss, learner, progress_writer)
for _ in range(0,30):
   input_data = pd.read_csv('iris.csv',
      names=['sepal_length', 'sepal_width','petal_length','petal_width', 'species'],
      index_col=False, chunksize=16)
for df_batch in input_data:
   feature_values = df_batch.iloc[:,:4].values
   feature_values = feature_values.astype(np.float32)
   label_values = df_batch.iloc[:,-1]
label_values = label_values.map(lambda x: label_mapping[x])
label_values = label_values.values
   encoded_labels = np.zeros((label_values.shape[0], 3))
   encoded_labels[np.arange(label_values.shape[0]),
label_values] = 1.
   trainer.train_minibatch({features: feature_values, labels: encoded_labels})

-------------------------------------------------------------------
average    since    average   since  examples
loss       last      metric   last
------------------------------------------------------
Learning rate per minibatch: 0.1
1.45       1.45     -0.189    -0.189   16
1.24       1.13     -0.0382    0.0371  48
[………]

from cntk import Evaluator
evaluator = Evaluator(loss.outputs[1], [progress_writer])
input_data = pd.read_csv('iris.csv',
   names=['sepal_length', 'sepal_width','petal_length','petal_width', 'species'],
index_col=False, chunksize=16)
for df_batch in input_data:
   feature_values = df_batch.iloc[:,:4].values
   feature_values = feature_values.astype(np.float32)
   label_values = df_batch.iloc[:,-1]
   label_values = label_values.map(lambda x: label_mapping[x])
   label_values = label_values.values
   encoded_labels = np.zeros((label_values.shape[0], 3))
   encoded_labels[np.arange(label_values.shape[0]), label_values] = 1.
   evaluator.test_minibatch({ features: feature_values, labels:
      encoded_labels})
evaluator.summarize_test_progress()

Finished Evaluation [1]: Minibatch[1-11]:metric = 74.62*143;

training_summary=loss.train((x_train,y_train),
parameter_learners=[learner],
callbacks=[progress_writer]),
minibatch_size=16, max_epochs=15)

from cntk.logging import ProgressPrinter
callbacks = [
   ProgressPrinter(0)
]
Trainer = Trainer(z, (loss, metric), learner, [callbacks])

ProgressPrinter(0, log_to_file=’test.txt’)

Test.txt
CNTKCommandTrainInfo: train : 300
CNTKCommandTrainInfo: CNTKNoMoreCommands_Total : 300
CNTKCommandTrainBegin: train
-------------------------------------------------------------------
average since average since examples
loss last metric last
------------------------------------------------------
Learning rate per minibatch: 0.1
1.45 1.45 -0.189 -0.189 16
1.24 1.13 -0.0382 0.0371 48
[………]

from cntk.layers import Convolution2D, Sequential, Dense, MaxPooling
from cntk.ops import log_softmax, relu
from cntk.initializer import glorot_uniform
from cntk import input_variable, default_options
features = input_variable((3,28,28))
labels = input_variable(10)
with default_options(initialization=glorot_uniform, activation=relu):
model = Sequential([
   Convolution2D(filter_shape=(5,5), strides=(1,1), num_filters=8, pad=True),
MaxPooling(filter_shape=(2,2), strides=(2,2)),
   Convolution2D(filter_shape=(5,5), strides=(1,1), num_filters=16, pad=True),
MaxPooling(filter_shape=(3,3), strides=(3,3)),
Dense(10, activation=log_softmax)
])
z = model(features)

from cntk.layers import Convolution2D, Sequential, Dense, MaxPooling
from cntk.ops import log_softmax, relu
from cntk.initializer import glorot_uniform
from cntk import input_variable, default_options
features = input_variable((3,28,28))
labels = input_variable(10)
with default_options(initialization=glorot_uniform, activation=relu):
model = Sequential([
   Convolution2D(filter_shape=(5,5), strides=(1,1), num_filters=8, pad=True),
MaxPooling(filter_shape=(2,2), strides=(2,2)),
   Convolution2D(filter_shape=(5,5), strides=(1,1), num_filters=16, pad=True),
MaxPooling(filter_shape=(3,3), strides=(3,3)),
Dense(10, activation=log_softmax)
])
z = model(features)
import os
from cntk.io import MinibatchSource, StreamDef, StreamDefs, ImageDeserializer, INFINITELY_REPEAT
import cntk.io.transforms as xforms
def create_datasource(folder, train=True, max_sweeps=INFINITELY_REPEAT):
   mapping_file = os.path.join(folder, 'mapping.bin')
   image_transforms = []
   if train:
    image_transforms += [
     xforms.crop(crop_type='randomside', side_ratio=0.8),
     xforms.scale(width=28, height=28, channels=3, interpolations='linear')
]
   stream_definitions = StreamDefs(
   features=StreamDef(field='image', transforms=image_transforms),
    labels=StreamDef(field='label', shape=10)
)
   deserializer = ImageDeserializer(mapping_file, stream_definitions)
return MinibatchSource(deserializer, max_sweeps=max_sweeps)
train_datasource = create_datasource('mnist_train')
test_datasource = create_datasource('mnist_test', max_sweeps=1, train=False)
from cntk import Function
from cntk.losses import cross_entropy_with_softmax
from cntk.metrics import classification_error
from cntk.learners import sgd
@Function
def criterion_factory(output, targets):
   loss = cross_entropy_with_softmax(output, targets)
   metric = classification_error(output, targets)
return loss, metric
loss = criterion_factory(z, labels)
learner = sgd(z.parameters, lr=0.2)
from cntk.logging import ProgressPrinter
from cntk.train import TestConfig
progress_writer = ProgressPrinter(0)
test_config = TestConfig(test_datasource)
input_map = {
   features: train_datasource.streams.features,
   labels: train_datasource.streams.labels
}
loss.train(train_datasource,
     max_epochs=10,
     minibatch_size=64,
     epoch_size=60000,
        parameter_learners=[learner],
     model_inputs_to_streams=input_map,
     callbacks=[progress_writer, test_config])

-------------------------------------------------------------------
average  since  average  since  examples
loss     last   metric   last
------------------------------------------------------
Learning rate per minibatch: 0.2
142      142      0.922   0.922    64
1.35e+06 1.51e+07 0.896   0.883    192
[………]

average  since  average  since  examples
loss      last  metric  last
------------------------------------------------------
Learning rate per minibatch: 0.005
0.4      0.4    0.4      0.4      19
0.4      0.4    0.4      0.4      59
0.452    0.495  0.452    0.495   129
[…]

array([[ 8081.7905],
[16597.693 ],
[13335.17 ],
...,
[11275.804 ],
[15621.697 ],
[16875.555 ]], dtype=float32)