由于一些原因，视频录制要告一段落了。再写一篇关于cntk的文章分享出来吧。我也很想将这个事情进行下去。以后如果条件允许还会接着做。

cntk2.0框架生成的模型才可以支持python。1.0不支持。

python可以导入cntk.exe生成的框架，也可以导入python调用cntk生成的框架。举两个例子：

1 、导入cntk.exe生成的框架。

from cntk.ops.functions import load_modelfrom PIL import Image import numpy as npfrom sklearn.utils import shufflenp.random.seed(0)def generate(N, mean, cov, diff): #import ipdb;ipdb.set_trace() samples_per_class = int(N/2) X0 = np.random.multivariate_normal(mean, cov, samples_per_class) Y0 = np.zeros(samples_per_class) for ci, d in enumerate(diff): X1 = np.random.multivariate_normal(mean+d, cov, samples_per_class) Y1 = (ci+1)*np.ones(samples_per_class) X0 = np.concatenate((X0,X1)) Y0 = np.concatenate((Y0,Y1)) X, Y = shuffle(X0, Y0) return X,Ymean = np.random.randn(2)cov = np.eye(2) features, labels = generate(6, mean, cov, [[3.0], [3.0, 0.0]])features= features.astype(np.float32) labels= labels.astype(np.int) print(features)print(labels)z = load_model("MC.dnn")print(z.parameters[0].value)print(z.parameters[0])print(z)print(z.uid)#print(z.signature)#print(z.layers[0].E.shape)#print(z.layers[2].b.value)for index in range(len(z.inputs)): print("Index {} for input: {}.".format(index, z.inputs[index]))for index in range(len(z.outputs)): print("Index {} for output: {}.".format(index, z.outputs[index].name))import cntk as ctz_out = ct.combine([z.outputs[2].owner])predictions = np.squeeze(z_out.eval({z_out.arguments[0]:[features]}))ret = list()for t in predictions: ret.append(np.argmax(t))top_class = np.argmax(predictions)print(ret)print("predictions{}.top_class{}".format(predictions,top_class))

上述的代码生成一个.py文件。放到3分类例子中，跟模型一个文件夹下（需要预先用cntk.exe生成模型）。CNTK-2.0.beta15.0\CNTK-2.0.beta15.0\Tutorials\HelloWorld-LogisticRegression\Models

2 、python生成模型和使用自己的模型：

代码如下：

# -*- coding: utf-8 -*-"""Created on Mon Apr 10 04:59:27 2017@author: Administrator"""from __future__ import print_functionimport matplotlib.pyplot as plt import numpy as np from matplotlib.colors import colorConverter, ListedColormap from cntk.learners import sgd, learning_rate_schedule, UnitType #old in learnerfrom cntk.ops.functions import load_modelfrom cntk.ops import * #softmaxfrom cntk.io import CTFDeserializer, MinibatchSource, StreamDef, StreamDefsfrom cntk import * from cntk.layers import Dense, Sequentialfrom cntk.logging import ProgressPrinterdef generate_random_data(sample_size, feature_dim, num_classes): # Create synthetic data using NumPy. Y = np.random.randint(size=(sample_size, 1), low=0, high=num_classes) # Make sure that the data is separable X = (np.random.randn(sample_size, feature_dim) + 3) * (Y + 1) X = X.astype(np.float32) # converting class 0 into the vector "1 0 0", # class 1 into vector "0 1 0", ... class_ind = [Y == class_number for class_number in range(num_classes)] Y = np.asarray(np.hstack(class_ind), dtype=np.float32) return X, Y# Read a CTF formatted text (as mentioned above) using the CTF deserializer from a filedef create_reader(path, is_training, input_dim, num_label_classes): return MinibatchSource(CTFDeserializer(path, StreamDefs( labels = StreamDef(field='labels', shape=num_label_classes, is_sparse=False), features = StreamDef(field='features', shape=input_dim, is_sparse=False) )), randomize = is_training, epoch_size = INFINITELY_REPEAT if is_training else FULL_DATA_SWEEP) def ffnet(): inputs = 2 outputs = 2 layers = 2 hidden_dimension = 50 # input variables denoting the features and label data features = input((inputs), np.float32) label = input((outputs), np.float32) # Instantiate the feedforward classification model my_model = Sequential ([ Dense(hidden_dimension, activation=sigmoid,name='d1'), Dense(outputs)]) z = my_model(features) ce = cross_entropy_with_softmax(z, label) pe = classification_error(z, label) # Instantiate the trainer object to drive the model training lr_per_minibatch = learning_rate_schedule(0.125, UnitType.minibatch) # Initialize the parameters for the reader input_dim=2 num_output_classes=2 num_samples_per_sweep = 6000 # Get minibatches of training data and perform model training minibatch_size = 25 num_minibatches_to_train = 1024 num_sweeps_to_train_with = 2#10 num_minibatches_to_train = (num_samples_per_sweep * num_sweeps_to_train_with) / minibatch_size # progress_printer = ProgressPrinter(0) progress_printer = ProgressPrinter(tag='Training',num_epochs=num_sweeps_to_train_with) trainer = Trainer(z, (ce, pe), [sgd(z.parameters, lr=lr_per_minibatch)], [progress_printer]) #trainer = Trainer(z, (ce, pe), [sgd(z.parameters, lr=lr_per_minibatch)]) train_file = "Train2-noLiner_cntk_text.txt" # Create the reader to training data set reader_train = create_reader(train_file, True, input_dim, num_output_classes) # Map the data streams to the input and labels. input_map = { label : reader_train.streams.labels, features : reader_train.streams.features } print(reader_train.streams.keys()) aggregate_loss = 0.0 #for i in range(num_minibatches_to_train): for i in range(0, int(num_minibatches_to_train)): #train_features, labels = generate_random_data(minibatch_size, inputs, outputs) # Specify the mapping of input variables in the model to actual minibatch data to be trained with #trainer.train_minibatch({features : train_features, label : labels}) # Read a mini batch from the training data file data = reader_train.next_minibatch(minibatch_size, input_map = input_map) trainer.train_minibatch(data) sample_count = trainer.previous_minibatch_sample_count aggregate_loss += trainer.previous_minibatch_loss_average * sample_count # last_avg_error = aggregate_loss / trainer.total_number_of_samples_seen trainer.summarize_training_progress() z.save_model("myfirstmod.dnn") print(z) print(z.parameters) print(z.d1) print(z.d1.signature) print(z.d1.root_function) print(z.d1.placeholders) print(z.d1.parameters) print(z.d1.op_name) print(z.d1.type) print(z.d1.output) print(z.outputs) test_features, test_labels = generate_random_data(minibatch_size, inputs, outputs) avg_error = trainer.test_minibatch({features : test_features, label : test_labels}) print(' error rate on an unseen minibatch: {}'.format(avg_error)) return last_avg_error, avg_errornp.random.seed(98052)ffnet()print("-------------分割-----------------")inputs = 2outputs = 2minibatch_size = 5features = input((inputs), np.float32)label = input((outputs), np.float32)test_features, test_labels = generate_random_data(minibatch_size, inputs, outputs) print('fea={}'.format(test_features))z = load_model("myfirstmod.dnn")ce = cross_entropy_with_softmax(z, label)pe = classification_error(z, label)lr_per_minibatch = learning_rate_schedule(0.125, UnitType.minibatch)progress_printer = ProgressPrinter(0)trainer = Trainer(z, (ce, pe), [sgd(z.parameters, lr=lr_per_minibatch)], [progress_printer])avg_error = trainer.test_minibatch({z.arguments[0] : test_features, label : test_labels})print(' error rate on an unseen minibatch: {}'.format(avg_error)) result1 = z.eval({z.arguments[0] : test_features}) #print("r={} ".format(result1)) out = softmax(z)result = out.eval({z.arguments[0] : test_features}) print(result)print("Label :", [np.argmax(label) for label in test_labels])print("Predicted :", [np.argmax(label) for label in result])#print("Predicted:", [np.argmax(result[i,:,:]) for i in range(result.shape[0])])type1_x=[]type1_y=[]type2_x=[]type2_y=[]for i in range(len(test_labels)):#for i in range(6): if np.argmax(test_labels[i]) == 0: type1_x.append( test_features[i][0] ) type1_y.append( test_features[i][1] ) if np.argmax(test_labels[i]) == 1: type2_x.append( test_features[i][0] ) type2_y.append( test_features[i][1] ) type1 = plt.scatter(type1_x, type1_y,s=40, c='red',marker='+' ) type2 = plt.scatter(type2_x, type2_y, s=40, c='green',marker='+') nb_of_xs = 100xs1 = np.linspace(2, 8, num=nb_of_xs)xs2 = np.linspace(2, 8, num=nb_of_xs)xx, yy = np.meshgrid(xs1, xs2) # create the gridfeatureLine = np.vstack((np.array(xx).reshape(1,nb_of_xs*nb_of_xs),np.array(yy).reshape(1,yy.size)))print(featureLine.T)r = out.eval({z.arguments[0] : featureLine.T})print(r)# Initialize and fill the classification planeclassification_plane = np.zeros((nb_of_xs, nb_of_xs))for i in range(nb_of_xs): for j in range(nb_of_xs): #classification_plane[i,j] = nn_predict(xx[i,j], yy[i,j]) #r = out.eval({z.arguments[0] : [xx[i,j], yy[i,j]]}) classification_plane[i,j] = np.argmax(r[i*nb_of_xs+j] )print(classification_plane)# Create a color map to show the classification colors of each grid pointcmap = ListedColormap([ colorConverter.to_rgba('r', alpha=0.30), colorConverter.to_rgba('b', alpha=0.30)])# Plot the classification plane with decision boundary and input samplesplt.contourf(xx, yy, classification_plane, cmap=cmap)plt.xlabel('x1') plt.ylabel('x2') #axes.legend((type1, type2,type3), ('0', '1','2'),loc=1) plt.show()

代码内容：

1先生成模型。并打印出模型里面的参数

2调用模型，测试下模型错误率

3调用模型，输出结果

4将数据可视化

输出：dict_keys([‘features', ‘labels'])

Finished Epoch[1 of 2]: [Training] loss = 0.485836 * 12000, metric = 20.36% * 12000 0.377s (31830.2 samples/s);

Composite(Dense): Input(‘Input456', [#], [2]) -> Output(‘Block577_Output_0', [#], [2])

(Parameter(‘W', [], [50 x 2]), Parameter(‘b', [], [2]), Parameter(‘W', [], [2 x 50]), Parameter(‘b', [], [50]))

Dense: Input(‘Input456', [#], [2]) -> Output(‘d1', [#], [50])

(Input(‘Input456', [#], [2]),)

Dense: Input(‘Input456', [#], [2]) -> Output(‘d1', [#], [50])

()

(Parameter(‘W', [], [2 x 50]), Parameter(‘b', [], [50]))

Dense

Tensor[50]

Output(‘d1', [#], [50])

(Output(‘Block577_Output_0', [#], [2]),)

error rate on an unseen minibatch: 0.6

————-分割—————–

fea=[[ 2.74521399 3.6318233 ]

[ 3.45750308 3.8683207 ]

[ 3.49858737 4.31363964]

[ 9.01324368 1.75216711]

[ 9.15447521 7.21175623]]

average since average since examples

loss last metric last

error rate on an unseen minibatch: 0.2

[[ 0.57505184 0.42494816]

[ 0.70583773 0.29416227]

[ 0.67773896 0.32226101]

[ 0.04568771 0.95431226]

[ 0.95059013 0.04940984]]

Label : [0, 0, 0, 1, 1]

Predicted : [0, 0, 0, 1, 0]

[[ 2. 2. ]

[ 2.06060606 2. ]

[ 2.12121212 2. ]

…,

[ 7.87878788 8. ]

[ 7.93939394 8. ]

[ 8. 8. ]]

Train2-noLiner_cntk_text 部分数据：

|features 1.480778 -1.265981 |labels 1 0

|features -0.592276 3.097171 |labels 0 1

|features 4.654565 1.054850 |labels 0 1

|features 6.124534 0.265861 |labels 0 1

|features 6.529863 1.347884 |labels 0 1

|features 2.330881 4.995633 |labels 0 1

|features 1.690045 0.171233 |labels 1 0

|features 2.101682 3.911253 |labels 0 1

|features 1.907487 0.201574 |labels 1 0

|features 5.141490 1.246433 |labels 0 1

|features 0.696826 0.481824 |labels 1 0

|features 3.305343 4.792150 |labels 1 0

|features 3.496849 -0.408635 |labels 1 0

|features 3.911750 0.205660 |labels 0 1

|features 5.154604 0.453434 |labels 0 1

|features 4.084166 2.718320 |labels 0 1

|features 5.544332 1.617196 |labels 0 1

|features -0.050979 0.466522 |labels 1 0

|features 5.168221 4.647089 |labels 1 0

|features 3.051973 0.864701 |labels 1 0

|features 5.989367 4.118536 |labels 1 0

|features 1.251041 -0.505563 |labels 1 0

|features 3.528092 0.319297 |labels 0 1

|features 6.907406 6.122889 |labels 1 0

|features 2.168320 0.546091 |labels 1 0

以上这篇用python生成与调用cntk模型代码演示方法就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持。