DL之LiR&DNN&CNN：利用LiR、DNN、CNN算法对MNIST手写数字图片(csv)识别数据集实现(10)分类预测

输出结果

设计思路

核心代码

classifier = skflow.TensorFlowLinearClassifier(

   n_classes=10, learning_rate=0.01)

classifier.fit(X_train, y_train)

linear_y_predict = classifier.predict(X_test)

classifier = skflow.TensorFlowDNNClassifier(hidden_units=[200, 50, 10], n_classes = 10,

   learning_rate=0.01)

classifier.fit(X_train, y_train)

dnn_y_predict = classifier.predict(X_test)

classifier = skflow.TensorFlowEstimator(

   model_fn=conv_model, n_classes=10, steps=20000,

   learning_rate=0.001)

classifier.fit(X_train, y_train)

classifier.predict(X_test)