一个小型的手卷式深度学习模型库
LensFlare的Python项目详细描述
镜头角度
lensflare是我为帮助自己和其他人更好地理解神经网络而创建的一个示例包。很多代码都是基于我在Coursera deeplearning.ai course
中所做的工作工作流程示例如下：
importtensorflowastffromlensflare.classificationimportTfNNClassifierfromlensflare.utilimportload_moons_dataset
X_train,y_train=load_moons_dataset()
tf.reset_default_graph()# layer_dims contains neural network structure parameterslayers_dims=[X_train.shape[0],200,80,10,1]clf=TfNNClassifier(layers_dims=layers_dims,optimizer="adam",lambd=.05,keep_prob=0.7,num_epochs=5000)clf.fit(X_train,y_train,seed=3)y_pred_train=clf.transform(X_train,y_train)
Cost after epoch 0: 1.036825
Cost after epoch 1000: 0.108737
Cost after epoch 2000: 0.104837
Cost after epoch 3000: 0.106805
Cost after epoch 4000: 0.105311
INFO:tensorflow:Restoring parameters from results/model
Training Accuracy: 0.983333333333
fromlensflare.funcs.tf_funcsimportplot_decision_boundary,predict_dec# Plot decision boundarypredictions,X,dropout_var,sess=predict_dec()model=lambdaX_train:sess.run([predictions],feed_dict={X:X_train,dropout_var:1.0});plot_decision_boundary(model,X_train,y_train)sess.close()
INFO:tensorflow:Restoring parameters from results/model
欢迎加入QQ群-->： 979659372
