美文网首页
绘制模型训练收敛曲线

绘制模型训练收敛曲线

作者: _龙雀 | 来源:发表于2019-06-12 17:58 被阅读0次
    • 定义模型
    from tensorflow.python.keras.models import Model, Sequential
    model = Model()
    model_trained = model.fit()
    
    • 绘图
    %matplotlib inline   #jupyter notebook 中显示
    import matplotlib
    matplotlib.use('ggplot') #绘图风格设置
    import matplotlib.pyplot as plt
    
    # Plot accuracy
    plt.subplot(211)
    plt.plot(model_trained.history['acc'])
    plt.plot(model_trained.history['val_acc'])
    plt.title('Model Accuracy')
    plt.ylabel('Accuracy')
    plt.xlabel('Epoch')
    plt.legend(['Train', 'Validation'], loc='upper left')
    
    # Plot loss
    plt.subplot(212)
    plt.plot(model_trained.history['loss'])
    plt.plot(model_trained.history['val_loss'])
    plt.title('Model Loss')
    plt.ylabel('Loss')
    plt.xlabel('Epoch')
    plt.legend(['Train', 'Validation'], loc='upper right')
    
    plt.show()
    
    plt.tight_layout(h_pad=1.0)
    plt.savefig('./output/history-graph.png')
    
    print(str(model_trained.history['val_acc'][-1])[:6] +
          "(max: " + str(max(model_trained.history['val_acc']))[:6] + ")")
    print("Done.")
    

    相关文章

      网友评论

          本文标题:绘制模型训练收敛曲线

          本文链接:https://www.haomeiwen.com/subject/lphrfctx.html