TensorFlowDNNClassifier class is deprecated but replacement does not seem to work?

前端 未结 2 807
北恋
北恋 2021-01-15 10:30

Using the following with TF .9.0rc0 on 60,000 (train) and 26,000 (test) on or so records with 145 coded columns (1,0) trying to predict 1 or 0 for class identification..

2条回答
  •  独厮守ぢ
    2021-01-15 10:56

    I just had a similar issue @Ismael answer is correct. I just wanted to add to the information that now classifier.fit() has the steps parameter that this parameter behaves differently. It doesn't abort earlier. There is another parameter called max_steps. That behaves as the original steps parameter of TensorFlowDNNClassifier.

    In short just use the max_steps parameter on fit() like this:

    classifier = skflow.DNNClassifier(...)
    classifier.fit(X_train, y_train, max_steps=3000)
    

提交回复
热议问题