Tensorflow出口估算器进行预测 [英] Tensorflow export estimators for prediction

问题描述

我想知道如何导出估算器，然后从MNIST教程

I wonder how can I export the estimator and then import it for prediction from MNIST tutorial, Tensorflow's page. Thank you!

推荐答案

Estimator具有model_dir args，将在其中保存模型.因此，在预测期间，我们使用Estimator并调用predict方法，该方法将重新创建图形并加载检查点.

The Estimator has model_dir args where the model will be saved. So during prediction we use the Estimator and call the predict method which recreates the graph and the checkpoints are loaded.

对于MNIST示例，预测代码为:

For the MNIST example, the prediction code would be:

tf.reset_default_graph()

# An input-function to predict the class of new data.
predict_input_fn = tf.estimator.inputs.numpy_input_fn(
    x={"x": eval_data},
    num_epochs=1,
    shuffle=False)

mnist_classifier = tf.estimator.Estimator(
      model_fn=cnn_model_fn, model_dir="/tmp/mnist_convnet_model")

#Prediction call
predictions = mnist_classifier.predict(input_fn=predict_input_fn)

pred_class = np.array([p['classes'] for p in predictions]).squeeze()
print(pred_class)

# Output
# [7 2 1 ... 4 5 6]

这篇关于Tensorflow出口估算器进行预测的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！