使用 keras api 导出的 .pb 模型进行预测

Question

我使用 keras api（使用 tensorflow 2.0）创建并保存了一个模型：

import pandas as pd
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import *

training_data_df = pd.read_csv("03\sales_data_training_scaled.csv")

X = training_data_df.drop('total_earnings', axis=1).values
Y = training_data_df[['total_earnings']].values

# Define the model
model = Sequential()
model.add(Dense(50, input_dim=9, activation='relu'))
model.add(Dense(100, activation='relu'))
model.add(Dense(50, activation='relu'))
model.add(Dense(1, activation='linear'))
model.compile(loss='mean_squared_error', optimizer='adam')

# Train the model
model.fit(
    X,
    Y,
    epochs=50,
    shuffle=True,
    verbose=2
)

# Load the separate test data set
test_data_df = pd.read_csv("03\sales_data_test_scaled.csv")

X_test = test_data_df.drop('total_earnings', axis=1).values
Y_test = test_data_df[['total_earnings']].values

test_error_rate = model.evaluate(X_test, Y_test, verbose=0)
print("The mean squared error (MSE) for the test data set is: {}".format(test_error_rate))

# Save the model to disk
model.save("04/model/trained_model")
print("Model saved to disk.")

以 .pb 格式保存模型。我知道我可以使用以下方法加载模型：

import tensorflow as tf

graph = tf.Graph() 
graph_def = tf.GraphDef()
graph_def.ParseFromString(pb_file.read()) 
with graph.as_default():
  tf.import_graph_def(graph_def)

但我对如何在加载模型后进行预测感到困惑？ 我偶然发现了this，它在预测之前讨论了模型的输入和输出部分的名称。 我的问题是，当我使用 Keras api 创建模型时，如何找到这些名称然后预测模型？

这是来自链接的预测代码：

# These names are part of the model and cannot be changed.
output_layer = 'loss:0'
input_node = 'Placeholder:0'

with tf.compat.v1.Session() as sess:
    try:
        prob_tensor = sess.graph.get_tensor_by_name(output_layer)
        predictions = sess.run(prob_tensor, {input_node: [augmented_image] })
    except KeyError:
        print ("Couldn't find classification output layer: " + output_layer + ".")
        print ("Verify this a model exported from an Object Detection project.")
        exit(-1)

Answer 1

#Save the model 
model.save('saved_model/my_model')
#Load the model 
import tensorflow as tf
new_model = tf.keras.models.load_model('saved_model/my_model')

# Check its architecture
new_model.summary()
#Predict model
new_model.predict(input)