Python 如何使用keras获得模型的准确性？
声明：本页面是StackOverFlow热门问题的中英对照翻译，遵循CC BY-SA 4.0协议，如果您需要使用它，必须同样遵循CC BY-SA许可，注明原文地址和作者信息，同时你必须将它归于原作者（不是我）：StackOverFlow
原文地址: http://stackoverflow.com/questions/51047676/
Warning: these are provided under cc-by-sa 4.0 license. You are free to use/share it, But you must attribute it to the original authors (not me):
StackOverFlow
How to get accuracy of model using keras?
提问by ZelelB
After fitting the model (which was running for a couple of hours), I wanted to get the accuracy with the following code:
拟合模型（运行了几个小时）后，我想使用以下代码获得准确性：
train_loss=hist.history['loss']
val_loss=hist.history['val_loss']
train_acc=hist.history['acc']
val_acc=hist.history['val_acc']
xc=range(nb_epoch)
of the trained model, but was getting an error, which is caused by the deprecated methods I was using.
经过训练的模型，但出现错误，这是由我使用的弃用方法引起的。
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
<ipython-input-233-081ed5e89aa4> in <module>()
3 train_loss=hist.history['loss']
4 val_loss=hist.history['val_loss']
----> 5 train_acc=hist.history['acc']
6 val_acc=hist.history['val_acc']
7 xc=range(nb_epoch)
KeyError: 'acc'
The code I used to fit the model before trying to read the accuracy, is the following:
在尝试读取准确性之前，我用来拟合模型的代码如下：
hist = model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch,
verbose=1, validation_data=(X_test, Y_test))
hist = model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch,
verbose=1, validation_split=0.2)
Which produces this output when running it:
运行它时会产生此输出：
Epoch 1/20
237/237 [==============================] - 104s 440ms/step - loss: 6.2802 - val_loss: 2.4209
.....
.....
.....
Epoch 19/20
189/189 [==============================] - 91s 480ms/step - loss: 0.0590 - val_loss: 0.2193
Epoch 20/20
189/189 [==============================] - 85s 451ms/step - loss: 0.0201 - val_loss: 0.2312
I've noticed that I was running deprecated methods & arguments.
我注意到我正在运行不推荐使用的方法和参数。
So how can I read the accuracy and val_accuracy without having to fit again, and waiting for a couple of hours again? I tried to replace train_acc=hist.history['acc']with train_acc=hist.history['accuracy']but it didn't help.
那么我如何才能读取准确度和 val_accuracy 而不必再次拟合，并再次等待几个小时？我试图用替换train_acc=hist.history['acc']，train_acc=hist.history['accuracy']但它没有帮助。
回答by Daniel M?ller
You probably didn't add "acc" as a metric when compiling the model.
编译模型时，您可能没有添加“acc”作为度量。
model.compile(optimizer=..., loss=..., metrics=['accuracy',...])
You can get the metrics and loss from any data without training again with:
您无需再次训练即可从任何数据中获取指标和损失：
model.evaluate(X, Y)
回答by user1906450
add a metrics = ['accuracy'] when you compile the model
simply get the accuracy of the last epoch . hist.history.get('acc')[-1]
what i would do actually is use a GridSearchCV and then get the best_score_ parameter to print the best metrics
编译模型时添加一个 metrics = ['accuracy']
只需获得最后一个时代的准确性。hist.history.get('acc')[-1]
我实际上会做的是使用 GridSearchCV 然后获取 best_score_ 参数来打印最佳指标
回答by Daniel B.
Just tried it in tensorflow==2.0.0. With the following result:
刚刚试了一下tensorflow==2.0.0。结果如下：
Given a training call like:
给定一个培训电话，如：
history = model.fit(train_data, train_labels, epochs=100,
validation_data=(test_images, test_labels))
The final accuracy for the above call can be read out as follows:
上述调用的最终精度可以读出如下：
history.history['accuracy']
Printing the entire dict history.historygives you overview of all the contained values.
You will find that all the values reported in a line such as:
打印整个 dict 可以history.history让您概览所有包含的值。您会发现在一行中报告了所有值，例如：
7570/7570 [==============================] - 42s 6ms/sample - loss: 1.1612 - accuracy: 0.5715 - val_loss: 0.5541 - val_accuracy: 0.8300
can be read out from that dict.
可以从那个字典中读出。
For the sake of completeness, I created the model as follows:
为了完整起见，我创建了如下模型：
model.compile(optimizer=tf.optimizers.Adam(learning_rate=0.0001,
beta_1=0.9,
beta_2=0.999,
epsilon=1e-07,
amsgrad=False,
name='Adam'
),
loss='sparse_categorical_crossentropy',
metrics=['accuracy']
