Python 验证模型时，Keras 中的verbose 有什么用？
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/47902295/
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
What is the use of verbose in Keras while validating the model?
提问by rakesh
I'm running the LSTM model for the first time. Here is my model:
我是第一次运行 LSTM 模型。这是我的模型：
opt = Adam(0.002)
inp = Input(...)
print(inp)
x = Embedding(....)(inp)
x = LSTM(...)(x)
x = BatchNormalization()(x)
pred = Dense(5,activation='softmax')(x)
model = Model(inp,pred)
model.compile(....)
idx = np.random.permutation(X_train.shape[0])
model.fit(X_train[idx], y_train[idx], nb_epoch=1, batch_size=128, verbose=1)
What is the use of verbose while training the model?
训练模型时verbose有什么用？
回答by Ankit
Check documentation for model.fit here.
在此处查看 model.fit 的文档。
By setting verbose 0, 1 or 2 you just say how do you want to 'see' the training progress for each epoch.
通过设置详细的 0、1 或 2，您只需说明您想如何“查看”每个时期的训练进度。
verbose=0will show you nothing (silent)
verbose=0什么都不给你看（沉默）
verbose=1will show you an animated progress bar like this:
verbose=1将向您显示一个动画进度条，如下所示：
verbose=2will just mention the number of epoch like this:
verbose=2只会提到这样的时代数：
回答by Ashok Kumar Jayaraman
verbose: Integer. 0, 1, or 2. Verbosity mode.
verbose: Integer. 0、1 或 2。详细模式。
Verbose=0 (silent)
详细=0（静音）
Verbose=1 (progress bar)
Verbose=1（进度条）
Train on 186219 samples, validate on 20691 samples
Epoch 1/2
186219/186219 [==============================] - 85s 455us/step - loss: 0.5815 - acc:
0.7728 - val_loss: 0.4917 - val_acc: 0.8029
Train on 186219 samples, validate on 20691 samples
Epoch 2/2
186219/186219 [==============================] - 84s 451us/step - loss: 0.4921 - acc:
0.8071 - val_loss: 0.4617 - val_acc: 0.8168
Verbose=2 (one line per epoch)
Verbose=2（每个纪元一行）
Train on 186219 samples, validate on 20691 samples
Epoch 1/1
- 88s - loss: 0.5746 - acc: 0.7753 - val_loss: 0.4816 - val_acc: 0.8075
Train on 186219 samples, validate on 20691 samples
Epoch 1/1
- 88s - loss: 0.4880 - acc: 0.8076 - val_loss: 0.5199 - val_acc: 0.8046
回答by Hugo Bevilacqua
For verbose> 0, fitmethod logs:
对于verbose> 0，fit方法日志：
- loss: value of loss function for your training data
- acc: accuracy value for your training data.
- loss: 训练数据的损失函数值
- acc：训练数据的准确度值。
Note: If regularization mechanisms are used, they are turned on to avoid overfitting.
注意：如果使用正则化机制，它们会被打开以避免过度拟合。
if validation_dataor validation_splitarguments are not empty, fitmethod logs:
如果validation_data或validation_split参数不为空，fit方法记录：
- val_loss: value of loss function for your validation data
- val_acc: accuracy value for your validation data
- val_loss：验证数据的损失函数值
- val_acc：验证数据的准确度值
Note: Regularization mechanisms are turned off at testing time because we are using all the capabilities of the network.
注意：正则化机制在测试时关闭，因为我们正在使用网络的所有功能。
For example, using verbosewhile training the model helps to detect overfitting which occurs if your acckeeps improving while your val_accgets worse.
例如，使用verbosewhile 训练模型有助于检测过度拟合，如果您acc不断改进而您val_acc变得更糟，则会发生过度拟合。
回答by Ashiq Imran
By default verbose = 1,
默认情况下详细 = 1，
verbose = 1, which includes both progress bar and one line per epoch
verbose = 1，其中包括进度条和每个 epoch 的一行
verbose = 0, means silent
verbose = 0，表示无声
verbose = 2, one line per epoch i.e. epoch no./total no. of epochs
详细 = 2，每个纪元一行，即纪元编号/总编号。时代的
