keras中不同批量大小的训练模型

Question

我想针对不同的批量大小训练我的模型，即：[64, 128] 我正在用下面的 for 循环来做

   epoch=2 
   batch_sizes = [128,256] 
   for i in range(len(batch_sizes)):
     history = model.fit(x_train, y_train, batch_sizes[i], epochs=epochs, 
          callbacks=[early_stopping, chk], validation_data=(x_test, y_test))

对于以上代码，我的模型产生以下结果：

    Epoch 1/2
    311/311 [==============================] - 157s 494ms/step - loss: 0.2318 - 
    f1: 0.0723 
    Epoch 2/2
    311/311 [==============================] - 152s 488ms/step - loss: 0.1402 - 
    f1: 0.4360 

    Epoch 1/2
    156/156 [==============================] - 137s 877ms/step - loss: 0.1197 - 
    f1: **0.5450** 
    Epoch 2/2
    156/156 [==============================] - 136s 871ms/step - loss: 0.1132 - 
    f1: 0.5756

看起来模型在完成批量大小 64 的训练后继续训练，即我想从头开始为下一批训练我的模型，请指导我如何做。 p.s：我尝试过的：

   epoch=2 
   batch_sizes = [128,256] 
   for i in range(len(batch_sizes)):
     history = model.fit(x_train, y_train, batch_sizes[i], epochs=epochs, 
          callbacks=[early_stopping, chk], validation_data=(x_test, y_test))
   keras.backend.clear_session()

也没用

Answer 1

您可以编写一个函数来定义模型，并且您需要在随后的 fit 调用之前调用它。如果您的模型包含在 model 中，则权重会在训练期间更新，并在 fit 调用后保持不变。这就是您需要重新定义模型的原因。这可以帮助你

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
import numpy as np

X = np.random.rand(1000,5)
Y = np.random.rand(1000,1)

def build_model():
    model = Sequential()
    model.add(Dense(64,input_shape=(X.shape[1],)))
    model.add(Dense(Y.shape[1]))
    model.compile(loss='mse',optimizer='Adam')
    return model

epoch=2
batch_sizes = [128,256]
for i in range(len(batch_sizes)):
    model = build_model()
    history = model.fit(X, Y, batch_sizes[i], epochs=epoch, verbose=2)
    model.save('Model_' + str(batch_sizes[i]) + '.h5')

然后，输出如下：

Epoch 1/2
8/8 - 0s - loss: 0.3164
Epoch 2/2
8/8 - 0s - loss: 0.1367
Epoch 1/2
4/4 - 0s - loss: 0.7221
Epoch 2/2
4/4 - 0s - loss: 0.4787

keras中不同批量大小的训练模型

training model for different batch sizes in keras

python

loops

model-fitting

keras