如何在keras中的卷积神经网络中设置批量大小

Question

我正在尝试在线训练神经网络。我想在卷积神经网络上使用Tensorflow Keras在批处理函数上训练。这是：

look_back=1600
inputTensor = keras.layers.Input([look_back+3,2])
inputTensorReshaped = tf.reshape(inputTensor, [1, look_back + 3, 2, 1])
#split into 2 groups
inputgroup1 = keras.layers.Lambda(lambda x: x[:, :3], output_shape=((1, 3, 2, 1)))(inputTensorReshaped)
inputgroup2 = keras.layers.Lambda(lambda x: x[:, 3:look_back + 3], output_shape=((1, look_back,2, 1)))(inputTensorReshaped)

conv1 = keras.layers.Conv2D(filters=1024, kernel_size=(10, 2), activation='relu')(inputgroup2)#10
pool1 = keras.layers.MaxPooling2D(pool_size=(2, 1))(conv1)
dropout1 = keras.layers.Dropout(rate=0.1)(pool1)
norm1 = keras.layers.LayerNormalization()(dropout1)

conv2 = keras.layers.Conv2D(filters=512, kernel_size=(8, 1), activation='relu')(norm1)
pool2 = keras.layers.MaxPooling2D(pool_size=(2, 1))(conv2)
dropout2 = keras.layers.Dropout(rate=0.1)(pool2)
norm2 = keras.layers.LayerNormalization()(dropout2)

conv3 = keras.layers.Conv2D(filters=256, kernel_size=(6, 1), activation='relu')(norm2)
pool3 = keras.layers.MaxPooling2D(pool_size=(2, 1))(conv3)
dropout3 = keras.layers.Dropout(rate=0.1)(pool3)
norm3 = keras.layers.LayerNormalization()(dropout3)

conv4 = keras.layers.Conv2D(filters=128, kernel_size=(4, 1), activation='relu')(norm3)
pool4 = keras.layers.MaxPooling2D(pool_size=(2, 1))(conv4)
dropout4 = keras.layers.Dropout(rate=0.1)(pool4)
norm4 = keras.layers.LayerNormalization()(dropout4)

conv5 = keras.layers.Conv2D(filters=64, kernel_size=(2, 1), activation='relu')(norm4)
pool5 = keras.layers.MaxPooling2D(pool_size=(2, 1))(conv5)
dropout5 = keras.layers.Dropout(rate=0.1)(pool5)
norm5 = keras.layers.LayerNormalization()(dropout5)
flatten1 = keras.layers.Flatten()(norm5)
dense1 = keras.layers.Dense(32, activation='relu')(flatten1)

misclayer1 = keras.layers.Dense(32, activation='relu')(inputgroup1)
miscdropout1 = keras.layers.Dropout(rate=0.1)(misclayer1)
miscnorm1 = keras.layers.LayerNormalization()(miscdropout1)

misclayer2 = keras.layers.Dense(128, activation='relu')(miscnorm1)
miscdropout2 = keras.layers.Dropout(rate=0.1)(misclayer2)
miscnorm2 = keras.layers.LayerNormalization()(miscdropout2)

misclayer3 = keras.layers.Dense(32, activation='relu')(miscnorm2)
miscdropout3 = keras.layers.Dropout(rate=0.1)(misclayer3)
miscnorm3 = keras.layers.LayerNormalization()(miscdropout3)
miscflatten1 = keras.layers.Flatten()(miscnorm3)
misclayer4 = keras.layers.Dense(32, activation='relu')(miscflatten1)

rejoinlayer = keras.layers.Concatenate()([dense1, misclayer4])

processing1 = keras.layers.Dense(64, activation='relu')(rejoinlayer)
totalnorm1 = keras.layers.LayerNormalization()(processing1)
processing2 = keras.layers.Dense(32, activation='relu')(totalnorm1)
totaldropout1 = keras.layers.Dropout(rate=0.2)(processing2)
processing3 = keras.layers.Dense(16, activation='relu')(totaldropout1)
totalnorm2 = keras.layers.LayerNormalization()(processing3)
processing4 = keras.layers.Dense(8, activation='relu')(totalnorm2)
totaldropout2 = keras.layers.Dropout(rate=0.2)(processing4)
processing5 = keras.layers.Dense(4, activation='relu')(totaldropout2)

output = keras.layers.Dense(1, activation='linear')(processing5)

model = keras.Model(inputTensor,output)

model.compile(optimizer=keras.optimizers.SGD(learning_rate=0.00005, momentum=0.1, nesterov=True), loss="mean_squared_error")

#trains the model with the 1st state, action, and value
def train():
    global qtable
    x = []
    y = []
    for i in range(0, 8):
        state = qtable.loc[qtable.index[i], "state"]
        action = [qtable.loc[qtable.index[i], "action"], qtable.loc[qtable.index[0], "action"]]
        x.append([action])
        x[i].extend(state)
        y.append([qtable.loc[qtable.index[i], "value"]])

    print("training...loss:")
    with tf.device('/gpu:0'):
        print(model.train_on_batch(np.nan_to_num(np.array(x)), np.nan_to_num(np.array(y))))

在这种情况下，变量“state”将是一个1202×2的列表[[a，b]，[c，d]，[e，f]，…]，变量“action”在被追加/扩展到x之前将是一个1×2的列表[a，b]。理论上，我想要的训练是8个批量，输入形状为1203×2。但是，我得到了这个错误： ValueError:无法将包含19248个元素的张量重塑为“{node model/tf.reformate/reformate}}=reformate[T=DT_FLOAT，Tshape=DT_INT32]（IteratorGetNext，model/tf.reformate/reformate/shape）]的[11203,2,1]（2406个元素），并将输入张量计算为部分形状：input[1]=[11203,2,1]

这表明所有的输入和输出都同时被输入到CNN中，这不是我想要的。相反，我希望数据以8个为一批。我该怎么做？？？我是否正确使用了“批量培训”

Answer 1

batch_size:: Integer or None. Number of samples per batch of computation. If unspecified, batch_size will default to 32. Do not specify the batch_size if your data is in the form of a dataset, generators, or keras.utils.Sequence instances (since they generate batches).

查找具有批量大小的以下示例

num_classes = 5

model = Sequential([
  layers.experimental.preprocessing.Rescaling(1./255, input_shape=(img_height, img_width, 3)),
  layers.Conv2D(16, 3, padding='same', activation='relu'),
  layers.MaxPooling2D(),
  layers.Conv2D(32, 3, padding='same', activation='relu'),
  layers.MaxPooling2D(),
  layers.Conv2D(64, 3, padding='same', activation='relu'),
  layers.MaxPooling2D(),
  layers.Flatten(),
  layers.Dense(128, activation='relu'),
  layers.Dense(num_classes)
])

model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

history = model.fit(
  train_ds,
  validation_data=val_ds,
  batch_size = 32
  epochs=10
)