我修改了这里找到的代码。但在我的输入中出现了维度错误，如下所示：
ValueError: 检查输入时出错：期望 InputLayer 有 4 个维度，但得到的数组形状为 (None, None)
这是我修改后的代码（我在 Colab 上运行）：
#Power data classification/regression with CNNimport numpy as npimport tensorflow as tffrom tensorflow import kerasimport pandas as pdimport csv as csvimport keras.backend as Kfrom sklearn.preprocessing import MinMaxScaler # For normalizing dataprint("TensorFlow version:",tf.__version__)!wget https://raw.githubusercontent.com/sibyjackgrove/CNN-on-Wind-Power-Data/master/MISO_power_data_classification_labels.csv!wget https://raw.githubusercontent.com/sibyjackgrove/CNN-on-Wind-Power-Data/master/MISO_power_data_input.csv#Read total rows in csv file without loading into memorydef data_set_size(csv_file): with open(csv_file) as csvfile: csv_rows = 0 for _ in csvfile: csv_rows += 1 return csv_rows-1 #Remove header from count and returncsv_file = "./MISO_power_data_classification_labels.csv"n_train = data_set_size(csv_file)print("Training data set size:",n_train)#Python generator to supply batches of traning data during training with loading full data set to memorydef power_data_generator(batch_size,gen_type=''): valid_size = max(1,np.int(0.2*batch_size)) while 1: df_input=pd.read_csv('./MISO_power_data_input.csv',usecols =['Wind_MWh','Actual_Load_MWh'],chunksize =24*(batch_size+valid_size), iterator=True) df_target=pd.read_csv('./MISO_power_data_classification_labels.csv',usecols =['Mean Wind Power','Standard Deviation','WindShare'],chunksize =batch_size+valid_size, iterator=True) for chunk, chunk2 in zip(df_input,df_target): scaler = MinMaxScaler() # Define limits for normalize data InputX = chunk.values InputX = scaler.fit_transform(InputX) # Normalize input data InputY = chunk2.values InputY = scaler.fit_transform(InputY) # Normalize output data if gen_type =='training': yield (InputX[0:batch_size],InputY[0:batch_size]) elif gen_type =='validation': yield (InputX[batch_size:batch_size+valid_size],InputY[batch_size:batch_size+valid_size])#Define model using KerasYclasses = 3 #Number of output classesdef nossa_metrica(y_true, y_pred): diff = y_true - y_pred count = K.sum(K.cast(K.equal(diff, K.zeros_like(diff)), 'int8')) # Count how many times y_true = y_pred return count/n_trainmodel = keras.Sequential([ tf.keras.layers.Input(shape=(2,24,1),name='InputLayer'), tf.keras.layers.Conv2D(filters=4,kernel_size=(2,6),strides=(1,1),activation='relu',name='ConvLayer1'), tf.keras.layers.Conv2D(filters=4,kernel_size=(1,6),strides=(1,1),activation='relu',name='ConvLayer2'), tf.keras.layers.Flatten(name="Flatten"), tf.keras.layers.Dense(units = 8,activation='relu',name='FeedForward1'), tf.keras.layers.Dense(units = Yclasses,name='OutputLayer'),])model.compile(loss='mse',optimizer='adam',verbose = 2,metrics = [nossa_metrica])model.summary()samples_per_batch = 5train_generator= power_data_generator(batch_size=samples_per_batch,gen_type='training')valid_generator= power_data_generator(batch_size=samples_per_batch,gen_type='validation')number_of_batches = np.int32(n_train/(samples_per_batch+max(1,np.int32(0.2*samples_per_batch)))) #Training startshistory = model.fit(train_generator, steps_per_epoch= number_of_batches,epochs=200,validation_data=valid_generator, validation_steps=number_of_batches,verbose=2)如果有人能在这里提供一些帮助，我将非常感激！
回答：
在
tf.keras.layers.Input(shape=(2,24,1),name='InputLayer')你指定了模型的输入，即传递给 model.fit 的第一个参数应该具有形状 (?, 2, 24, 1)，但你传递的并不是这样。实际上，next(train_generator) 产生以下输出：
(array([[0.62840991, 0.36867201], [0.68026787, 0.32275764], [0.67140497, 0.30866827], [0.61158515, 0.32725069], [0.57037451, 0.41795902]]), array([[0.0301671 , 1. , 0.00581285], [0. , 0.18781352, 0. ], [0.12077826, 0.3356642 , 0.19676627], [0.56275038, 0.8747475 , 0.69121483], [1. , 0. , 1. ]]))这是一个形状分别为 (5, 2) 和 (5, 3) 的数组元组。
在你参考的笔记本中，他们通过
InputX = np.resize(InputX,(batch_size+valid_size,24,2,1))明确设置了所需形状的输入，但这部分代码不在你的代码中。
