我正在尝试构建一个用于图像分类的GoogleNet Inception架构。我已经读取并保存了我的图像数据和标签，如下所示。
print(X_train.shape)(16016, 224, 224, 3)print(X_test.shape)(16016, 1, 163)print(y_train.shape)(14939, 224, 224, 3)print(y_test.shape)(14939, 1, 163)使用这些数据，我正在尝试训练我的分类器。以下是我的代码。
IMG_SIZE = 224input_image = Input(shape = (IMG_SIZE,IMG_SIZE,3))tower_1 = Conv2D(64,(1,1),padding='same', activation='relu') (input_image)tower_1 = Conv2D(64,(3,3), padding='same',activation='relu') (tower_1)tower_2 = Conv2D(64,(1,1), padding='same',activation='relu')(input_image)tower_2 = Conv2D(64,(5,5), padding='same', activation='relu')(tower_2)tower_3 = MaxPooling2D((3,3),strides=(1,1),padding='same')(input_image)tower_3 = Conv2D(64,(1,1), padding='same',activation='relu')(tower_3)output = keras.layers.concatenate([tower_1,tower_2,tower_3],axis=3)output = Flatten()(output)out = Dense(163, activation='softmax')(output)model = Model(inputs = input_image, outputs = out)print(model.summary())epochs = 30lrate = 0.01decay = lrate/epochssgd = SGD(lr=lrate, momentum=0.9, decay=decay, nesterov= False)model.compile(loss='categorical_crossentropy',optimizer=sgd, metrics=['accuracy'])history = model.fit(X_train,y_train,validation_data=(X_test,y_test), epochs=epochs, batch_size=32)from keras.models import model_from_jsonmodel_json = model.to_json()with open("model.json", "w") as json_file: json_file.write(model_json)model.save_weights(os.path.join(os.getcwd(),'model.h5'))scores = model.evaluate(X_test,y_test, verbose=0)print("Accuracy: %.2f%%" % (scores[1]*100))但每次我运行程序时，都会得到一个我不理解的ValueError。我已经尝试过'y_test= y_test.reshape(14939,IMG_SIZE,IMG_SIZE,3)'，但仍然得到相同的错误。
错误
Traceback (most recent call last): File "c:/Users/zeele/OneDrive/Desktop/googleNet_Architecture.py", line 149, in <module> history = model.fit(X_train,y_train,validation_data=(X_test,y_test), epochs=epochs, batch_size=32) File "C:\Users\zeele\Miniconda3\lib\site-packages\keras\engine\training.py", line 1405, in fit batch_size=batch_size) File "C:\Users\zeele\Miniconda3\lib\site-packages\keras\engine\training.py", line 1299, in _standardize_user_data exception_prefix='model target') File "C:\Users\zeele\Miniconda3\lib\site-packages\keras\engine\training.py", line 121, in _standardize_input_data str(array.shape))ValueError: Error when checking model target: expected dense_1 to have 2 dimensions, but got array with shape (14939, 224, 224, 3)请帮助我解决这个问题。
谢谢你。
回答：
可以肯定的是，你的数据形状不正确/不一致；因为
print(X_train.shape)(16016, 224, 224, 3)人们肯定会期望X_test.shape在性质上是相似的，唯一的区别在于样本数量，即类似于(NUM_TEST_SAMPLES, 224, 224, 3)的形式；但你报告的是：
print(X_test.shape)(16016, 1, 163)这看起来更像是你的标签的预期形状（即y_train.shape）。
还请注意，训练集和测试集的数据和标签的长度必须相同，这在这里再次不是情况：对于训练集和测试集，你报告了16,016个数据样本和只有14,939个标签。
我的猜测是，你在使用scikit-learn的train_test_split将数据分割成训练集和测试集时很可能犯了一个（足够常见的）错误（参见文档）：
# 错误的顺序:X_train, y_train, X_test, y_test = train_test_split(X, y, test_size=0.33, random_state=42)# 正确的顺序:X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)