首次使用CNN预测Lab颜色值遇输入形状不兼容错误求助

报错信息 #

2023-05-30 16:57:03.347650: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
Traceback (most recent call last):
  File "C:\Users\Desktop\src\main.py", line 57, in <module>
    main()
  File "C:\Users\Desktop\src\main.py", line 31, in main
    models.train.main(model='cnn', color='gray', type='sig', vis=False, explain=False,
  File "C:\Users\Desktop\src\models\train.py", line 571, in main
    train_cv(df, model, color, type, vis, explain, store_train, store_val, store_cv_model)
  File "C:\Users\Desktop\src\models\train.py", line 314, in train_cv
    model.fit(X_train, y_train)
  File "C:\Users\Anaconda3\envs\lib\site-packages\keras\utils\traceback_utils.py", line 70, in error_handler
    raise e.with_traceback(filtered_tb) from None
  File "C:\Users\AppData\Local\Temp\__autograph_generated_file2mx7mlql.py", line 15, in tf__train_function
    retval_ = ag__.converted_call(ag__.ld(step_function), (ag__.ld(self), ag__.ld(iterator)), None, fscope)
ValueError: in user code:

    File "C:\Users\Anaconda3\envs\lib\site-packages\keras\engine\training.py", line 1249, in train_function  *
        return step_function(self, iterator)
    File "C:\Users\Anaconda3\envs\lib\site-packages\keras\engine\training.py", line 1233, in step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    File "C:\Users\Anaconda3\envs\lib\site-packages\keras\engine\training.py", line 1222, in run_step  **
        outputs = model.train_step(data)
    File "C:\Users\Anaconda3\envs\lib\site-packages\keras\engine\training.py", line 1023, in train_step
        y_pred = self(x, training=True)
    File "C:\Users\Anaconda3\envs\lib\site-packages\keras\utils\traceback_utils.py", line 70, in error_handler
        raise e.with_traceback(filtered_tb) from None
    File "C:\Users\Anaconda3\envs\lib\site-packages\keras\engine\input_spec.py", line 295, in assert_input_compatibility
        raise ValueError(

    ValueError: Input 0 of layer "sequential" is incompatible with the layer: expected shape=(None, 30, 30, 3), found shape=(None, 26)

模型代码 #

elif algorithm == 'cnn':

        model = Sequential()

        model.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=(30,30,3)))
        model.add(MaxPooling2D(pool_size=(2, 2)))
        model.add(Conv2D(64, kernel_size=(3, 3), activation='relu'))
        model.add(MaxPooling2D(pool_size=(2, 2)))
        model.add(Flatten())
        model.add(Dense(128, activation='relu'))
        model.add(Dense(3))
        model.compile(optimizer='adam', loss='mean_squared_error')

错误原因 #

核心问题是模型输入形状与实际训练数据形状不匹配：

• 定义的CNN模型要求输入是(None, 30, 30, 3)的4维张量，对应批量的30×30像素3通道彩色图像；
• 实际传入的X_train是(None,26)的2维张量，即每个样本是26个特征的一维向量，两者完全不兼容，导致模型无法处理输入。

另外调用训练时传入了color='gray'参数，可能数据加载逻辑并未生成灰度图像的二维张量，而是输出了一维特征，进一步加剧了形状不匹配问题。

解决方法 #

根据实际数据类型，选择以下方案：

方案1：输入确实是图像数据（30×30的彩色/灰度图） #

1. 修正数据预处理：确保X_train被转换为对应形状的4维张量：
   • 彩色图：形状应为(样本数, 30, 30, 3)；
   • 灰度图：修改模型的input_shape为(30,30,1)，同时将X_train处理为(样本数,30,30,1)的形状，或者把单通道数据重复3次模拟3通道输入。
2. 检查数据加载逻辑：确认color='gray'参数是否正确触发了灰度图像的加载与张量转换，而非输出一维特征。

方案2：输入实际是26维一维特征（非图像） #

CNN专为二维/三维网格数据（如图像）设计，这种场景更适合用全连接神经网络（MLP），替换模型代码如下：

elif algorithm == 'cnn':  # 可改名为'mlp'，保持调用逻辑兼容
        model = Sequential()
        model.add(Dense(128, activation='relu', input_shape=(26,)))
        model.add(Dense(64, activation='relu'))
        model.add(Dense(3))
        model.compile(optimizer='adam', loss='mean_squared_error')

如果坚持要用CNN，需要将26维特征重塑为(样本数,26,1,1)的形状，同时修改模型input_shape=(26,1,1)，但这种做法无法发挥CNN的优势，不推荐。

内容的提问来源于stack exchange，提问作者Torsten Buchert