主页 / 问题 / 1566465
Accepted
Mixadyt
Asked:2024-02-15 22:39:08 +0800 CST2024-02-15 22:39:08 +0800 CST

我提交了 720x1280x3 的图像，模型接受 Nonex1280x3 Keras

  • 772

我的型号：

self.model = Sequential()
        self.model.add(Lambda(lambda x: print(x.shape)))
        self.model.add(InputLayer(input_shape=(720, 1280, 3)))
        self.model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))
        self.model.add(Conv2D(64, (3, 3), activation='relu', padding='same', strides=2))
        self.model.add(Conv2D(128, (3, 3), activation='relu', padding='same'))
        self.model.add(Conv2D(128, (3, 3), activation='relu', padding='same', strides=2))
        self.model.add(Conv2D(256, (3, 3), activation='relu', padding='same'))
        self.model.add(Conv2D(256, (3, 3), activation='relu', padding='same', strides=2))
        self.model.add(Conv2D(512, (3, 3), activation='relu', padding='same'))
        self.model.add(Conv2D(256, (3, 3), activation='relu', padding='same'))
        self.model.add(Conv2D(128, (3, 3), activation='relu', padding='same'))
        self.model.add(UpSampling2D((2, 2)))
        self.model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))
        self.model.add(UpSampling2D((2, 2)))
        self.model.add(Conv2D(32, (3, 3), activation='relu', padding='same'))
        self.model.add(Conv2D(2, (3, 3), activation='sigmoid', padding='same'))
        self.model.add(UpSampling2D((2, 2)))

        self.model.compile(optimizer="adam", loss="mse")

我在一开始就添加了Lambda来获取输入维度。这就是我的预测方式：

print(image.shape)
self.model.predict(image)

一开始运行程序后我得到：

(720, 1280, 3)
(None, 1280, 3)
(None, 1280, 3)

然后是错误：

Traceback (most recent call last):
  File "C:\Users\Амаль\PreviuMaker\resizer\main.py", line 12, in <module>
    print(resizer.predict(image))
  File "C:\Users\Амаль\PreviuMaker\resizer\Model.py", line 32, in predict
    return self.model.predict(image)
  File "C:\Users\Амаль\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\keras\src\utils\traceback_utils.py", line 70, in error_handler
    raise e.with_traceback(filtered_tb) from None
  File "C:\Users\5C61~1\AppData\Local\Temp\__autograph_generated_fileo1wmzcyg.py", line 15, in tf__predict_function
    retval_ = ag__.converted_call(ag__.ld(step_function), (ag__.ld(self), ag__.ld(iterator)), None, fscope)
TypeError: in user code:

    File "C:\Users\Амаль\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\keras\src\engine\training.py", line 2416, in predict_function  *
        return step_function(self, iterator)
    File "C:\Users\Амаль\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\keras\src\engine\training.py", line 2401, in step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    File "C:\Users\Амаль\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\keras\src\engine\training.py", line 2389, in run_step  **
        outputs = model.predict_step(data)
    File "C:\Users\Амаль\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\keras\src\engine\training.py", line 2357, in predict_step
        return self(x, training=False)
    File "C:\Users\Амаль\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\keras\src\utils\traceback_utils.py", line 70, in error_handler
        raise e.with_traceback(filtered_tb) from None
    File "C:\Users\Амаль\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\keras\src\engine\input_spec.py", line 213, in assert_input_compatibility
        raise TypeError(

    TypeError: Exception encountered when calling layer 'sequential' (type Sequential).

    Inputs to a layer should be tensors. Got 'None' (of type <class 'NoneType'>) as input for layer 'conv2d'.

    Call arguments received by layer 'sequential' (type Sequential):
      • inputs=tf.Tensor(shape=(None, 1280, 3), dtype=float32)
      • training=False
      • mask=None

你能告诉我可能是什么问题吗？

python

1 个回答

  1. Best Answer

    print不返回任何内容，即 None有人可能会说，回报。该层Lambda用于转换数据。事实证明，在这一层的输出中，您得到了None. 快速修复可能如下所示：

    self.model.add(Lambda(lambda x: print(x.shape) or x))
                                               ^^^^ возвращаем в итоге x

    但总的来说，可能有Keras一个更适合输出调试信息的层。

    PS 你可以这样查看第一层的输入：

    print(model.get_layer(index=0).input)
    • 0

相关问题