ValueError：层“顺序”的输入 0 与层不兼容：预期形状=（无，32,32,3），找到形状=（32,32,3）

Question

我在另一个代码中制作了一个模型，我想使用图像对其进行预测。

import numpy as np
from keras.preprocessing.image import img_to_array, load_img
from tensorflow import keras

model = keras.models.load_model('Faces/model/alexnet')
# load the image
img = load_img('Faces/text.jpg', target_size=(32, 32))

# prepare the image
x = img_to_array(img)
# perform prediction
preds = model.predict(x)
print('Predicted:', preds)

我在期望 shape=(None, 32, 32, 3) 的地方收到错误，但发现了一个相似但缺少 None 参数的形状，shape=(32, 32, 3)。 对我来说， load_img()似乎没有加载正确的形状。 我可以应用哪些解决方案？

Traceback (most recent call last):
File "d:\Projects\Experiment\findresult.py", line 12, in <module>
preds = model.predict(x)
File "C:\Users\USER\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\keras\utils\traceback_utils.py", line 67, in error_handler   
raise e.with_traceback(filtered_tb) from None
File "C:\Users\USER\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\tensorflow\python\framework\func_graph.py", line 1129, in autograph_handler
raise e.ag_error_metadata.to_exception(e)
ValueError: in user code:

File "C:\Users\USER\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\keras\engine\training.py", line 1621, in predict_function  
*
return step_function(self, iterator)
File "C:\Users\USER\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\keras\engine\training.py", line 1611, in step_function  ** 
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "C:\Users\USER\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\keras\engine\training.py", line 1604, in run_step  **      
outputs = model.predict_step(data)
File "C:\Users\USER\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\keras\engine\training.py", line 1572, in predict_step      
return self(x, training=False)
File "C:\Users\USER\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\keras\utils\traceback_utils.py", line 67, in error_handler 
raise e.with_traceback(filtered_tb) from None
File "C:\Users\USER\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\keras\engine\input_spec.py", line 263, in assert_input_compatibility
raise ValueError(f'Input {input_index} of layer "{layer_name}" is '

ValueError: Input 0 of layer "sequential" is incompatible with the layer: expected shape=(None, 32, 32, 3), found shape=(32, 32, 3)

我尝试将target_size=(32,32)更改为target_size=(224,244)并相应地调整模型。 但是报错改成expected shape=(None, 224, 224, 3), found shape=(32, 224, 3) 。

Answer 1

在代码x = img_to_array(img)之后添加代码

x=np.expand_dims(x, axis=0)