python tensorflow踩坑记录

问题

model.fit错误

输入shape检查过，是对的

Traceback (most recent call last):
  File "main.py", line 136, in <module>
    results = model.predict(testImageSet, verbose=1)
  File ".../lib/python3.8/site-packages/keras/utils/traceback_utils.py", line 70, in error_handler
    raise e.with_traceback(filtered_tb) from None
  File "/home/luosj/.local/lib/python3.8/site-packages/keras/engine/input_spec.py", line 216, in assert_input_compatibility
    raise ValueError(
ValueError: Layer "model" expects 1 input(s), but it received 38 input tensors. Inputs received: [<tf.Tensor: shape=(32, 256, 50), dtype=float32, numpy=
array([[[0.        , 0.43137255, 0.29411766, ..., 0.29803923,
         0.29411766, 0.29803923],
        [0.        , 0.43137255, 0.29411766, ..., 0.29803923,
         0.29411766, 0.29803923],
...

解决

输入不能为list，改为numpy.array

参考

python - ValueError: Layer sequential expects 1 inputs, but it received 211 input tensors in tensorflow 2.0 - Stack Overflow