我无法让 FER 使用示例代码

Question

我想使用 FER 只是为了好玩和修补，但是在我安装它之后，我正在尝试运行示例代码，但我遇到了这个错误，请受过更多教育的人帮助我。

最新的 TensorFlow 版本， 视窗 10 专业版， Python 3.8.6 64位

https://github.com/justinshenk/fer

https://github.com/justinshenk/fer/blob/master/example.py

WARNING:tensorflow:From C:\Users\perlu\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\compat\v2_compat.py:96: disable_resource_variables (from tensorflow.python.ops.variable_scope) is deprecated and will be removed in a future version.
Instructions for updating:
non-resource variables are not supported in the long term
WARNING:tensorflow:From C:\Users\perlu\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\keras\engine\training_v1.py:2070: Model.state_updates (from tensorflow.python.keras.engine.training) is deprecated and will be removed in a future version.
Instructions for updating:
This property should not be used in TensorFlow 2.0, as updates are applied automatically.
23-10-2020:22:29:59,746 WARNING  [deprecation.py:317] From C:\Users\perlu\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\keras\engine\training_v1.py:2070: Model.state_updates (from tensorflow.python.keras.engine.training) is deprecated and will be removed in a future version.
Instructions for updating:
This property should not be used in TensorFlow 2.0, as updates are applied automatically.
Traceback (most recent call last):
  File "C:\Users\perlu\Desktop\benj.py", line 8, in <module>
    result = detector.detect_emotions(image)
  File "C:\Users\perlu\AppData\Roaming\Python\Python38\site-packages\fer\fer.py", line 236, in detect_emotions
    face_rectangles = self.find_faces(img, bgr=True)
  File "C:\Users\perlu\AppData\Roaming\Python\Python38\site-packages\fer\fer.py", line 194, in find_faces
    results = self._mtcnn.detect_faces(img)
  File "C:\Users\perlu\AppData\Roaming\Python\Python38\site-packages\mtcnn\mtcnn.py", line 302, in detect_faces
    result = stage(img, result[0], result[1])
  File "C:\Users\perlu\AppData\Roaming\Python\Python38\site-packages\mtcnn\mtcnn.py", line 342, in __stage1
    out = self._pnet.predict(img_y)
  File "C:\Users\perlu\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\keras\engine\training_v1.py", line 983, in predict
    return func.predict(
  File "C:\Users\perlu\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\keras\engine\training_arrays.py", line 708, in predict
    return predict_loop(
  File "C:\Users\perlu\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\keras\engine\training_arrays.py", line 386, in model_iteration
    batch_outs = f(ins_batch)
  File "C:\Users\perlu\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\keras\backend.py", line 3824, in __call__
    fetched = self._callable_fn(*array_vals,
  File "C:\Users\perlu\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\client\session.py", line 1470, in __call__
    ret = tf_session.TF_SessionRunCallable(self._session._session,
tensorflow.python.framework.errors_impl.UnknownError: 2 root error(s) found.
  (0) Unknown: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above.
     [[{{node conv2d/Conv2D}}]]
     [[conv2d_4/BiasAdd/_783]]
  (1) Unknown: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above.
     [[{{node conv2d/Conv2D}}]]
0 successful operations.
0 derived errors ignored.

Answer 1

您使用的是 Anaconda 还是 Miniconda？ 尝试在本地机器上安装 tensorflow + fer，不使用环境，它对我有用。