The kernel appears to have died. It will restart automatically.

参考：https://github.com/tensorflow/tensorflow/issues/9829

出现这个错误的原因有很多，我这里只分享我遇到的这个错误原因。

 

在Jupyter中运行如下代码，报 kernel died 的错误。

# 加载模型
new_model = load_model('./saved_models/my_model.h5')

def test_reprocess(img_path):
    img = cv2.imread(img_path)
    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
    img = np.expand_dims(img, axis=0)
    img = np.array(img)
    img = (1.0 * img) / 255

    return img

img = test_reprocess('239.jpg')
print(new_model.predict(img))

 

原因是我运行了另一个python程序，使用tensorflow进行训练，占用了GPU的所有显存。

在这个程序中，上面代码的最后一行又想调用GPU，但是没有显存，所以就报错。

将另一个程序在jupyter中关闭（shutdown）就可以了。

 

同样的tensorflow显存的问题，在终端中执行python文件，报错如下：

tensorflow.python.framework.errors_impl.InternalError: Failed to create session.

raceback (most recent call last):
  File "/home/ejior/working/demo/test.py", line 12, in <module>
    new_model = load_model('/home/ejior/working/demo/saved_models/my_model.h5')
  File "/home/ejior/anaconda3/envs/tf/lib/python3.6/site-packages/keras/engine/saving.py", line 419, in load_model
    model = _deserialize_model(f, custom_objects, compile)
  File "/home/ejior/anaconda3/envs/tf/lib/python3.6/site-packages/keras/engine/saving.py", line 287, in _deserialize_model
    K.batch_set_value(weight_value_tuples)
  File "/home/ejior/anaconda3/envs/tf/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 2470, in batch_set_value
    get_session().run(assign_ops, feed_dict=feed_dict)
  File "/home/ejior/anaconda3/envs/tf/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 186, in get_session
    _SESSION = tf.Session(config=config)
  File "/home/ejior/anaconda3/envs/tf/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1563, in __init__
    super(Session, self).__init__(target, graph, config=config)
  File "/home/ejior/anaconda3/envs/tf/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 633, in __init__
    self._session = tf_session.TF_NewSession(self._graph._c_graph, opts)
tensorflow.python.framework.errors_impl.InternalError: Failed to create session.

 

可以在通过命令 nvidia-smi 查看显存使用情况：

(tf) ejior@ejior-XPS-8930:~$ nvidia-smi
Tue Jan 15 12:02:41 2019       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 415.25       Driver Version: 415.25       CUDA Version: 10.0     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  GeForce RTX 208...  Off  | 00000000:01:00.0  On |                  N/A |
| 18%   42C    P2    70W / 250W |  10737MiB / 10986MiB |     33%      Default |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |
|=============================================================================|
|    0      1046      G   /usr/lib/xorg/Xorg                           250MiB |
|    0     16027      C   ...e/ejior/anaconda3/envs/tf/bin/python3.6 10475MiB |
+-----------------------------------------------------------------------------+

对占用显存的进程kill掉就可以了。