tensorflow.python.framework.errors_impl.UnknownError: 2 root error(s) found.

잘못 보고하다
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 SegNet/block1_conv2/Relu (defined at media/ac/ubuntu train/Semantic-Segmentation-main/train.py:337) ]]      [[confusion_matrix/assert_less_1/Assert/AssertGuard/pivot_f/_31/_77]]   (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 SegNet/block1_conv2/Relu (defined at media/ac/ubuntu train/Semantic-Segmentation-main/train.py:337) ]] 0 successful operations. 0 derived errors ignored. [Op:__inference_train_function_6169]
 
원인 분석: 메모리가 너무 작을 수도 있어요.
 
솔루션:
 

physical_devices = tf.config.experimental.list_physical_devices('GPU')
assert len(physical_devices) > 0, "Not enough GPU hardware devices available"
tf.config.experimental.set_memory_growth(physical_devices[0], True)



#  GPU 
from tensorflow.compat.v1 import ConfigProto
from tensorflow.compat.v1 import InteractiveSession
config = ConfigProto()
config.gpu_options.allow_growth = True
session = InteractiveSession(config=config)

위의 임의의 코드를 추가하면 해결할 수 있다