神经网络运行 CNN 报错

运行CNN报错：

Failed to get convolution algorithm. This is probably because cuDNN failed to initialize

原因：GPU显存占满

处理方法：限制显存占用率即可

import keras

config = tf.compat.v1.ConfigProto(allow_soft_placement=True)

config.gpu_options.per_process_gpu_memory_fraction = 0.5

tf.compat.v1.keras.backend.set_session(tf.compat.v1.Session(config=config))

//禁用GPU

# import os

# os.environ[‘CUDA_VISIBLE_DEVICES’] = ‘/gpu:0’