深度学习tensorflow运行报错问题

Question

2021-06-29 18:40:56.887930: I tensorflow/compiler/jit/xla_cpu_device.cc:41] Not creating XLA devices, tf_xla_enable_xla_devices not set
2021-06-29 18:40:56.912075: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2021-06-29 18:40:56.980304: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:196] None of the MLIR optimization passes are enabled (registered 0 passes)
2021-06-29 18:40:58.935123: W tensorflow/core/framework/cpu_allocator_impl.cc:80] Allocation of 78643200 exceeds 10% of free system memory.
2021-06-29 18:41:01.752603: W tensorflow/core/framework/cpu_allocator_impl.cc:80] Allocation of 78643200 exceeds 10% of free system memory.

Answer 1

这是由于内存不足，不足以保存模型导致的。可以根据自己的情况对下面的进行修改：
1.把batchsize改小一些
2.把placeholder位置放在卷积之前，
3.把测试集改为批次放入预测