请提出你的问题 Please ask your question
完整报错:
PreconditionNotMetError: Tensor's dimension is out of bound.Tensor's dimension must be equal or less than the size of its memory.But received Tensor's dimension is 7741440, memory's size is 7004160.
[Hint: Expected numel() * SizeOf(dtype()) <= memory_size(), but received numel() * SizeOf(dtype()):7741440 > memory_size():7004160.] (at /paddle/paddle/phi/core/dense_tensor_impl.cc:55)
[operator < fused_conv2d > error]
2条答案
按热度按时间w9apscun1#
您好,麻烦补充下飞桨版本号,复现代码;
fgw7neuy2#
另外,请教下为什么会有这种诉求,是想提升推理服务并发度吗,部署多个服务,启多个进程是不是更合适。两个线程运行同一份数据和模型,如果没做好线程间同步和互斥机制,问题会比较大,而且并没有真正高并发。