Hi! We've received your issue and please be patient to get responded. We will arrange technicians to answer your questions as soon as possible. Please make sure that you have posted enough message to demo your request. You may also check out the API,FAQ,Github Issue and AI community to get the answer.Have a nice day!
def getdata(): def reader(): for i in range(len(data_y)): yield np.array(data_X[i]).astype('float32'), np.array(data_y[i]- 3).astype('int64') return reader 这是在哪里改?
5条答案
按热度按时间6tr1vspr1#
您好,我们已经收到了您的问题,会安排技术人员尽快解答您的问题,请耐心等待。请您再次检查是否提供了清晰的问题描述、复现代码、环境&版本、报错信息等。同时,您也可以通过查看官网API文档、常见问题、历史Issue、AI社区来寻求解答。祝您生活愉快~
Hi! We've received your issue and please be patient to get responded. We will arrange technicians to answer your questions as soon as possible. Please make sure that you have posted enough message to demo your request. You may also check out the API,FAQ,Github Issue and AI community to get the answer.Have a nice day!
svmlkihl2#
要不先试一下paddle的python推理呢?先确认下是否为环境问题
332nm8kg3#
这个问题,https://github.com/PaddlePaddle/Paddle/issues/33171这个也是同样这个函数崩溃了,我觉得跟环境有关系,但是也是共性问题,应该还是库的问题。我就全新的一台机器,在我本机上编译好的C++推理,下载的官方的预测库,gpu的推理,放过去,就崩溃,cuda10.1,cuda10.0,cuda10.2都试过,都不行,又另外换了一台机器,依然是这个崩溃。应该是库的问题。
niknxzdl4#
应该是内存访问导致的问题,是库的问题,您看看,百度一下,导出都是这个问题:
0x00007FFA0CAB62D1 (paddle_inference.dll)处(位于 xxx.exe 中)引发的异常: 0xC0000005: 读取位置 0x0000000000000000 时发生访问冲突。
https://www.cnblogs.com/dzqiu/p/9518190.html
https://blog.csdn.net/PaddlePaddle/article/details/86739880
PaddlePaddle运行时出现EnforceNotMet: Enforce failed错误:
问题解决
PaddlePaddle的label要从0开始递增。
def getdata():
def reader():
for i in range(len(data_y)):
yield np.array(data_X[i]).astype('float32'), np.array(data_y[i]- 3).astype('int64')
return reader
这是在哪里改?
blpfk2vs5#
麻烦帮忙解决一下,很着急。现场部署,没法用。