Why the error message ?

[jhaiWang]

terminate called after throwing an instance of 'std::bad_alloc'
what(): std::bad_alloc

[yizt]

@jhaiWang 您好，不清楚您遇到的错误；能否详细描述一下？谢谢！

[jhaiWang]

大概是因为内存的原因，我把config里面的IMAGE_PER_GPU=2修改成16，就会出现上面的错误，把这个值调低一点就可以 ------------------ 原始邮件 ------------------ 发件人: "mick.yi"<notifications@github.com>; 发送时间: 2019年4月23日(星期二) 中午1:57 收件人: "embracesource-cv-com/keras-east"<keras-east@noreply.github.com>; 抄送: "北纬51°~~华丽的伪装"<240349215@qq.com>; "Mention"<mention@noreply.github.com>; 主题: Re: [embracesource-cv-com/keras-east] Why the error message ? (#2) @jhaiWang 您好，不清楚您遇到的错误；能否详细描述一下？谢谢！ — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or mute the thread.

[bharatsubedi]

after run evaluate.py I faced this issue. can you tell me how to solve?

[yizt]

@bharatsubedi 感谢您的反馈，这是bug,已经修复

[jhaiWang]

您好： 我想问一下您这个实验跑数据的时候，用的是什么数据库，跑了多久呢？我的5000张图片，跑一次Epoch就要一天的时间了，这个有点太慢了

…

------------------ 原始邮件 ------------------ 发件人: "mick.yi"<notifications@github.com>; 发送时间: 2019年4月23日(星期二) 中午1:57 收件人: "embracesource-cv-com/keras-east"<keras-east@noreply.github.com>; 抄送: "北纬51°~~华丽的伪装"<240349215@qq.com>; "Mention"<mention@noreply.github.com>; 主题: Re: [embracesource-cv-com/keras-east] Why the error message ? (#2) @jhaiWang 您好，不清楚您遇到的错误；能否详细描述一下？谢谢！ — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or mute the thread.

[yizt]

@jhaiWang ICDAR2015 训练集，1000张图像，1个epochs 平均155秒

[jhaiWang]

那这个差距还有点大啊，我现在自己的数据集，5000张图片，而且只标注了一个位置，GPU是1070ti，现在跑一个epoch要几个小时，这差距有点大，1000张数据是不是有点少？

…

------------------ 原始邮件 ------------------ 发件人: "mick.yi"<notifications@github.com>; 发送时间: 2019年4月28日(星期天) 上午9:34 收件人: "embracesource-cv-com/keras-east"<keras-east@noreply.github.com>; 抄送: "北纬51°~~华丽的伪装"<240349215@qq.com>; "Mention"<mention@noreply.github.com>; 主题: Re: [embracesource-cv-com/keras-east] Why the error message ? (#2) @jhaiWang ICDAR2015 训练集，1000张图像，1个epochs 平均155秒 — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or mute the thread.

[WJinhai]

make: Entering directory '/media/image/新加卷/kaggle/keras-east-master/lanms'
g++ -o adaptor.so -I include -std=c++11 -O3 -I/root/anaconda3/envs/keras/include/python3.6m -L/home/image/anaconda3/envs/tensorflow/lib/python3.5/config-3.5m -L/home/image/anaconda3/envs/tensorflow/lib -lpython3.5m -lpthread -ldl -lutil -lrt -lm -Xlinker -export-dynamic adaptor.cpp include/clipper/clipper.cpp --shared -fPIC
In file included from include/pybind11/pytypes.h:12:0,
from include/pybind11/cast.h:13,
from include/pybind11/attr.h:13,
from include/pybind11/pybind11.h:43,
from adaptor.cpp:1:
include/pybind11/common.h:100:20: fatal error: Python.h: No such file or directory
#include <Python.h>
^
compilation terminated.
make: *** [adaptor.so] Error 1
Traceback (most recent call last):
File "/media/image/新加卷/kaggle/keras-east-master/evaluate.py", line 20, in
import lanms
File "/media/image/新加卷/kaggle/keras-east-master/lanms/init.py", line 8, in
raise RuntimeError('Cannot compile lanms: {}'.format(BASE_DIR))
RuntimeError: Cannot compile lanms: /media/image/新加卷/kaggle/keras-east-master/lanms

用了最新的代码compile出现问题