bigmoyan
bigmoyan
Pre-trained is of course very attractive. But I'm wondering if you could also upload the training script for reproduction? thks.
RT，没有安装CUDA的机器，设置USE_CUDA=OFF, BUILD_ALL_EXAMPLES = OFF，因为仍然还是会编example，编译时报找不到头文件错误，具体： ``` In file included from /root/installs/libdeepvac/examples/src/test_resnet_benchmark.cpp:11: /usr/libtorch/include/c10/cuda/CUDAStream.h:6:10: fatal error: cuda_runtime_api.h: No such file or directory #include ``` 似应根据BUILD_ALL_EXAMPLES 和USE_CUDA的状态决定要build哪些examples？
各位亲爱的keras用户以及keras-cn用户，大家好！ 为了丰富大家的交流，我们现在准备把github issues利用起来~各位可以在这里： - 问问题 - 为keras和keras-cn讨论PR - 求debug - 论文阅读与讨论 - 论文合作 - 竞赛交流 - 找工作 - 找朋友 - 吹水 当然，尽量聊技术~ 发布帖子打好标签，方便大家寻找，格式为 【标签】标题 建议： 1. 尽量为自己的帖子打上标签，页面右侧有“label”选项，方便大家寻找 2. 求debug类的帖子请附上出错代码与traceback 3....
Hi erhwenkuo. I was deeply surprised when finding your repo.... No offense, but I don't see any necessity of your repo. Some researchers/engineers/learners feel difficulty in reading English docs and...
Hi. I wanna know why there is no "label" input in "siamese network" ? And how you input the label data?
It's really confusing when I realized that the offered pretrained models only produce bottleneck feature and users need to fit their own regressor to evaluate. Which makes it's a necessity...