sunanlin comments

Results 10 comments of


                                            sunanlin

converting trained model doesn't work, while the pretrained model works..?(coreML)

do you finish it ?

converting trained model doesn't work, while the pretrained model works..?(coreML)

thanks friend,can you tell me how use turicreate to transform h5 to mlmodel?

converting trained model doesn't work, while the pretrained model works..?(coreML)

> > do you finish it ? > > No, I used turicreate instead. hey!friend, i know how to solve your problem,because your .h5 model only save_weights, there is no...

converting trained model doesn't work, while the pretrained model works..?(coreML)

i have converted h5 to mlmodel,your are right,this code produced final_h5 is save_weights, i do following step: 1. i converted final_h5 to darknet's weights and cfg, refered to https://github.com/caimingxie/h5_to_weight_yolo3. 2....

Can this library be used in mm detection? How to use？

Hi, @pprp ,CWD is a good example, and it would be perfect if there was a general tutorial on how to implement mmdet and mmseg in MMRazor.

the questions in resprune.py

我刚刚也遇到了这个问题，现在明白了，感谢你们的讨论

gpu运行出错，大神解答一下

很可能是GPU显存占满了，可以试试调小batch

error in main.cpp

> > I met the same error, did you solve it ? > > Yes I have solved it > My cmakelist is error 是用-DCMAKE。。。传入Torch的路径吗

Couldn't open shared file mapping. 训练可以跑起来，但是训练到某个epoch后就会报错？

你可以在train_one_iter()中释放每一次反向传播后的变量，源代码中没有释放

data.txt中class_id开始序号

从0开始，修改了数据载入形式，其他的要求跟YOLO系列一致