Chenyi Wang comments

Results 25 comments of


                                            Chenyi Wang

do u do some ablation experments on ur modules

could u please share the names of paper compare about it pls thx ------------------ Original ------------------ From: AngeLouCN ***@***.***> Date: Fri,May 27,2022 10:49 AM To: AngeLouCN/CaraNet ***@***.***> Cc: q671383789 ***@***.***>,...

fps

RTX2060 5.6fps with demo

fps

> test on the GTX1070 7fps did not reach 40fps Are there alse parameters that need to be modified Have u solved the fps problem?

onnx转engine，make时出错

同错哪里能找到第一个版本的代码吗

About the hard anchor samping

I met the problem, and It's because ur decoder have already upsample the predictions, like after the encoder maybe the feature_map's h w is 16X16 , so the embed is...

Multiple GPUs training on very large scale dataset

@Haroldzha Hi, is there any method to aviod this, I'm meeting the same situation now. What if do not using prefetcher, I'm not sure pytorch dataloader will do prefetch automatically...

Trying to backward through the graph a second time, but the buffers have already been freed. Specify retain_graph=True when calling backward the first time.

Yeah, u should use detach , because your gridient will be freed the first time you use kl and backward

Chenyi Wang

do u do some ablation experments on ur modules

fps

fps

onnx转engine，make时出错

About the hard anchor samping

Multiple GPUs training on very large scale dataset

Trying to backward through the graph a second time, but the buffers have already been freed. Specify retain_graph=True when calling backward the first time.

HELP： Error(s) in loading state_dict for ResnetGenerator:

view control does not work on the latest vesrion, had to downgrage it to 0.16.0

Solve specific GPU problem.