Johnson yue

run on python3.7 tested

 Did you have same problem？？

Hi, your Discriminator Design is unique . So , I want to know this Discriminator architure about output is num_classes channel format what is meaning ? and why do you...

Require a ReadMe

2

Hello， think for your share，and I want to use ssd on Windows with VS2013. Then I saw this repo but I don`t know how to build caffe.lib and libcaffe.lib ....

Can you remove the dependency on the mmcv library? Because mmcv often changes a lot, is very unstable and not backwards compatible, and has very strict environmental requirements. It is...

this performance is from L1loss ？

1

hi， thank your share the code. I have an question about loss did you analysis loss importance for w & w/o L1 loss ? the result is for blur ,...

how to use implement text2speech？

5

Hi， thanks for your sharing , I can test it for Text-to-Music. and I want to test Text-to-Speech How to write prompt to do it ??? Can you tell a...

How does it work？

4

Hi， unsky: thank you for sharing your code , and I want to know is the *Focal Loss* work well?? How much improve than before?

Hi, I saw your code in "sample_compression.py", did you do compression?? where is the compression function ? 3Q

looking forward to pytorch version code

2

hi， thanks for your good work， but tf is not good for debug and modified if someone have pytorch version ，plz！ 3Q