Guanghui Ren(任广辉)

icon indicating a website link https://scholar.google.com/citations?user=oqN1dA8AAAAJ icon indicating an email [email protected]

icon company CoLab@BUAA icon location Beijing,China icon location CoLab@BUAA; University of Chinese Academy of Sciences; Xi'an Jiao Tong University

Results 6 issues of Guanghui Ren(任广辉)

Fix parse bug

7 comment

https://github.com/microsoft/MMdnn/issues/882

Compatible with python2

rename some funcs to make the code clearer

refine the calculation of relation for speed

tail-stream does not notice that a file(nfs mount) has been changed

Thanks for your great work. The problem is just as the title said.

Some questions about the trainable parameters?

Thanks for your great code! `self.centered_gradient_kernels = self.get_centered_gradient_kernel().train(False)` When I remove the 'train(False)', I found that the paramters of get_centered_gradient_kernel cannot be trained and it retains unchanged.I guess that maybe...