Jianwei Yang

Hi, Peter, I checked the evaluation code again. The mean AP is computed by averaging over all 1600 entries in app, that is: ``` print('Mean AP = {:.4f}'.format(np.mean(aps))) ``` and...

Hi, @peteanderson80 , thanks a lot for your replying, and sharing the log file. Yeah, it is very weird to me. I compared the 5000 validation images, they are the...

@fxia22 , Hi, Fei, thanks a lot for sharing this code. I compared with Pytorch official STN and your implementation, and found the gradients are different when the number of...

@fxia22 One more point, when channel > 1, the gradients of the first channel are the same, the other channels are different.

I found the problem, it is not about the cuda code, it on my own code. never mind.

@GuohongLi Hi, I did not try that, what's your idea?

Use pytorch 1.0.0 instead. > On May 7, 2019, at 10:11 PM, Bingoren wrote: > > Wait Online! > > — > You are receiving this because you are subscribed...

@world4jason thanks for reminding. I think that is because the data is deleted from our sever. I will upload a new one to google driver.

Hi, @tackgeun , glad to know you have successfully get the results as the paper! Regarding the conditional image generation, ## [Encoder architecture] - Use same architecture with a discriminator....

Hi, @tackgeun With your help, my code starts to generate an image. But reconstructed images are blurry compared to the paper. But I'm confusing that the encoder architecture and the...