Tiansheng Wen

> > Hi, I cannot understand the expression "recon_loss = -(preds * bows).sum(1)“ in etm.py forward() function. Could you help me explain it? The loss function seems to be different...

> 细节上说的有一点小小的错误 - 若field_dim = [5,10,5], np.cumsum(field_dims)[:-1]=[5,15], 所以源码中 补了一个零 np.array((**0**, *np.cumsum(field_dims)[:-1])

> @LangdonYu how should I modify it specifically, I did not find torch.Dataset() in 721 in the denoising_diffusion_pytorch.py file. Thanks! Did you solve this problem?

> @Flu0XeT1n want to try 1.8.9 and see if it works now? I tried 1.8.9. The original problem is solved but a new one occurs. 

Have you solved the problem? Can you fill me in?