Johnson yue

how to reconstructions input image like Fig.8 in paper?

2

Hi, thanks your code , the paper is said that diffusion model can not reverse the image so , how to reconstruction input image like Fig8 in paper ??

Would you release the code of Demostration ？

1

I have a trained model ，I want test this model like your **Demostration**， But， it seems no code here

Failed writing body (0 != 16384)

1

你好，谢谢你的分享， 我可以按照Usage 运行并生成语音文件。 但是当我尝试运行web api 的时候，返回的结果有问题，我对web不了解，不知道怎么解决 Client：  Server：  可以看得出来，server那边已经生成完了，但是返回可能有点问题吧

Compiler Boost error

2

Hello，I run ‘build_v140.cmd’ in windows10，and occur an error`Performing configuration checks - 32-bit : yes (cached) - arm : no (cached) - mips1 : no (cached) - power : no (cached)...

how to apply on new datasets

1

Hi，if I have a new dataset with source domain x and target domain y ， how I train the model like creativity/portrait-to-photo as your paper said， it should be train...

RuntimeError: data array has wrong number of channels

2

Hi, Thank you for your share.When I reproduce ,I have some trouble .It confuse me much time.Please help me. Error log: Extracting X relu1_1 From Y conv1_2 stride 1 Process...

how to build a dataset

17

I want to train with my own dataset， it is like FONT-SVG dataset. but the original data format is *.ttf, So My qestion is how to build a dataset as...

In svgtensor.ipynb , if I want to optimize from Img2 to Img1 ,not from SVG.unit_circle() to Img1, how should I do, I tried replaced svg_pred with other SVG.load_data() , but...

embedding_num question

5

Hi, thank you your code, I learn a lot, but I want to ask: you train your model with 27 fonts but in your code embedding_num=40, so the true_labels range...

  But in the code https://github.com/hszhao/SAN/blob/d88b022fc3ec4920d4596f94983f0e5b1ced62c6/model/san.py#L39-L42 I think the self.conv_w is the mapping function but it is different from paper **code**: BN -> R -> Conv -> BN ->...