floydhub / pix2code-template Goto Github PK

HI ,It is a cool job.Thanks . Could you upload a pre-trained model ,so we can test the result in minutes.
I want to improve the ability of the model to use it in my work ,could you please tell me any other big datasets?
Thanks very much.It is a great job.

Hi, there. When learning pix2code-template, I found that the trained web model can only output the same DSL content, that is to say, no matter what pictures are given, the output DSL is the same. Note in advance: since my GPU is only 8g, according to the original configuration of your project, my GPU memory is not enough, so I made some modifications during training, changed dtype (float32 - > float16), the model can be trained, but there are problems as I said above. Besides, after several epoches of learning, the loss is always around 0.2. Is this a normal situation? It will be great if you can help me out.