search

jimth001 / formality_style_transfer_with_shared_latent_space

The repo of the paper "Formality Style Transfer with Shared Latent Space"
MIT License
9 stars 1 forks source link

why will this question happen? I get the same result #3

Open wusuhuang opened 2 years ago

wusuhuang commented 2 years ago

hello, thank you for answering me the question about "how to prepare the data" again. Now I want to ask you another question when I train and evaluate the data. The dataset is made by myself. I want to transfer one style to another style. I have 6000 for train, 2000 for validation and 2000 for test parallel data. But when I print the inf2fm data in the file _slsgpt.py in 559 line in batch_num: 100 image I get the result: image

I don't know why. When I run another experiment "Style Transfer Through Back-Translation. ACL 2018" . I also get the same result. image So I turn to you for help~

best wishes, thank you very much!!!!

jimth001 commented 2 years ago

Hi,

Do you mean the input is "convert a string to a string" and the output is "Return a list of file"? And the result is unsatisfied? If so, I think you can first check if the pre-trained model is loaded successfully. The code would initialize the model randomly when the pre-trained ckpt is not found. Without the large pre-trained LM model, the result may not be so good on such a small dataset. 

Good luck to your research!

Yunli

------------------ 原始邮件 ------------------ 发件人: "jimth001/formality_style_transfer_with_shared_latent_space" @.>; 发送时间: 2022年2月28日(星期一) 晚上11:04 @.>; @.***>; 主题: [jimth001/formality_style_transfer_with_shared_latent_space] why will this question happen? I get the same result (Issue #3)

hello, thank you for answering me the question about "how to prepare the data" again. Now I want to ask you another question when I train and evaluate the data. The dataset is made by myself. I want to transfer one style to another style. I have 6000 for train, 2000 for validation and 2000 for test parallel data. But when I print the inf2fm data in the file sls_gpt.py in 559 line in batch_num: 100

I get the result:

I don't know why. When I run another experiment "Style Transfer Through Back-Translation. ACL 2018" . I also get the same result.

So I turn to you for help~

best wishes, thank you very much!!!!

— Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android. You are receiving this because you are subscribed to this thread.Message ID: @.***>