wuzeww

Results 17 comments of wuzeww

But the result of GIGA-Aff is higher than the paper.

I am currently making a graduation project based on your thesis, so I am eager to know the specific epochs of your work. You can also reply me by email...

5 or 6 percentage points

Yes, the random seeds are [0, 1, 2, 3, 4]. The epoches are 20. I tested twice, the results were both higher than the paper.

emm, the result of GIGA-Aff sometimes are better than GIGA. About 1 percent. ---Original--- From: "Zhenyu ***@***.***> Date: Wed, Oct 27, 2021 06:42 AM To: ***@***.***>; Cc: ***@***.***>;"State ***@***.***>; Subject: Re: [UT-Austin-RPL/GIGA] How (Issue #8) Hmmm, how about the result of GIGA?...

### **This is the loss graph of GIGA-Aff training 20 epoches** ![2021-10-28 09-59-19 的屏幕截图](https://user-images.githubusercontent.com/44798683/139174227-62269f9a-adb1-4062-b40f-77ef30873fb7.png) ### **This is the 10 epoches** ![2021-10-28 09-59-26 的屏幕截图](https://user-images.githubusercontent.com/44798683/139174355-29153f68-0325-44b5-8979-e39adc479099.png)

Hi, I trained GIGA-Aff for 10 epoches, the result is higher 5 percentage points than the paper. I wonder if there is a problem with the code.

This the loss curve of giga: ![2021-10-30 20-51-43 的屏幕截图](https://user-images.githubusercontent.com/44798683/139533551-8aad669b-ddd2-43af-b892-5925863b9a01.png)

yes ---Original--- From: "Zhenyu ***@***.***> Date: Sun, Oct 31, 2021 05:10 AM To: ***@***.***>; Cc: ***@***.***>;"State ***@***.***>; Subject: Re: [UT-Austin-RPL/GIGA] How (Issue #8) So the GIGA trained with the same...

packed. Is the cause of network instability? ---Original--- From: "Zhenyu ***@***.***> Date: Mon, Nov 1, 2021 03:11 AM To: ***@***.***>; Cc: ***@***.***>;"State ***@***.***>; Subject: Re: [UT-Austin-RPL/GIGA] How (Issue #8) Hmmm,...