MQR icon indicating copy to clipboard operation
MQR copied to clipboard

Baseline Models

Open dakshvar22 opened this issue 5 years ago • 3 comments

Hi,

Do you plan to release the trained baseline models that you benchmarked in the paper?

Regards, Daksh

dakshvar22 avatar Jan 14 '20 11:01 dakshvar22

No   didnt thought about that

------------------ 原始邮件 ------------------ 发件人: "Daksh Varshneya"<[email protected]>; 发送时间: 2020年1月14日(星期二) 晚上7:10 收件人: "ZeweiChu/MQR"<[email protected]>; 抄送: "Subscribed"<[email protected]>; 主题: [ZeweiChu/MQR] Baseline Models (#2)

Hi,

Do you plan to release the trained baseline models that you benchmarked in the paper?

Regards, Daksh

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or unsubscribe.

DouglasY avatar Jan 18 '20 07:01 DouglasY

Would it be possible for you to share them?

On Sat, Jan 18, 2020, 08:13 DouglasY [email protected] wrote:

No   didnt thought about that

------------------ 原始邮件 ------------------ 发件人: "Daksh Varshneya"<[email protected]>; 发送时间: 2020年1月14日(星期二) 晚上7:10 收件人: "ZeweiChu/MQR"<[email protected]>; 抄送: "Subscribed"<[email protected]>; 主题: [ZeweiChu/MQR] Baseline Models (#2)

Hi,

Do you plan to release the trained baseline models that you benchmarked in the paper?

Regards, Daksh

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or unsubscribe.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/ZeweiChu/MQR/issues/2?email_source=notifications&email_token=ACCOBGOS4MKGOAFFFFRO4XTQ6KTYVA5CNFSM4KGRFSVKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEJJSH3A#issuecomment-575874028, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACCOBGPLJO6WVMRPJBJMLQ3Q6KTYVANCNFSM4KGRFSVA .

dakshvar22 avatar Jan 18 '20 07:01 dakshvar22

Hi, the work was performed during my internship at Google, so I don't have access to the baseline models now. However, most models use Tensor2Tensor library, https://github.com/tensorflow/tensor2tensor so it should be straightforward to retrain them.

ZeweiChu avatar Apr 08 '20 22:04 ZeweiChu