search

HelloRicky123 / Siamese-RPN

Full reimplementation of siamese rpn, has 0.24 eao on vot2017.
MIT License
223 stars 44 forks source link

about the 54version #10

Closed ArsNova123 closed 5 years ago

ArsNova123 commented 5 years ago

I noticed that the config.py in your 54version is different from the former version ,the instance_size of 54ver is 271 while the instance_size of the former ver is 255.Does this mean that data preprocessing needs to be done again when running version 054 of the code?

HelloRicky123 commented 5 years ago

no

ArsNova123 commented 5 years ago

no

OK,thank you,I followed your settings to train this model and found the loss turned into nan,I slightly reduced the initial learning rate.It can run properly.

Holdeny commented 5 years ago

no

OK,thank you,I followed your settings to train this model and found the loss turned into nan,I slightly reduced the initial learning rate.It can run properly.

Could you tell me the initial learning rate you set? I have the same problem as you, thank you.

HelloRicky123 commented 5 years ago

All setting is in the 59version folder without any warmup.------------------ Original ------------------From: Holdeny notifications@github.comDate: Sat,Mar 30,2019 11:35 PMTo: HelloRicky123/Siamese-RPN Siamese-RPN@noreply.github.comCc: HelloRicky123 qftju12345@163.com, Comment comment@noreply.github.comSubject: Re: [HelloRicky123/Siamese-RPN] about the 54version (#10)

no

OK,thank you,I followed your settings to train this model and found the loss turned into nan,I slightly reduced the initial learning rate.It can run properly.

Could you tell me the initial learning rate you set? I have the same problem as you, thank you.

—You are receiving this because you commented.Reply to this email directly, view it on GitHub, or mute the thread. {"api_version":"1.0","publisher":{"api_key":"05dde50f1d1a384dd78767c55493e4bb","name":"GitHub"},"entity":{"external_key":"github/HelloRicky123/Siamese-RPN","title":"HelloRicky123/Siamese-RPN","subtitle":"GitHub repository","main_image_url":"https://github.githubassets.com/images/email/message_cards/header.png","avatar_image_url":"https://github.githubassets.com/images/email/message_cards/avatar.png","action":{"name":"Open in GitHub","url":"https://github.com/HelloRicky123/Siamese-RPN"}},"updates":{"snippets":[{"icon":"PERSON","message":"@Holdeny in #10: \u003e \u003e no\r\n\u003e \r\n\u003e OK,thank you,I followed your settings to train this model and found the loss turned into nan,I slightly reduced the initial learning rate.It can run properly.\r\n\r\nCould you tell me the initial learning rate you set? I have the same problem as you, thank you."}],"action":{"name":"View Issue","url":"https://github.com/HelloRicky123/Siamese-RPN/issues/10#issuecomment-478256814"}}} [ { "@context": "http://schema.org", "@type": "EmailMessage", "potentialAction": { "@type": "ViewAction", "target": "https://github.com/HelloRicky123/Siamese-RPN/issues/10#issuecomment-478256814", "url": "https://github.com/HelloRicky123/Siamese-RPN/issues/10#issuecomment-478256814", "name": "View Issue" }, "description": "View this Issue on GitHub", "publisher": { "@type": "Organization", "name": "GitHub", "url": "https://github.com" } } ]

HelloRicky123 commented 5 years ago

Closed