关于学习率

[EillotY]

你好，我现在想利用这个模型提优，加入了trick之后，是有点提高，但是我觉得应该还有进步，现在想询问你的是：代码中设置的学习率很低，你是根据经验设置的嘛？还是自己寻找到的这个学习率，我想找到最优学习率，我现在能想到的是，慢慢的提高学习率这样，但是感觉还是会有问题，因为我还是不能知道什么时候才能得到一个好的学习率

[ft-z]

Hello, I am also looking at this code, can you please implement the detection after inserting a new picture?
你好，我也在看这个代码，请问你能实现新的图片插入后检测吗？

[EillotY]

Hello, I am also looking at this code, can you please implement the detection after inserting a new picture?
你好，我也在看这个代码，请问你能实现新的图片插入后检测吗？

you mean a interface to detect one image from reality? i think you should use the last.pt to create a model, this code does not have the function.

[ft-z]

Unfortunately, I didn't find the last.pt information you mentioned, then I will try to add the code to generate density map. Thank you for the reply! 很遗憾我没有找到你说的last.pt相关资料，那我将尝试加入生成密度图的代码。谢谢你的答复！

…

------------------&nbsp;原始邮件&nbsp;------------------ 发件人:&nbsp;"M.Yuan"<[email protected]&gt;; 发送时间:&nbsp;2020年4月15日(星期三) 晚上11:58 收件人:&nbsp;"svishwa/crowdcount-mcnn"<[email protected]&gt;; 抄送:&nbsp;"郑兴文"<[email protected]&gt;;"Comment"<[email protected]&gt;; 主题:&nbsp;Re: [svishwa/crowdcount-mcnn] 关于学习率 (#57) Hello, I am also looking at this code, can you please implement the detection after inserting a new picture? 你好，我也在看这个代码，请问你能实现新的图片插入后检测吗？ you mean a interface to detect one image from reality? i think you should use the last.pt to create a model, this code does not have the function. — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.

[EillotY]

soy, i find out it is the best.h5 file to create model. my bad

[ft-z]

thanks！

…

------------------&nbsp;原始邮件&nbsp;------------------ 发件人:&nbsp;"M.Yuan"<[email protected]&gt;; 发送时间:&nbsp;2020年4月16日(星期四) 凌晨0:11 收件人:&nbsp;"svishwa/crowdcount-mcnn"<[email protected]&gt;; 抄送:&nbsp;"郑兴文"<[email protected]&gt;;"Comment"<[email protected]&gt;; 主题:&nbsp;Re: [svishwa/crowdcount-mcnn] 关于学习率 (#57) soy, i find out it is the best.h5 file to create model. my bad — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.