The test effect of the data set is much worse than the indicators reported in the original paper，How to solve it？

[FPX-Tian1998]

[Cloud-Liu]

Hello, I have the same problem, have you solved it now?

[sdtegaotian]

use some trick on dataset

[Better-77]

use some trick on dataset

Can you elaborate?

[sdtegaotian]

sorry this model, I can not arrive acurracy in his paper .I change some components

---- Replied Message ---- | From | @.> | | Date | 02/25/2023 16:15 | | To | @.> | | Cc | @.>@.> | | Subject | Re: [jeya-maria-jose/UNeXt-pytorch] The test effect of the data set is much worse than the indicators reported in the original paper，How to solve it？ (Issue #19) |

use some trick on dataset

Can you elaborate?

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.***>

[Better-77]

I used my own dataset and got very low metrics, iou and dice less than 0.5, do you have a suggestion for a solution? ------------------ 原始邮件 ------------------ 发件人: "jeya-maria-jose/UNeXt-pytorch" @.>; 发送时间: 2023年2月25日(星期六) 下午4:20 @.>; @.@.>; 主题: Re: [jeya-maria-jose/UNeXt-pytorch] The test effect of the data set is much worse than the indicators reported in the original paper，How to solve it？ (Issue #19)

sorry this model, I can not arrive acurracy in his paper .I change some components

---- Replied Message ---- | From | @.> | | Date | 02/25/2023 16:15 | | To | @.> | | Cc | @.>@.> | | Subject | Re: [jeya-maria-jose/UNeXt-pytorch] The test effect of the data set is much worse than the indicators reported in the original paper，How to solve it？ (Issue #19) |

use some trick on dataset

Can you elaborate?

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.> — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.>