关于代码中的Trlabel以及Telabel

[Uncolor-Duck]

想请问一个问题，原本的代码是从每个55的像素里面提取出x个可能端元吗？为什么我的Trlabel最终结果的尺度为9560760（9560为像素个数） Telabel代码无法生成，他是从哪来的呢？

[danfenghong]

我们是有重叠地抽取每个patch，在上面提取端元，然后去除重复的，所以数量不是固定的。Trlabel包含的是不同材质端元的数量。 Telabel是ground truth用于评估算法结果的，不用于训练。

Uncolor-Duck @.***> 于2021年12月22日周三 13:40写道：

想请问一个问题，原本的代码是从每个55的像素里面提取出x个可能端元吗？为什么我的Trlabel最终结果的尺度为9560 760（9560为像素个数） Telabel代码无法生成，他是从哪来的呢？

— Reply to this email directly, view it on GitHub https://github.com/danfenghong/IEEE_TNNLS_EGU-Net/issues/7, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFL2GZQNHHN56CIFITB5QWLUSFQD5ANCNFSM5KRXY7JQ . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.

You are receiving this because you are subscribed to this thread.Message ID: @.***>

[Uncolor-Duck]

我们是有重叠地抽取每个patch，在上面提取端元，然后去除重复的，所以数量不是固定的。Trlabel包含的是不同材质端元的数量。 Telabel是ground truth用于评估算法结果的，不用于训练。 Uncolor-Duck @.> 于2021年12月22日周三 13:40写道： … 想请问一个问题，原本的代码是从每个55的像素里面提取出x个可能端元吗？为什么我的Trlabel最终结果的尺度为9560 760（9560为像素个数） Telabel代码无法生成，他是从哪来的呢？ — Reply to this email directly, view it on GitHub <#7>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFL2GZQNHHN56CIFITB5QWLUSFQD5ANCNFSM5KRXY7JQ . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub. You are receiving this because you are subscribed to this thread.Message ID: @.>

感谢您的回答 您给的数据集中Trlabel尺度为8000×5而TeLabel为40000×5，这个5是如何将端元数量缩减到如此小的？难道是使用vca对EM再进行一次端元提取吗？ 麻烦您能否解答一下呢？

[danfenghong]

5是端元种类不是端元数量

Uncolor-Duck @.***> 于2021年12月26日周日 12:33写道：

我们是有重叠地抽取每个patch，在上面提取端元，然后去除重复的，所以数量不是固定的。Trlabel包含的是不同材质端元的数量。 Telabel是ground truth用于评估算法结果的，不用于训练。 Uncolor-Duck @.

*> 于2021年12月22日周三 13:40写道： … <#m2901006459238136555> 想请问一个问题，原本的代码是从每个55的像素里面提取出x个可能端元吗？为什么我的Trlabel最终结果的尺度为9560 760（9560为像素个数） Telabel代码无法生成，他是从哪来的呢？ — Reply to this email directly, view it on GitHub <#7 https://github.com/danfenghong/IEEE_TNNLS_EGU-Net/issues/7>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFL2GZQNHHN56CIFITB5QWLUSFQD5ANCNFSM5KRXY7JQ https://github.com/notifications/unsubscribe-auth/AFL2GZQNHHN56CIFITB5QWLUSFQD5ANCNFSM5KRXY7JQ . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub. You are receiving this because you are subscribed to this thread.Message ID: @.***>

感谢您的回答

您给的数据集中Trlabel尺度为8000×5而TeLabel为40000×5，这个5是如何将端元数量缩减到如此小的？难道是使用vca对EM再进行一次端元提取吗？ 麻烦您能否解答一下呢？

— Reply to this email directly, view it on GitHub https://github.com/danfenghong/IEEE_TNNLS_EGU-Net/issues/7#issuecomment-1001105361, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFL2GZX6HO4QS64R2I2L6Z3US2LIFANCNFSM5KRXY7JQ . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.

You are receiving this because you commented.Message ID: @.***>

[Uncolor-Duck]

5是端元种类不是端元数量 Uncolor-Duck @.> 于2021年12月26日周日 12:33写道： … 我们是有重叠地抽取每个patch，在上面提取端元，然后去除重复的，所以数量不是固定的。Trlabel包含的是不同材质端元的数量。 Telabel是ground truth用于评估算法结果的，不用于训练。 Uncolor-Duck @. > 于2021年12月22日周三 13:40写道： … <#m2901006459238136555> 想请问一个问题，原本的代码是从每个55的像素里面提取出x个可能端元吗？为什么我的Trlabel最终结果的尺度为9560 760（9560为像素个数） Telabel代码无法生成，他是从哪来的呢？ — Reply to this email directly, view it on GitHub <#7 <#7>>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFL2GZQNHHN56CIFITB5QWLUSFQD5ANCNFSM5KRXY7JQ https://github.com/notifications/unsubscribe-auth/AFL2GZQNHHN56CIFITB5QWLUSFQD5ANCNFSM5KRXY7JQ . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub. You are receiving this because you are subscribed to this thread.Message ID: @.**> 感谢您的回答 您给的数据集中Trlabel尺度为8000×5而TeLabel为40000×5，这个5是如何将端元数量缩减到如此小的？难道是使用vca对EM再进行一次端元提取吗？ 麻烦您能否解答一下呢？ — Reply to this email directly, view it on GitHub <#7 (comment)>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFL2GZX6HO4QS64R2I2L6Z3US2LIFANCNFSM5KRXY7JQ . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub. You are receiving this because you commented.Message ID: @.>

那请问，使用您的代码'Pseudo_endmembers_generation'以及数据Mix生成的Trlabel尺度为8000×40000而不是8000×5 为了代码不报错，我将 Abund = sunsal(EM, X', 'lambda', 0, 'ADDONE', 'no', 'POSITIVITY', 'yes', ... 'AL_iters', 200, 'TOL', 1e-4, 'verbose','yes'); 改为了 Abund = sunsal(EM, X, 'lambda', 0, 'ADDONE', 'no', 'POSITIVITY', 'yes', ... 'AL_iters', 200, 'TOL', 1e-4, 'verbose','yes'); 否则将会报错X与EM的一维尺度不同

[danfenghong]

Trlabel得到的是abundances不是端元，端元是EM，建议可以多读几遍论文。 此外，我那么写X和EM维度是对应的，是可以运行的，只要合理就行，还要看你代码中维度是放在那的。

Uncolor-Duck @.***> 于2021年12月26日周日 12:54写道：

5是端元种类不是端元数量 Uncolor-Duck @.

*> 于2021年12月26日周日 12:33写道： … <#m-8272285862764587946> 我们是有重叠地抽取每个patch，在上面提取端元，然后去除重复的，所以数量不是固定的。Trlabel包含的是不同材质端元的数量。 Telabel是ground truth用于评估算法结果的，不用于训练。 Uncolor-Duck @. > 于2021年12月22日周三 13:40写道： … <#m2901006459238136555> 想请问一个问题，原本的代码是从每个55的像素里面提取出x个可能端元吗？为什么我的Trlabel最终结果的尺度为9560 760（9560为像素个数） Telabel代码无法生成，他是从哪来的呢？ — Reply to this email directly, view it on GitHub <#7 https://github.com/danfenghong/IEEE_TNNLS_EGU-Net/issues/7 <#7 https://github.com/danfenghong/IEEE_TNNLS_EGU-Net/issues/7>>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFL2GZQNHHN56CIFITB5QWLUSFQD5ANCNFSM5KRXY7JQ https://github.com/notifications/unsubscribe-auth/AFL2GZQNHHN56CIFITB5QWLUSFQD5ANCNFSM5KRXY7JQ https://github.com/notifications/unsubscribe-auth/AFL2GZQNHHN56CIFITB5QWLUSFQD5ANCNFSM5KRXY7JQ https://github.com/notifications/unsubscribe-auth/AFL2GZQNHHN56CIFITB5QWLUSFQD5ANCNFSM5KRXY7JQ . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub. You are receiving this because you are subscribed to this thread.Message ID: @.> 感谢您的回答 您给的数据集中Trlabel尺度为8000×5而TeLabel为40000×5，这个5是如何将端元数量缩减到如此小的？难道是使用vca对EM再进行一次端元提取吗？ 麻烦您能否解答一下呢？ — Reply to this email directly, view it on GitHub <#7 (comment) https://github.com/danfenghong/IEEE_TNNLS_EGU-Net/issues/7#issuecomment-1001105361>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFL2GZX6HO4QS64R2I2L6Z3US2LIFANCNFSM5KRXY7JQ https://github.com/notifications/unsubscribe-auth/AFL2GZX6HO4QS64R2I2L6Z3US2LIFANCNFSM5KRXY7JQ . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub. You are receiving this because you commented.Message ID: @.***>

那请问，使用您的代码'Pseudo_endmembers_generation'以及数据Mix生成的Trlabel尺度为8000×40000而不是8000×5 为了代码不报错，我将 Abund = sunsal(EM, X', 'lambda', 0, 'ADDONE', 'no', 'POSITIVITY', 'yes', ... 'AL_iters', 200, 'TOL', 1e-4, 'verbose','yes'); 改为了 Abund = sunsal(EM, X, 'lambda', 0, 'ADDONE', 'no', 'POSITIVITY', 'yes', ... 'AL_iters', 200, 'TOL', 1e-4, 'verbose','yes'); 否则将会报错X与EM的一维尺度不同

— Reply to this email directly, view it on GitHub https://github.com/danfenghong/IEEE_TNNLS_EGU-Net/issues/7#issuecomment-1001106463, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFL2GZXMBRRFG7BJ335YRRLUS2NXTANCNFSM5KRXY7JQ . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.

You are receiving this because you commented.Message ID: @.***>

[Uncolor-Duck]

Trlabel得到的是abundances不是端元，端元是EM，建议可以多读几遍论文。 此外，我那么写X和EM维度是对应的，是可以运行的，只要合理就行，还要看你代码中维度是放在那的。 Uncolor-Duck @.> 于2021年12月26日周日 12:54写道： … 5是端元种类不是端元数量 Uncolor-Duck @. > 于2021年12月26日周日 12:33写道： … <#m-8272285862764587946> 我们是有重叠地抽取每个patch，在上面提取端元，然后去除重复的，所以数量不是固定的。Trlabel包含的是不同材质端元的数量。 Telabel是ground truth用于评估算法结果的，不用于训练。 Uncolor-Duck @. > 于2021年12月22日周三 13:40写道： … <#m2901006459238136555> 想请问一个问题，原本的代码是从每个55的像素里面提取出x个可能端元吗？为什么我的Trlabel最终结果的尺度为9560 760（9560为像素个数） Telabel代码无法生成，他是从哪来的呢？ — Reply to this email directly, view it on GitHub <#7 <#7> <#7 <#7>>>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFL2GZQNHHN56CIFITB5QWLUSFQD5ANCNFSM5KRXY7JQ https://github.com/notifications/unsubscribe-auth/AFL2GZQNHHN56CIFITB5QWLUSFQD5ANCNFSM5KRXY7JQ https://github.com/notifications/unsubscribe-auth/AFL2GZQNHHN56CIFITB5QWLUSFQD5ANCNFSM5KRXY7JQ https://github.com/notifications/unsubscribe-auth/AFL2GZQNHHN56CIFITB5QWLUSFQD5ANCNFSM5KRXY7JQ . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub. You are receiving this because you are subscribed to this thread.Message ID: @.> 感谢您的回答 您给的数据集中Trlabel尺度为8000×5而TeLabel为40000×5，这个5是如何将端元数量缩减到如此小的？难道是使用vca对EM再进行一次端元提取吗？ 麻烦您能否解答一下呢？ — Reply to this email directly, view it on GitHub <#7 (comment) <#7 (comment)>>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFL2GZX6HO4QS64R2I2L6Z3US2LIFANCNFSM5KRXY7JQ https://github.com/notifications/unsubscribe-auth/AFL2GZX6HO4QS64R2I2L6Z3US2LIFANCNFSM5KRXY7JQ . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub. You are receiving this because you commented.Message ID: @.**> 那请问，使用您的代码'Pseudo_endmembers_generation'以及数据Mix生成的Trlabel尺度为8000×40000而不是8000×5 为了代码不报错，我将 Abund = sunsal(EM, X', 'lambda', 0, 'ADDONE', 'no', 'POSITIVITY', 'yes', ... 'AL_iters', 200, 'TOL', 1e-4, 'verbose','yes'); 改为了 Abund = sunsal(EM, X, 'lambda', 0, 'ADDONE', 'no', 'POSITIVITY', 'yes', ... 'AL_iters', 200, 'TOL', 1e-4, 'verbose','yes'); 否则将会报错X与EM的一维尺度不同 — Reply to this email directly, view it on GitHub <#7 (comment)>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFL2GZXMBRRFG7BJ335YRRLUS2NXTANCNFSM5KRXY7JQ . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub. You are receiving this because you commented.Message ID: @.>

感谢您的指教。 我现在明白了，使用K-means算法对EM重新进行了一次提取，目前已经比较完整了。 再次感谢您！

[danfenghong]

好的，😀。 祝好！ 丹枫

Uncolor-Duck @.***> 于2021年12月26日周日 15:36写道：

Trlabel得到的是abundances不是端元，端元是EM，建议可以多读几遍论文。 此外，我那么写X和EM维度是对应的，是可以运行的，只要合理就行，还要看你代码中维度是放在那的。 Uncolor-Duck @.

*> 于2021年12月26日周日 12:54写道： … <#m8667143110820393214> 5是端元种类不是端元数量 Uncolor-Duck @. > 于2021年12月26日周日 12:33写道： … <#m-8272285862764587946> 我们是有重叠地抽取每个patch，在上面提取端元，然后去除重复的，所以数量不是固定的。Trlabel包含的是不同材质端元的数量。 Telabel是ground truth用于评估算法结果的，不用于训练。 Uncolor-Duck @. > 于2021年12月22日周三 13:40写道： … <#m2901006459238136555> 想请问一个问题，原本的代码是从每个55的像素里面提取出x个可能端元吗？为什么我的Trlabel最终结果的尺度为9560 760（9560为像素个数） Telabel代码无法生成，他是从哪来的呢？ — Reply to this email directly, view it on GitHub <#7 https://github.com/danfenghong/IEEE_TNNLS_EGU-Net/issues/7 <#7 https://github.com/danfenghong/IEEE_TNNLS_EGU-Net/issues/7> <#7 https://github.com/danfenghong/IEEE_TNNLS_EGU-Net/issues/7 <#7 https://github.com/danfenghong/IEEE_TNNLS_EGU-Net/issues/7>>>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFL2GZQNHHN56CIFITB5QWLUSFQD5ANCNFSM5KRXY7JQ https://github.com/notifications/unsubscribe-auth/AFL2GZQNHHN56CIFITB5QWLUSFQD5ANCNFSM5KRXY7JQ https://github.com/notifications/unsubscribe-auth/AFL2GZQNHHN56CIFITB5QWLUSFQD5ANCNFSM5KRXY7JQ https://github.com/notifications/unsubscribe-auth/AFL2GZQNHHN56CIFITB5QWLUSFQD5ANCNFSM5KRXY7JQ https://github.com/notifications/unsubscribe-auth/AFL2GZQNHHN56CIFITB5QWLUSFQD5ANCNFSM5KRXY7JQ https://github.com/notifications/unsubscribe-auth/AFL2GZQNHHN56CIFITB5QWLUSFQD5ANCNFSM5KRXY7JQ https://github.com/notifications/unsubscribe-auth/AFL2GZQNHHN56CIFITB5QWLUSFQD5ANCNFSM5KRXY7JQ https://github.com/notifications/unsubscribe-auth/AFL2GZQNHHN56CIFITB5QWLUSFQD5ANCNFSM5KRXY7JQ . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub. You are receiving this because you are subscribed to this thread.Message ID: @.> 感谢您的回答 您给的数据集中Trlabel尺度为8000×5而TeLabel为40000×5，这个5是如何将端元数量缩减到如此小的？难道是使用vca对EM再进行一次端元提取吗？ 麻烦您能否解答一下呢？ — Reply to this email directly, view it on GitHub <#7 https://github.com/danfenghong/IEEE_TNNLS_EGU-Net/issues/7 (comment) <#7 (comment) https://github.com/danfenghong/IEEE_TNNLS_EGU-Net/issues/7#issuecomment-1001105361>>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFL2GZX6HO4QS64R2I2L6Z3US2LIFANCNFSM5KRXY7JQ https://github.com/notifications/unsubscribe-auth/AFL2GZX6HO4QS64R2I2L6Z3US2LIFANCNFSM5KRXY7JQ https://github.com/notifications/unsubscribe-auth/AFL2GZX6HO4QS64R2I2L6Z3US2LIFANCNFSM5KRXY7JQ https://github.com/notifications/unsubscribe-auth/AFL2GZX6HO4QS64R2I2L6Z3US2LIFANCNFSM5KRXY7JQ . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub. You are receiving this because you commented.Message ID: @.> 那请问，使用您的代码'Pseudo_endmembers_generation'以及数据Mix生成的Trlabel尺度为8000×40000而不是8000×5 为了代码不报错，我将 Abund = sunsal(EM, X', 'lambda', 0, 'ADDONE', 'no', 'POSITIVITY', 'yes', ... 'AL_iters', 200, 'TOL', 1e-4, 'verbose','yes'); 改为了 Abund = sunsal(EM, X, 'lambda', 0, 'ADDONE', 'no', 'POSITIVITY', 'yes', ... 'AL_iters', 200, 'TOL', 1e-4, 'verbose','yes'); 否则将会报错X与EM的一维尺度不同 — Reply to this email directly, view it on GitHub <#7 (comment) https://github.com/danfenghong/IEEE_TNNLS_EGU-Net/issues/7#issuecomment-1001106463>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFL2GZXMBRRFG7BJ335YRRLUS2NXTANCNFSM5KRXY7JQ https://github.com/notifications/unsubscribe-auth/AFL2GZXMBRRFG7BJ335YRRLUS2NXTANCNFSM5KRXY7JQ . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub. You are receiving this because you commented.Message ID: @.***>

感谢您的指教。 我现在明白了，使用K-means算法对EM重新进行了一次提取，目前已经比较完整了。 再次感谢您！

— Reply to this email directly, view it on GitHub https://github.com/danfenghong/IEEE_TNNLS_EGU-Net/issues/7#issuecomment-1001118001, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFL2GZTX6CHKSSOA7KL4F5TUS3AYJANCNFSM5KRXY7JQ . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.

You are receiving this because you commented.Message ID: @.***>