Micro-Expression-with-Deep-Learning
Micro-Expression-with-Deep-Learning copied to clipboard
IcedDoggie
The result did not reach the declared accuracy
Hi, I ran the example for single db use the data you give in CASME2_Optical: https://drive.google.com/open?id=1fq_eHCLiUT9hP0npq6vkMYiO2Ka-39Mf CASME2_STRAIN: https://drive.google.com/open?id=1-l_CtP9awfMV6pXSrBIPRiIujQLjCv9H. The result is as follows： F1-score:0.2625012255303448 WAR:0.3617886178861789 UAR:0.2455069375069375
Since this result is too far from what you claim to be,I want to know if I have missed any important steps, or can I ask you to give me a trained model. I look forward to hearing from you.Thank you very much.
I have download links. But when I run the main.py, an error came up, " ImportError: No module named 'new_ram'". Can you help me? My email is [email protected] Thank you very much.
How to set TIM length?Because I found that most micro-expression sequences are over 20 frames from onset to offset,Why did you set it 10? And which parameter in TIM correspnd to this length?Looking forward to your reply ~
Hi, do you find the problem about the result, can you tell me?And in the paper, i think f1 should be Macro F1-score
Ya if you changed to MF1, it would drop a little bit.
Sorry because I am not too sure about the problem, there are too much factors that could affect the problem.
Best Regards, Huai-Qian Khor -- *Journey of thousand miles begins with a single step, Doing the best at this moment puts you in the best place for the next moment. *
On Tue, 14 Jan 2020 at 21:17, XShunGao [email protected] wrote:
Hi, do you find the problem about the result, can you tell me?And in the paper, i think f1 should be Macro F1-score
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/IcedDoggie/Micro-Expression-with-Deep-Learning/issues/28?email_source=notifications&email_token=AA7ZNECXRL7G7WLKRCDRVM3Q5W3O7A5CNFSM4G7AZKQ2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEI4R4YY#issuecomment-574168675, or unsubscribe https://github.com/notifications/unsubscribe-auth/AA7ZNEFFGLV3LMR4LTQQIDTQ5W3O7ANCNFSM4G7AZKQQ .
Thanks for your reply. I have questiones about this. When i use sklearn to calculate accuracy and F1, i find accuracy is equal to the micro-F1 in the multiple classes. And in the references 22, the method FDM, he use Macro-F1
Ya a bit of confusion. But the way I calculated it is summing all tp, fp and fn. U can find it in evaluationmatrix.py
On Wed, 15 Jan 2020, 17:11 XShunGao, [email protected] wrote:
Thanks for your reply. I have questiones about this. When i use sklearn to calculate accuracy and F1, i find accuracy is equal to the micro-F1 in the multiple classes. And in the references 22, the method FDM, he use Macro-F1
— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/IcedDoggie/Micro-Expression-with-Deep-Learning/issues/28?email_source=notifications&email_token=AA7ZNEEBH5EGBGQVK7P633LQ53HLRA5CNFSM4G7AZKQ2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEI7SX2Q#issuecomment-574565354, or unsubscribe https://github.com/notifications/unsubscribe-auth/AA7ZNECS7BAIEQZ3M2Y6HWLQ53HLRANCNFSM4G7AZKQQ .
Ya a bit of confusion. But the way I calculated it is summing all tp, fp and fn. U can find it in evaluationmatrix.py … On Wed, 15 Jan 2020, 17:11 XShunGao, @.***> wrote: Thanks for your reply. I have questiones about this. When i use sklearn to calculate accuracy and F1, i find accuracy is equal to the micro-F1 in the multiple classes. And in the references 22, the method FDM, he use Macro-F1 — You are receiving this because you commented. Reply to this email directly, view it on GitHub <#28?email_source=notifications&email_token=AA7ZNEEBH5EGBGQVK7P633LQ53HLRA5CNFSM4G7AZKQ2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEI7SX2Q#issuecomment-574565354>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AA7ZNECS7BAIEQZ3M2Y6HWLQ53HLRANCNFSM4G7AZKQQ .
Thanks. I will read the code. LOSO(Leave-One-Subject-Out) means leave a person's data to test, is right?
Yes. Best Regards, Huai-Qian Khor -- *Journey of thousand miles begins with a single step, Doing the best at this moment puts you in the best place for the next moment. *
On Wed, 15 Jan 2020 at 12:54, XShunGao [email protected] wrote:
Ya a bit of confusion. But the way I calculated it is summing all tp, fp and fn. U can find it in evaluationmatrix.py … <#m_-4205260546320504722_> On Wed, 15 Jan 2020, 17:11 XShunGao, @.***> wrote: Thanks for your reply. I have questiones about this. When i use sklearn to calculate accuracy and F1, i find accuracy is equal to the micro-F1 in the multiple classes. And in the references 22, the method FDM, he use Macro-F1 — You are receiving this because you commented. Reply to this email directly, view it on GitHub <#28 https://github.com/IcedDoggie/Micro-Expression-with-Deep-Learning/issues/28?email_source=notifications&email_token=AA7ZNEEBH5EGBGQVK7P633LQ53HLRA5CNFSM4G7AZKQ2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEI7SX2Q#issuecomment-574565354>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AA7ZNECS7BAIEQZ3M2Y6HWLQ53HLRANCNFSM4G7AZKQQ .
Thanks. I will read the code. LOSO(Leave-One-Subject-Out) means leave a person's data to test, is right?
— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/IcedDoggie/Micro-Expression-with-Deep-Learning/issues/28?email_source=notifications&email_token=AA7ZNEBIDKBTUJAMTFCUON3Q53TPLA5CNFSM4G7AZKQ2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEI747LA#issuecomment-574607276, or unsubscribe https://github.com/notifications/unsubscribe-auth/AA7ZNEDQRYEPLJG5CZDE4L3Q53TPLANCNFSM4G7AZKQQ .