Using model and data provided,but acc is very bad

[junqiangwu]

Using the fh02.pth that you provided, and test data is ccpd_rotate, but the test_acc is very bad. loger show acc is around 0.187? Is this model not the final version?

total 1350 correct 248 error 0 precision 0.1837037037037037 six 0.4777777777777778 avg_time 0.10965083245877866
total 1400 correct 263 error 0 precision 0.18785714285714286 six 0.4742857142857143 avg_time 0.10965067097118923
total 1450 correct 275 error 0 precision 0.1896551724137931 six 0.47448275862068967 avg_time 0.10962377745529701
total 1500 correct 285 error 0 precision 0.19 six 0.47733333333333333 avg_time 0.10957734648386637
total 1550 correct 290 error 0 precision 0.1870967741935484 six 0.47483870967741937 avg_time 0.10940563063467702
total 1600 correct 302 error 0 precision 0.18875 six 0.474375 avg_time 0.10931647881865501
total 1650 correct 312 error 0 precision 0.1890909090909091 six 0.4763636363636364 avg_time 0.10937356255271218
total 1700 correct 322 error 0 precision 0.18941176470588236 six 0.4758823529411765 avg_time 0.10934952160891365
total 1750 correct 336 error 0 precision 0.192 six 0.47885714285714287 avg_time 0.10931393827710832
total 1800 correct 346 error 0 precision 0.1922222222222222 six 0.4777777777777778 avg_time 0.1093952649169498
total 1850 correct 354 error 0 precision 0.19135135135135134 six 0.4772972972972973 avg_time 0.10933325612867201
total 1900 correct 364 error 0 precision 0.19157894736842104 six 0.47421052631578947 avg_time 0.10927746433960764
total 1950 correct 373 error 0 precision 0.19128205128205128 six 0.4764102564102564 avg_time 0.10912113580948267
total 2000 correct 381 error 0 precision 0.1905 six 0.477 avg_time 0.10900945067405701
total 2050 correct 394 error 0 precision 0.19219512195121952 six 0.47804878048780486 avg_time 0.108927451924579

[junqiangwu]

Using test data ccpd_base, the acc is around 0.50

total 250 correct 124 error 0 precision 0.496 six 0.836 avg_time 0.10912780570983886
total 300 correct 147 error 0 precision 0.49 six 0.84 avg_time 0.10871603012084961
total 350 correct 180 error 0 precision 0.5142857142857142 six 0.8514285714285714 avg_time 0.10944753987448556
total 400 correct 205 error 0 precision 0.5125 six 0.8575 avg_time 0.1089352834224701
total 450 correct 232 error 0 precision 0.5155555555555555 six 0.86 avg_time 0.10881534046596951
total 500 correct 255 error 0 precision 0.51 six 0.862 avg_time 0.10848832941055297
total 550 correct 280 error 0 precision 0.509090909090909 six 0.8563636363636363 avg_time 0.10873743317343972
total 600 correct 303 error 0 precision 0.505 six 0.8466666666666667 avg_time 0.10865229447682699
total 650 correct 336 error 0 precision 0.5169230769230769 six 0.8507692307692307 avg_time 0.10865203710702749
total 700 correct 362 error 0 precision 0.5171428571428571 six 0.8542857142857143 avg_time 0.10874608993530273
total 750 correct 391 error 0 precision 0.5213333333333333 six 0.8546666666666667 avg_time 0.1086995906829834
total 800 correct 412 error 0 precision 0.515 six 0.85625 avg_time 0.10871987730264664

[Harsha-1729]

fh02.pth that is provided is trained only for 5 epochs, in the paper its given that 300 epochs trained network will give the best results. So I think we need to train for 300 epochs atleast and try to test the accuracy.

[kingStar1006]

fh02.pth that is provided is trained only for 5 epochs, in the paper its given that 300 epochs trained network will give the best results. So I think we need to train for 300 epochs atleast and try to test the accuracy.

i will try

[xiamangfu]

结果根本复现不出来啊