The mAP on VOC2007 test in only 53.5%, which is much worse than 56.8% in the Neurips paper
dsthing opened this issue · comments
Hello, your work is excellent!
But the result of your code is only 53.5% mAP, which is significantly lower than 56.8% mAP reported in your paper.
Any suggestions to how one might reproduce the published results?
the classification AP is
AP for aeroplane = 0.9836
AP for bicycle = 0.9709
AP for bird = 0.9765
AP for boat = 0.9553
AP for bottle = 0.8009
AP for bus = 0.9501
AP for car = 0.9724
AP for cat = 0.9677
AP for chair = 0.7514
AP for cow = 0.9229
AP for diningtable = 0.8283
AP for dog = 0.9770
AP for horse = 0.9687
AP for motorbike = 0.9549
AP for person = 0.9897
AP for pottedplant = 0.8265
AP for sheep = 0.9278
AP for sofa = 0.8116
AP for train = 0.9726
AP for tvmonitor = 0.9102
__________________
the mAP is 92.0957
Evaluating detections
Writing aeroplane VOC results file
Writing bicycle VOC results file
Writing bird VOC results file
Writing boat VOC results file
Writing bottle VOC results file
Writing bus VOC results file
Writing car VOC results file
Writing cat VOC results file
Writing chair VOC results file
Writing cow VOC results file
Writing diningtable VOC results file
Writing dog VOC results file
Writing horse VOC results file
Writing motorbike VOC results file
Writing person VOC results file
Writing pottedplant VOC results file
Writing sheep VOC results file
Writing sofa VOC results file
Writing train VOC results file
Writing tvmonitor VOC results file
VOC07 metric? Yes
AP for aeroplane = 0.6933
AP for bicycle = 0.6773
AP for bird = 0.5468
AP for boat = 0.3945
AP for bottle = 0.2312
AP for bus = 0.6964
AP for car = 0.6922
AP for cat = 0.7217
AP for chair = 0.2173
AP for cow = 0.6577
AP for diningtable = 0.4632
AP for dog = 0.6464
AP for horse = 0.5931
AP for motorbike = 0.6789
AP for person = 0.1639
AP for pottedplant = 0.2502
AP for sheep = 0.5352
AP for sofa = 0.5645
AP for train = 0.6312
AP for tvmonitor = 0.6608
Mean AP = 0.5358
Hi,
The current version only contains unparalleled CASD_IW(54.6%). Paralleled CASD_LW and regression_brand is coming soon.
Hello, your work is excellent!
But the result of your code is only 53.5% mAP, which is significantly lower than 56.8% mAP reported in your paper.
Any suggestions to how one might reproduce the published results?the classification AP is AP for aeroplane = 0.9836 AP for bicycle = 0.9709 AP for bird = 0.9765 AP for boat = 0.9553 AP for bottle = 0.8009 AP for bus = 0.9501 AP for car = 0.9724 AP for cat = 0.9677 AP for chair = 0.7514 AP for cow = 0.9229 AP for diningtable = 0.8283 AP for dog = 0.9770 AP for horse = 0.9687 AP for motorbike = 0.9549 AP for person = 0.9897 AP for pottedplant = 0.8265 AP for sheep = 0.9278 AP for sofa = 0.8116 AP for train = 0.9726 AP for tvmonitor = 0.9102 __________________ the mAP is 92.0957 Evaluating detections Writing aeroplane VOC results file Writing bicycle VOC results file Writing bird VOC results file Writing boat VOC results file Writing bottle VOC results file Writing bus VOC results file Writing car VOC results file Writing cat VOC results file Writing chair VOC results file Writing cow VOC results file Writing diningtable VOC results file Writing dog VOC results file Writing horse VOC results file Writing motorbike VOC results file Writing person VOC results file Writing pottedplant VOC results file Writing sheep VOC results file Writing sofa VOC results file Writing train VOC results file Writing tvmonitor VOC results file VOC07 metric? Yes AP for aeroplane = 0.6933 AP for bicycle = 0.6773 AP for bird = 0.5468 AP for boat = 0.3945 AP for bottle = 0.2312 AP for bus = 0.6964 AP for car = 0.6922 AP for cat = 0.7217 AP for chair = 0.2173 AP for cow = 0.6577 AP for diningtable = 0.4632 AP for dog = 0.6464 AP for horse = 0.5931 AP for motorbike = 0.6789 AP for person = 0.1639 AP for pottedplant = 0.2502 AP for sheep = 0.5352 AP for sofa = 0.5645 AP for train = 0.6312 AP for tvmonitor = 0.6608 Mean AP = 0.5358
Hi, when I run the codes, there occurred an error: 'Selective search data not found at: data/selective_search_data/voc_2007_trainval.mat' in pascal_voc.py , did you meet the same problem?
Hello, your work is excellent!
But the result of your code is only 53.5% mAP, which is significantly lower than 56.8% mAP reported in your paper.
Any suggestions to how one might reproduce the published results?the classification AP is AP for aeroplane = 0.9836 AP for bicycle = 0.9709 AP for bird = 0.9765 AP for boat = 0.9553 AP for bottle = 0.8009 AP for bus = 0.9501 AP for car = 0.9724 AP for cat = 0.9677 AP for chair = 0.7514 AP for cow = 0.9229 AP for diningtable = 0.8283 AP for dog = 0.9770 AP for horse = 0.9687 AP for motorbike = 0.9549 AP for person = 0.9897 AP for pottedplant = 0.8265 AP for sheep = 0.9278 AP for sofa = 0.8116 AP for train = 0.9726 AP for tvmonitor = 0.9102 __________________ the mAP is 92.0957 Evaluating detections Writing aeroplane VOC results file Writing bicycle VOC results file Writing bird VOC results file Writing boat VOC results file Writing bottle VOC results file Writing bus VOC results file Writing car VOC results file Writing cat VOC results file Writing chair VOC results file Writing cow VOC results file Writing diningtable VOC results file Writing dog VOC results file Writing horse VOC results file Writing motorbike VOC results file Writing person VOC results file Writing pottedplant VOC results file Writing sheep VOC results file Writing sofa VOC results file Writing train VOC results file Writing tvmonitor VOC results file VOC07 metric? Yes AP for aeroplane = 0.6933 AP for bicycle = 0.6773 AP for bird = 0.5468 AP for boat = 0.3945 AP for bottle = 0.2312 AP for bus = 0.6964 AP for car = 0.6922 AP for cat = 0.7217 AP for chair = 0.2173 AP for cow = 0.6577 AP for diningtable = 0.4632 AP for dog = 0.6464 AP for horse = 0.5931 AP for motorbike = 0.6789 AP for person = 0.1639 AP for pottedplant = 0.2502 AP for sheep = 0.5352 AP for sofa = 0.5645 AP for train = 0.6312 AP for tvmonitor = 0.6608 Mean AP = 0.5358
hello, i want to ask you a question. when I run the codes, there occurred an error: 'Selective search data not found at: data/selective_search_data/voc_2007_trainval.mat', I want to know where or how to get this file?
Hi,
The current version only contains unparalleled CASD_IW(54.6%). Paralleled CASD_LW and regression_brand is coming soon.
Hi,
It's been a while since you said paralleled version will be added but I don't think it has been updated yet. Do you have a plan to add it sometime soon?