You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
hello,i run your code and the setp just like question #13 ,i just test two video 250 560 and thy both have annotation.i try extract frame in per-one-frame and per-six-frame .
but the result is :
+Detection Performance on thumos14+------+------+------+------+------+------+---------+
| IoU thresh | 0.10 | 0.20 | 0.30 | 0.40 | 0.50 | 0.60 | 0.70 | 0.80 | 0.90 | Average |
+------------+------+------+------+------+------+------+------+------+------+---------+
| mean AP | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan |
+------------+------+------+------+------+------+------+------+------+------+---------+
i do:
1.>python build_of.py SRC OUT
whilch structure is SRC/video_test_0000179.mp4 and unzip the flow.zip and img.zip to
OUT/video_test_0000250/img_00001.jpg
2.>python gen_proposal_list.py thumos14 OUT
the thumos14_tag_test_proposal_list.txt is like this:
I can see that you use "python ssn_test.py thumos14 RGB none RESULT_PICKLE --use_reference" to generate "result_inceptionv3_thumos14_imagenet_rgb.npz"!
hello,i run your code and the setp just like question #13 ,i just test two video 250 560 and thy both have annotation.i try extract frame in per-one-frame and per-six-frame .
but the result is :
+Detection Performance on thumos14+------+------+------+------+------+------+---------+
| IoU thresh | 0.10 | 0.20 | 0.30 | 0.40 | 0.50 | 0.60 | 0.70 | 0.80 | 0.90 | Average |
+------------+------+------+------+------+------+------+------+------+------+---------+
| mean AP | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan |
+------------+------+------+------+------+------+------+------+------+------+---------+
i do:
1.>python build_of.py SRC OUT
whilch structure is SRC/video_test_0000179.mp4 and unzip the flow.zip and img.zip to
OUT/video_test_0000250/img_00001.jpg
2.>python gen_proposal_list.py thumos14 OUT
the thumos14_tag_test_proposal_list.txt is like this:
1
src2/video_test_0000560
1501
1
3
2 265 289
2 597 622
2 1046 1076
39
2 0.2274 0.2274 955 1088
2 0.2858 0.2858 555 638
2 0.2779 0.2779 973 1082
3.>python ssn_test.py thumos14 RGB none result_inceptionv3_thumos14_imagenet_rgb.npz --arch InceptionV3 --use_reference
4.>python eval_detection_results.py thumos14 result_inceptionv3_thumos14_imagenet_rgb.npz
should change somewhere else? wish your reply.
The text was updated successfully, but these errors were encountered: