Open fanw52 opened 6 years ago
On Apr 16, 2018, at 07:06, kstys notifications@github.com<mailto:notifications@github.com> wrote:
hi, I find a question,but I am not sure whether is right or not. in the code :activitynet_log_analysis.py
left_frame = float(l.split()[1])stride + start_frame right_frame = float(l.split()[2])stride + start_frame
and then i change the code to :
left_frame = float(l.split()[0].split('[')[-1])*stride + start_frame
right_frame = float(l.split()[1])*stride + start_frame
and then,it works ,or it will come across some error ,and I hope you can check it.
The origin one is correct, since there is a white space between bracket and number.
[[ 19.049221 65.19444 0.1244299]]
otherwise, there still another question:
activity: 80 [[19.049221 65.19444 0.1244299]] activity: 115 [[9.4955711e+00 7.9366196e+01 6.5591358e-02]]
what's the meaning of the three parameters??
[[ left_frame right_frame score]]
thanks for your attention.
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHubhttps://github.com/VisionLearningGroup/R-C3D/issues/24, or mute the threadhttps://github.com/notifications/unsubscribe-auth/AFOa_2XM1X13A220337--BpME4RLLg5fks5tpHs4gaJpZM4TWUHH.
I have met the same problem, and i donnot know why the log file have this format : [[9.4955711e+00 7.9366196e+01 6.5591358e-02]] ? But there should be [[ 9.4955711e+00 7.9366196e+01 6.5591358e-02]] , what has caused this problem ? i have no idea, have you solved this problem?(The first time i got the true format of this log file like [[ left_frame right_frame score]], but this time i got log file like[[left_frame right_frame score]] , this format can not be analysis by the code of analysis_log.py because of the false format) Thanks for your reply!
hi @kstys @wangwen39
I am new for action detection and very interested in this field. I use the test script R-C3D/experiments/activitynet/test_net.py to do the test. I am using a card of 1080Ti with 11G memory, but 2.5G was used by other students, so I was only left with 8.5G memory with GPU. But when I run the test_net.py script in ActivityNet , only loaded one 1 video's frams(768 images), but out of memory at the step: blobs_out = net.forward(forward_kwargs) """ F0713 15:08:15.452706 22317 syncedmem.cpp:56] Check failed: error == cudaSuccess (2 vs. 0) out of memory ** Check failure stack trace: Aborted (core dumped) """
so could you plz tell me what is your GPU type and how many GPUs have you used when testing and training this code? Thanks in advance!
@wangwen39 Have you solved your problem? I have the same issue: some of the matrixs are in this format: [[9.4955711e+00 7.9366196e+01 6.5591358e-02]], and some of them have "space" between number and '[[', I cannot figure out the reason for that.
It’s because of the python version. You can change the parsing code in the log analysis code.
On Aug 30, 2018, at 03:02, ivyvideo notifications@github.com<mailto:notifications@github.com> wrote:
@wangwen39https://github.com/wangwen39 Have you solved your problem? I have the same issue: some of the matrixs are in this format: [[9.4955711e+00 7.9366196e+01 6.5591358e-02]], and some of them have "space" between number and '[[', I cannot figure out the reason for that.
— You are receiving this because you commented. Reply to this email directly, view it on GitHubhttps://github.com/VisionLearningGroup/R-C3D/issues/24#issuecomment-417211682, or mute the threadhttps://github.com/notifications/unsubscribe-auth/AFOa_1hkyWwQbpeMZx2xsbLPPl-19Yz9ks5uV44PgaJpZM4TWUHH.
I think it is because when printing a matrix in python, the numbers should be aligned in the direction of a column as follows. So once you save the results in log file, the space between '[[' and the number would also be saved.
In order to tackle the problem, I add a postprocess to deal with the spaces...
hi, I find a question,but I am not sure whether is right or not. in the code :activitynet_log_analysis.py
and then i change the code to :