Closed 77QIQI closed 7 years ago
I am also curious how man can change the window size. Some action happens fast, especially in sport, so a 32-frame-window is still too large.
Following conventional settings, I sample frames at around 25~30 FPS during frame extraction so that most of video samples are longer than 1s and thus has at least one window. For these video samples happen to be shorter than 1 window, I guess it won't affect results significantly. If you still concern, probably can pad with blank frames.
Hi, @77QIQI I am sorry to trouble you. How to prepare your own training data? Do you have background or ambigious classes? Thank you very much!
@buaa-luzhi I am sorry to reply now. I didn't succeed to train with a right results. So I am sorry that I can't help you.
Hi Mr. Shou,
I have some following questions during the process of training:
Thanks in advance.
==================================================================
Step1 Prepare pre-trained model
cd THUMOS14/training/init/ sh run_net_surgey_sports1m_convdeconv.sh
Step2 prepare your own training data
exact frames from UCF101 (25 fps) generate the bin files and the list file for the test set with gen_test_bin_and_list.py as following:
Step3 train
sh finetuning.sh and get the convdeconv-TH14_iter_24390 in the folder /snapshot