OPN Model testing
anasgit opened this issue · comments
Hi @HsinYingLee , I would like to thank you for the tutorial.
I have a question about applying an already trained model (Unsupervised trained on UCF) or (Unsupervised trained on UCF+HMDB+ACT) on an external video in order to re-sort its frames sequence using:
$ python visualize.py $MODEL $OUTPUT_FIG
so how can define the video sequence directory?
what does "$OUTPUT_FIG" represent?
Thanking you in advance.
Hi,
The file "visualize.py" is used for visualizing conv1 filter, not for
performing sorting on frames. The code for ordering frames should not be
difficult either using datalayers or explicitly feeding images in.
Thank you.
Best,
James
2018-07-09 14:49 GMT-07:00 anasgit <notifications@github.com>:
… Hi, I would like to thank you for the tutorial.
I have a question about applying an already trained model (Unsupervised
trained on UCF) or (Unsupervised trained on UCF+HMDB+ACT) on an external
video in order to re-sort its frames sequence using:
$ python visualize.py $MODEL $OUTPUT_FIG
so how can define the video sequence directory?
what does "$OUTPUT_FIG" represent?
Thanking you in advance.
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
<#5>, or mute the thread
<https://github.com/notifications/unsubscribe-auth/ANlWwDC2Pjv0ka-P_YYkSzlOMjZAiSN9ks5uE8_TgaJpZM4VIcNf>
.
Thank you for reply.
Okey, how many frames can I re-order for each forward? In other-words, the number of input/output frames each time?
Many thanks,