Is annot generated by the function read_assignment? I'm not sure because I see line 242 is commented. I guess you might generate annot by this function then comment it when evaluating CrossTask, right?
Is the length of annot equal to the length of 2D feature? And is the video_3d downsampled via adaptive_max_pool1d to have the same length of video_2d for concatenation?
When evaluation, in the function get_recall in eval_cross.py, does setting args.recall_frame to 0 matter? It seems line 127 and line 129 do the same computation.
Yes, that is correct. We followed that from the author of CrossTask (_adaptive_maxpool1d is thus just an ugly hack to ensure that both arrays are of the same length.).
The default will be recall_frame==0, the arg_max_predict is used for another evaluation testing.
Yes, the args.mining about the evaluation on Mining YouTube dataset. Yes, we use cvpr19_predict in the end.
Hi, I met some questions about the CrossTask evaluation and beg your help.
https://github.com/brian7685/Multimodal-Clustering-Network/blob/808948b4007c47de82bb8e371277130e5b901cad/cvpr19_dataloader.py#L200 The quesionts are:
annot
generated by the functionread_assignment
? I'm not sure because I see line 242 is commented. I guess you might generateannot
by this function then comment it when evaluating CrossTask, right?annot
equal to the length of 2D feature? And is thevideo_3d
downsampled viaadaptive_max_pool1d
to have the same length ofvideo_2d
for concatenation?get_recall
ineval_cross.py
, does setting args.recall_frame to 0 matter? It seems line 127 and line 129 do the same computation.cvpr19_predict
andarg_max_predict
? https://github.com/brian7685/Multimodal-Clustering-Network/blob/808948b4007c47de82bb8e371277130e5b901cad/eval_cross.py#L232-L243Sorry to bother you. Thanks for your patience and help in advance!