-
Hi,
Thanks for sharing the code.
I'm getting NaN loss on the first epoch, and also although I have 8 gpus only 4 seem to be used.
-
The code generates h5 files for which each video has some wierd keys (corresponding to their urls like "HzYtvOYOEoU_21_32"). But SAAT expects keys to be of integer form like 0, 1, 2 and so on.
The e…
-
Thanks for sharing this project!!
But after I run the following command, I met into a segmentation fault (core dumped) error:
` wget http://pascal.inrialpes.fr/data2/vgabeur/video-features/MSRVTT.t…
-
-
Hello,
Thank you so much for sharing your code and pretrained models. I was trying to replicate your text-video retrieval results on the MSR-VTT dataset. I obtained the pretrained model from here -…
-
Could you provide configs of different data sets, which will make it easier to reproduce the results.
-
Thanks for your released code!
I am new to "text-video retrieval" task, and wonder why the retrieval result of ClipBERT is much lower than that in paper "Support-set bottlenecks for video-text rep…
-
1. msrvtt_roi_feat.h5
2. msrvtt_roi_box.h5
this two h5 files have 10000 datasets respectively。
you just have 6513 videos ,but why you have 10000 datasets each file ?
what is the meaning of each …
-
I want to know how to make lables_svo in msrvtt_train_sequencelabel.h5 so that I can preprocess the data on my own.
In your paper, this is produced by using nltk. Could you give me more details?
-
When I run to train the dataset, the following error occurred:
![Snipaste_2020-10-22_10-59-26](https://user-images.githubusercontent.com/56346294/96819209-aa7c9880-1455-11eb-983f-c728a0e487d8.png)
…