-
Hello,
What is the best way to continue training of an epoch from a saved checkpoint of previous epoch?
Thank you
-
Hi, thank you for sharing this interesting work!
I would like to try fine-tuining ClipBERT on other video-and-language dataset, such as YouCook2.
My target downstream task is cross-modal retrieval…
-
Hi,
Thanks for the nice work.
I am trying to replicate the experiments and observed the following as result on the text-video retrieval task with MSR-VTT dataset
```
{'text2video': {'r1': 21…
-
Hi,
I really appreciate your excellent work! I tried to train on NExT-QA, but first I found that it doesn't have qns _bert file for the test.
And one more thing, when I shift to NExT-QA and chan…
-
Hi,
TypeError: Can't instantiate abstract class MixDataset with abstract methods configure_train_test_splits, load_features, sanity_checks.
The TypeError show up when I run `python -m train --confi…
-
Hi,
Thank you very much for your great code. May I ask if you would provide the extracted and pre-processed features (the .npz files) for datasets such as COCO, VCR, MSVTT?
Thank you very much!
-
wget http://pascal.inrialpes.fr/data2/vgabeur/video-features/MSRVTT.tar.gz
wget http://pascal.inrialpes.fr/data2/vgabeur/video-features/activity-net.tar.gz
wget http://pascal.inrialpes.fr/data2/vgab…
-
Dear author,
I want to reproduce your paper results. I run the pre-training.sh, but the msrvtt zero-shot rank@1 only 10.7 not matched your result 22.2. Could you please share your pre-training log. …
-
Dear Author,
I hope almost done with running your framework, and It should be last question from me,
I saw some successful step to run, but I found that any log is written in log.txt.
(By th…
-
为啥训练集train_ans2label 有1500个，测试集answer 有5000个，而且不在train_ans2label里面。这样怎么分类啊