ViS4mer

ViS4mer copied to clipboard

Hi! After reading your paper, I wonder how to use Transformer Encoder to encode each video frame in parallel?

wsasdsda

Hi, I have run this code on lvu dataset, but the output is nan during training. Could you please provide pretrained checkpoints on speaking task of lvu? thank you very...

pilibb0712

lvu_durations.csv

8

Hi authors, How are the durations in lvu_durations.csv computed? The last 20s in most videos show preview for other videos. Does lvu_durations.csv show the number of seconds in the video...

nbgundavarapu

Hi authors, I'm getting NaNs in the training loss in the first epoch itself. I've tried 3 different seeds on relationship task, and it resulted in NaNs each time. Is...

nbgundavarapu

ReduceLROnPlateau

1

ReduceLROnPlateau by default assumes a "min" metric (https://pytorch.org/docs/stable/generated/torch.optim.lr_scheduler.ReduceLROnPlateau.html) `mode ([str](https://docs.python.org/3/library/stdtypes.html#str)) – One of min, max. In min mode, lr will be reduced when the quantity monitored has stopped decreasing; in...

nbgundavarapu

Hi, I tried to train a model on the LVU dataset, but got acc about 0.25 and the loss is NAN，I want to know what else should I do ?thanks.

FancyL1999

Pre-trained model weights

4

Hi Will you publish any pre-trained model? Preferably in torchHub? I was thinking of using ViS4mer for extracting image embedding.

nahidalam

Hello, thank you for your excellent work. When I tried to download the dataset from the LVU official link, I found that they did not provide the raw video, and...

huaiyi66