microsoft UniVL issues - Githubissues

microsoft / UniVL

An official implementation for " UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation"

https://arxiv.org/abs/2002.06353

MIT License

339 stars 54 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Bump torch from 1.7.0 to 2.2.0

#48 dependabot[bot] opened 4 months ago
0
Non-Configurable GPU Count via Arguments

#47 willyfh opened 9 months ago
0
Zero score (every output is None) on evaluation captioning with pretrained model

#46 Borntowarn opened 1 year ago
1
Estimate of zero-shot performance

#45 bpiyush opened 2 years ago
1
Error message (torch.distributed.elastic.multiprocessing.errors.ChildFailedError:)

#44 tingchihc closed 2 years ago
0
Issues about Freezing some additional layers instead of meanP in CLIP4Clip

#43 celestialxevermore closed 2 years ago
2
CVE-2007-4559 Patch

#42 TrellixVulnTeam opened 2 years ago
1
Is there a code for Finetune on CMU-MOSI here?

#41 sen0902 opened 2 years ago
1
How to only input text feature or video feature

#40 tingchihc opened 2 years ago
2
video only test for youcook

#39 mhyeonsoo closed 2 years ago
2
How can I create my video feature pickle

#38 tingchihc closed 2 years ago
4
feature & data shape

#37 mhyeonsoo closed 2 years ago
6
end-to-end video file captioning process

#36 mhyeonsoo closed 2 years ago
3
where to get transcript to generate youcookii_data.pickle

#35 zhaoying9105 opened 2 years ago
2
Unable to run video captioning code

#34 Davidyao99 opened 2 years ago
3
This repo is missing important files

#33 microsoft-github-policy-service[bot] closed 1 year ago
1
Adding Microsoft SECURITY.MD

#32 microsoft-github-policy-service[bot] closed 1 year ago
0
Change in metrics code to convert list of x to np array

#31 sagarsj42 opened 2 years ago
0
Can you share your HowTo100M.csv file?

#30 ShinJQ opened 2 years ago
3
Pre-training acceleration using multi-machine distributed training

#29 mingtan2 closed 2 years ago
1
How to run captioning task on my own video datasets?

#28 Kevinkaiyan opened 2 years ago
1
TypeError: bad operand type for unary -: 'list'

#27 jxrloveyou opened 2 years ago
6
Run Without Distributed

#26 Maddy12 opened 2 years ago
3
How to fine-tune with additional layers before UniVL?

#25 CrystalSixone closed 2 years ago
2
Questions on retrieval result and "Info: Weight doesn't exsits"

#24 HenryHZY closed 2 years ago
4
What's mean of the 'step_size=5' in modeling.py

#23 saicoco closed 3 years ago
2
CrossTask and COIN dataset code

#22 TXH-mercury closed 3 years ago
1
Joint loss in pretraining

#21 zhangliang-04 opened 3 years ago
1
How does the visual token come from?

#20 renmada closed 3 years ago
1
About auto mixed precision training

#19 zhangliang-04 closed 3 years ago
1
Hyper-parameter in pretraining

#18 zhangliang-04 closed 3 years ago
2
About msrvtt retrieval results

#17 zhangliang-04 closed 3 years ago
1
Captioning task clarification: video vs. video+text for captioning task

#16 tchang1997 closed 3 years ago
2
The bert univl using is very different from Huggingfaces' (or pytorch's) bert

#15 butterluo closed 3 years ago
0
What's the role of the parameter coef_lr?

#14 forence closed 3 years ago
1
About multi-gpu loss calculation

#13 forence closed 3 years ago
10
The program hangs when runs into parallel_apply() function in util.py

#12 butterluo closed 3 years ago
7
caption using features extracted from my raw video

#11 dawnlh closed 3 years ago
6
caption my own video with provided pretrained model

#10 dawnlh closed 3 years ago
8
How should I set the value in youcookii_videos_features.pickle when fine-tuning with single transcript as input?

#9 lokeaichirou closed 3 years ago
2
Why is the fine-tuning performance much lower than benchmark in paper?

#8 lokeaichirou closed 3 years ago
8
Is the provided weights based on the pre-trained work on Howto100M dataset?

#7 lokeaichirou closed 3 years ago
2
RuntimeError: Default process group has not been initialized, please make sure to call init_process_group.

#6 lokeaichirou closed 3 years ago
3
Weights from pretrained model not used in UniVL in evaluation. In EVALUATION, there is lack of visual_pytorch_model.bin, cross_pytorch_model.bin, decoder_pytorch_model.bin in visual-base, cross-base , decoder-base

#5 lokeaichirou closed 3 years ago
12
CLip

#4 johnbager closed 3 years ago
1
When will you release the code of 'Action Step Localization' and 'Action Segmentation' tasks?

#3 butterluo closed 3 years ago
1
When will you release the pre-trained model？

#2 menggehe closed 3 years ago
1
Expected data format?

#1 mckinziebrandon closed 3 years ago
3