Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / facebookresearch/LaViLa issues and pull requests
#43 - LaViLa Third-person Video Pre-training Model
Issue -
State: open - Opened by geanrobotics 2 months ago
#41 - About the requirement of GPU RAMs size
Issue -
State: closed - Opened by Oshikaka 4 months ago
#40 - the output of sentence is not complete
Issue -
State: open - Opened by zhaishengfu 5 months ago
- 1 comment
#39 - the meaning of demo_narrator.py?
Issue -
State: open - Opened by zhaishengfu 5 months ago
#38 - How to get text caption for each frame of video?
Issue -
State: open - Opened by zhaishengfu 5 months ago
#37 - About Ego4d dataset
Issue -
State: closed - Opened by lwpyh 8 months ago
- 2 comments
#37 - About Ego4d dataset
Issue -
State: closed - Opened by lwpyh 8 months ago
- 2 comments
#36 - Checkpoint of the pre-trained dual-encoder.
Issue -
State: open - Opened by AlbertHuyb 9 months ago
- 1 comment
#36 - Checkpoint of the pre-trained dual-encoder.
Issue -
State: open - Opened by AlbertHuyb 9 months ago
- 1 comment
#35 - What is the source of WIT video dataset?
Issue -
State: open - Opened by rixejzvdl649 9 months ago
- 3 comments
#35 - What is the source of WIT video dataset?
Issue -
State: open - Opened by rixejzvdl649 9 months ago
- 3 comments
#34 - val .pkl files for pre-training LAVILA Dual-Encoder
Issue -
State: closed - Opened by AlbertHuyb 10 months ago
- 2 comments
#34 - val .pkl files for pre-training LAVILA Dual-Encoder
Issue -
State: closed - Opened by AlbertHuyb 10 months ago
- 2 comments
#33 - Base narrator model
Issue -
State: closed - Opened by sarisel 11 months ago
#32 - May be repeatedly loade the checkpoints.
Issue -
State: closed - Opened by yyvhang 12 months ago
- 1 comment
#31 - Cannot use Huggingface demo
Issue -
State: open - Opened by fgvfgfg564 12 months ago
#30 - EGTEA reproduce
Issue -
State: open - Opened by jong980812 about 1 year ago
- 1 comment
#29 - Run locally on multiple GPUs
Issue -
State: open - Opened by maximotus about 1 year ago
- 3 comments
#28 - if the model supports Chinese language prompts or narrations?
Issue -
State: open - Opened by ruifenggong about 1 year ago
- 1 comment
#27 - Extracting spatial feature maps from LaViLa
Issue -
State: open - Opened by vineetparikh over 1 year ago
#26 - helper script to convert egovlp checkpoint
Pull Request -
State: closed - Opened by zhaoyue-zephyrus over 1 year ago
Labels: CLA Signed
#25 - add ego4d pre-processing script
Pull Request -
State: closed - Opened by zhaoyue-zephyrus over 1 year ago
Labels: CLA Signed
#24 - Preprocessing of Ego4D for pretraining
Issue -
State: closed - Opened by chuyishang over 1 year ago
- 2 comments
#23 - Training/fine-tuning the narrator
Issue -
State: open - Opened by tobyperrett over 1 year ago
- 2 comments
#22 - LaViLa as feature extractor
Issue -
State: open - Opened by deepsurbhi8 over 1 year ago
- 3 comments
#21 - The pre-training weights of Dual-Encoder Baseline (with TSF-B/L)
Issue -
State: closed - Opened by daiguangzhao over 1 year ago
- 1 comment
#20 - The pre-training weights of Dual-Encoder Baseline (with TSF-B/L)
Issue -
State: closed - Opened by daiguangzhao over 1 year ago
- 2 comments
#19 - Currently unable to run the demo between Colab and Huggingface.
Issue -
State: open - Opened by kuangxiaoye over 1 year ago
- 3 comments
#18 - The pretraining weights of TSF-B/L (visual only) on EPIC-KITCHENS-100 and EGTEA.
Issue -
State: closed - Opened by daiguangzhao over 1 year ago
- 1 comment
#17 - About the demo
Issue -
State: closed - Opened by aa7784171 over 1 year ago
- 1 comment
#16 - Question about preprocessing Ego4D
Issue -
State: closed - Opened by hyojinie almost 2 years ago
- 2 comments
#15 - Normalization values for CLIP models
Issue -
State: closed - Opened by Jazzcharles almost 2 years ago
- 1 comment
#14 - Updated `transformers` version and updated import path
Pull Request -
State: closed - Opened by gzhihongwei almost 2 years ago
- 1 comment
Labels: CLA Signed
#13 - Pretrained weight of HowTo100M
Issue -
State: open - Opened by HYUNJS almost 2 years ago
- 3 comments
#12 - Narrator Training
Issue -
State: closed - Opened by Flaick almost 2 years ago
- 2 comments
#11 - Reproducing zero-shot eval results on EK100-MIR
Issue -
State: open - Opened by melongua almost 2 years ago
- 1 comment
#10 - fix #4 potential seg. fault in demo
Pull Request -
State: closed - Opened by zhaoyue-zephyrus almost 2 years ago
Labels: CLA Signed
#9 - Train LAVILA (L) to perform action recognition on the EPIC-100 dataset?
Issue -
State: open - Opened by daiguangzhao almost 2 years ago
- 1 comment
#8 - Thank you for contributing such excellent work!
Issue -
State: closed - Opened by daiguangzhao almost 2 years ago
- 1 comment
#7 - Resized Version of EK100
Issue -
State: closed - Opened by SJTUwxz about 2 years ago
- 3 comments
#6 - Update PRETRAIN.md
Pull Request -
State: closed - Opened by zhaoyue-zephyrus about 2 years ago
- 1 comment
Labels: CLA Signed
#5 - Training narrations for downloading
Issue -
State: closed - Opened by melongua about 2 years ago
- 1 comment
#4 - Segmentation fault when launching demo_narrator [was: Keys remapping seems not to work]
Issue -
State: closed - Opened by amessina71 about 2 years ago
- 9 comments
#3 - Training Time
Issue -
State: closed - Opened by mmaaz60 about 2 years ago
- 2 comments
#2 - Git clone failing in Colab
Issue -
State: closed - Opened by nateraw about 2 years ago
- 1 comment
#1 - Add models/demo to Hugging Face Hub
Issue -
State: open - Opened by nateraw about 2 years ago
- 4 comments