Comments (3)
chevalierNoir
commented on September 10, 2024
1
Hi, nshard and rank are used if you want to parallelize your processing. Suppose you want to detect facial landmark by running python detect_face.py ... --shard <nshard> --rank <rank>, then the the whole dataset will be divided into nshard parts and this particular job will detect facial landmark for rankth part.
If you are are on a cluster, then launch nshard jobs with rank argument of each job being set to 0, 1, ... nshard-1. If you are on a single machine and do not need parallelizing, simply putting nshard to 1 and rank to 0 will process all videos in one job.
from av_hubert.
18445864529
commented on September 10, 2024
Thank you for your explaination! Close this issue now.
from av_hubert.
PussyCat0700
commented on September 10, 2024
Hi,
nshardandrankare used if you want to parallelize your processing. Suppose you want to detect facial landmark by runningpython detect_face.py ... --shard <nshard> --rank <rank>, then the the whole dataset will be divided intonshardparts and this particular job will detect facial landmark forrankth part.If you are are on a cluster, then launch
nshardjobs withrankargument of each job being set to0, 1, ... nshard-1. If you are on a single machine and do not need parallelizing, simply puttingnshardto 1 andrankto 0 will process all videos in one job.
Great answer! That solves my problem again
from av_hubert.
Related Issues (20)
- How to get the ${nshard} value and ${rank} value? Are they random numbers? HOT 2
- Finetuning Models for Visual Speech Recognition HOT 8
- Checkpoints of finetuned AVSR models without VoxCeleb2 data? HOT 4
- How to align and fuse acoustic and visual features HOT 2
- Question on result of pretrain 433h and finetune 30h on LRS3 HOT 5
- FileNotFoundError HOT 2
- How to only perform test? HOT 2
- infer_s2s.py: Load dataset (possibly sharded) ??? HOT 2
- ImportError: cannot import name 'metrics' from 'fairseq' (unknown location) HOT 5
- preparation-cnn_face_detector HOT 1
- Question about the use of CMUDict in CTC finetuning HOT 3
- issue during 1st iteration of pretraining HOT 1
- How to train a LM used for decoding HOT 2
- Error in step 2 of preprocessing, what values to put in ${rank} and ${nshard} HOT 5
- non-deterministic results when decoding with noises HOT 5
- Fixing Colab
- How to finetune on AVSR setting? HOT 3
- What's the difference between A/MFCC→A and A/MFCC→AV in the paper? HOT 1
- Value expected for ${layer}-th transformer layer of a trained AV-HuBERT model saved at ${ckpt_path} HOT 1
- Format of pretrain data in the LRS3 dataset HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from av_hubert.