• face_recognition version: latest docs
• Python version: N/A
• Operating System: N/A

Description

the docs say that default value for 'model' is "large". in fact, it is "small", which makes a different. please correct the docs

Dears,

if somebody has instructions , my target is to recognize a face using tensor flow but I didn't find a full instructions which scripts to use to do the following :
1- crop faces
2- Train images .
3- face recognition.

if examples or sample commands that would be appreciated!

I have Ubuntu Linux with python and tensor flow environment ready.

appreciate your steps to go forward

I've ran into this issue for a couple hours and I ended up editing the dist library adding two new functions called fetchVideo and bufferToVideo that works pretty much like the fetchImage and bufferToImage functions.

I'll leave it here to help somebody else with the same issue and in case someone wants to include it on future releases.

face-api.js

...
exports.fetchVideo = fetc

From the documentation(https://scikit-image.org/docs/dev/api/skimage.transform.html#skimage.transform.SimilarityTransform), I notice that the order given to estimate is swapped.

https://github.com/deepinsight/insightface/blob/4a4b8d03fec981912fdef5b3232a37a827cbeed6/src/common/face_preprocess.py#L61-L72

Is there any reason to swap the dst and src? Is that a mistake? If it's intended, it wou

Describe the bug
Now, when we compile milvus, there still have lots of warning. Eliminating those errors are necessary.

As 'User 1' I have 3 people in my facial recognition.
When I log in as 'User 2' I also see 3 people, but I haven't even scanned the folder yet.
Seems like a bug! ;-)

Since all comments in the python scripts are written in chinese, I wonder if one could improve the docs for this tool. How do you start it? What parameters and options are available?

I made a video tutorial on Ubuntu here: https://youtu.be/bZvHaEiP81Y
It can be added to README. I can make one for Arch too but I guess Arch users don't need video tutorials :)

Issues should contain the following details which increases the probability of it get resolved quickly

• Exact error or Issue details
• OpenCV Version
• Python Version
• Operating System
• Changes done, if any in the original code