Comments (16)
csaftoiu
commented on June 30, 2024
1
Ah thanks for that! Very helpful.
I managed to get it to train a few steps on some images of my own. However
I couldn’t load it into a net_type because the saved weights have the
affine layers while the net_type has batchnorm layers. Though I see it auto
converts from batchnorm to affine when saving, I wasn’t able to get it to
auto convert from affine to batchnorm to keep training. So I have been
training the anet_type directly.
Is there a way to retrieve the net_type from the saved weights on the repo?
Or are part of the batchnorm parameters lost when saving the model meaning
I can’t transfer learn it?
…On Thu, Oct 31, 2019 at 12:02 AM Davis E. King ***@***.***> wrote:
The notes on how this model was trained are in the example program that
shows how to use it: http://dlib.net/dnn_face_recognition_ex.cpp.html
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#11?email_source=notifications&email_token=AAAKQ2OQY3ISUSKPO7BLFTDQRIOC5A5CNFSM4GMJTZUKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOECWEUAY#issuecomment-548162051>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AAAKQ2IQAVDMXCVBUR3ZWQLQRIOC5ANCNFSM4GMJTZUA>
.
from dlib-models.
csaftoiu
commented on June 30, 2024
1
Is there any way to get the batch norm form of the model on the repo? Or is
this reserved for secret sauce not for public consumption? :). I understand
if it’s the latter.
If it’s not available I suppose we can’t transfer learn it as-is. If we
load weights and swap out the affine for a random batch norm it seems
that’d lose all the learning in first few steps. Best option seems to be to
keep the affine as-is. Let me know what you think.
On Thu, Oct 31, 2019 at 11:52 PM Davis E. King <[email protected]>
wrote:
… Some things are lost when converting from batch norm to affine. Save in
batch norm form when doing training.
On Thu, Oct 31, 2019 at 9:17 AM Claudiu ***@***.***> wrote:
> Ah thanks for that! Very helpful.
>
> I managed to get it to train a few steps on some images of my own.
However
> I couldn’t load it into a net_type because the saved weights have the
> affine layers while the net_type has batchnorm layers. Though I see it
auto
> converts from batchnorm to affine when saving, I wasn’t able to get it to
> auto convert from affine to batchnorm to keep training. So I have been
> training the anet_type directly.
>
> Is there a way to retrieve the net_type from the saved weights on the
repo?
> Or are part of the batchnorm parameters lost when saving the model
meaning
> I can’t transfer learn it?
>
> On Thu, Oct 31, 2019 at 12:02 AM Davis E. King ***@***.***
>
> wrote:
>
> > The notes on how this model was trained are in the example program that
> > shows how to use it: http://dlib.net/dnn_face_recognition_ex.cpp.html
> >
> > —
> > You are receiving this because you commented.
> > Reply to this email directly, view it on GitHub
> > <
>
#11?email_source=notifications&email_token=AAAKQ2OQY3ISUSKPO7BLFTDQRIOC5A5CNFSM4GMJTZUKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOECWEUAY#issuecomment-548162051
> >,
> > or unsubscribe
> > <
>
https://github.com/notifications/unsubscribe-auth/AAAKQ2IQAVDMXCVBUR3ZWQLQRIOC5ANCNFSM4GMJTZUA
> >
> > .
> >
>
> —
> You are receiving this because you were mentioned.
> Reply to this email directly, view it on GitHub
> <
#11?email_source=notifications&email_token=ABPYFR6IRGWI4PNRKTODKX3QRLLFRA5CNFSM4GMJTZUKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOECXXJLI#issuecomment-548369581
>,
> or unsubscribe
> <
https://github.com/notifications/unsubscribe-auth/ABPYFR3L2HVRKDUDMGM23LLQRLLFRANCNFSM4GMJTZUA
>
> .
>
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#11?email_source=notifications&email_token=AAAKQ2OIPL4XCVLKHUDYJTLQRNVVVA5CNFSM4GMJTZUKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOECZS6HQ#issuecomment-548613918>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AAAKQ2OEDSXHAB65ZNDRVT3QRNVVVANCNFSM4GMJTZUA>
.
from dlib-models.
nicolaerosia
commented on June 30, 2024
@davisking I'm also interested if you're willing to release the dataset. In any case, I understand that it involved a lot of work.
from dlib-models.
davisking
commented on June 30, 2024
You can use the trillion faces or ms celeb datasets. They are already available and very large.
from dlib-models.
pdstanley
commented on June 30, 2024
Davis, is there a python API for training your own model? Thank you, sir! Dlib is amazing.
from dlib-models.
davisking
commented on June 30, 2024
No
from dlib-models.
shenjackson
commented on June 30, 2024
@davisking , I don't know how to train my dlib_face_recognition_resnet_model_v1 model, can you give me some methods!
from dlib-models.
davisking
commented on June 30, 2024
This example program goes into the details: http://dlib.net/dnn_metric_learning_on_images_ex.cpp.html
from dlib-models.
csaftoiu
commented on June 30, 2024
@davisking Just to be sure, is that C++ code the one used to train this model? I'd like to transfer learn on my own dataset and want to be sure I'm starting from the right place
from dlib-models.
csaftoiu
commented on June 30, 2024
Also we’re rhe input images aligned centered cropped etc or just resized to 150x150 with a crop from a face finding model? Also be helpful to know this just in terms of using the base model - I see the sample code that uses it does this so I presume it was trained that way As well
from dlib-models.
davisking
commented on June 30, 2024
The notes on how this model was trained are in the example program that shows how to use it: http://dlib.net/dnn_face_recognition_ex.cpp.html
from dlib-models.
davisking
commented on June 30, 2024
Some things are lost when converting from batch norm to affine. Save in
batch norm form when doing training.
…On Thu, Oct 31, 2019 at 9:17 AM Claudiu ***@***.***> wrote:
Ah thanks for that! Very helpful.
I managed to get it to train a few steps on some images of my own. However
I couldn’t load it into a net_type because the saved weights have the
affine layers while the net_type has batchnorm layers. Though I see it auto
converts from batchnorm to affine when saving, I wasn’t able to get it to
auto convert from affine to batchnorm to keep training. So I have been
training the anet_type directly.
Is there a way to retrieve the net_type from the saved weights on the repo?
Or are part of the batchnorm parameters lost when saving the model meaning
I can’t transfer learn it?
On Thu, Oct 31, 2019 at 12:02 AM Davis E. King ***@***.***>
wrote:
> The notes on how this model was trained are in the example program that
> shows how to use it: http://dlib.net/dnn_face_recognition_ex.cpp.html
>
> —
> You are receiving this because you commented.
> Reply to this email directly, view it on GitHub
> <
#11?email_source=notifications&email_token=AAAKQ2OQY3ISUSKPO7BLFTDQRIOC5A5CNFSM4GMJTZUKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOECWEUAY#issuecomment-548162051
>,
> or unsubscribe
> <
https://github.com/notifications/unsubscribe-auth/AAAKQ2IQAVDMXCVBUR3ZWQLQRIOC5ANCNFSM4GMJTZUA
>
> .
>
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#11?email_source=notifications&email_token=ABPYFR6IRGWI4PNRKTODKX3QRLLFRA5CNFSM4GMJTZUKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOECXXJLI#issuecomment-548369581>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/ABPYFR3L2HVRKDUDMGM23LLQRLLFRANCNFSM4GMJTZUA>
.
from dlib-models.
davisking
commented on June 30, 2024
You could copy the layer parameters into a network with batch norm layers and go in and manually fill in the missing batch norm parameters with something reasonable.
from dlib-models.
ismailpolas
commented on June 30, 2024
Does anyone build the dlib_face_recognition_resnet_model_v1.dat with custom dataset? If Yes, Please share the method. Thanks in Advance.
from dlib-models.
davisking
commented on June 30, 2024
http://dlib.net/dnn_face_recognition_ex.cpp.html and
http://dlib.net/dnn_metric_learning_on_images_ex.cpp.html explain all that.
…On Wed, Sep 9, 2020 at 6:06 AM ismailpolas ***@***.***> wrote:
Does anyone build the dlib_face_recognition_resnet_model_v1.dat with
custom dataset? If Yes, Please share the method. Thanks in Advance.
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#11 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/ABPYFRZ4RB3SAR3D2ZM6KPDSE5HRNANCNFSM4GMJTZUA>
.
from dlib-models.
aishaandatt
commented on June 30, 2024
I tried Loading a custom dataset and successfully made the resnet .dat file but I'm getting this error. ERROR: Unexpected version found while deserializing dlib::input_rgb_image_sized. Please refer to the issue link given below for more detials on this error.
davisking/dlib#2598
from dlib-models.
Related Issues (20)
- How to reduce size of the model? HOT 1
- Would you be interested in a pretrainted ResNet50? HOT 3
- Trained HOG detector, but variation(jitter and shake) in bounding box output result.
- Computer specs required when training HOT 2
- Need more tuning of mmod_face_detector.dat's parameters
- How to train gender model? HOT 7
- Any trained model for ID card shape detector? HOT 2
- Details regarding mmod_human_face_detector HOT 3
- body pose model? HOT 4
- How to use dnn_gender_classifier_v1.dat in Python? HOT 4
- GPU Accerlation For Age Estimation HOT 2
- dlib_face_recognition_resnet_model_v1.dat dataset HOT 1
- Verification rate of face recognition model HOT 1
- 98 face landmarks
- How to config shape_predictor_68_face_landmarks.dat to use GPU HOT 1
- Details about training dnn_age_predictor_v1.dat.bz2 HOT 5
- how to get dlib_face_live_detector_v1.dat
- Is it possible to convert shape_predictor_68_face_landmarks dlib model to an onnx model? HOT 1
- Decrease in recognition rate HOT 2
- I would like to introduce the facial recognition model I trained, which includes a large number of Asian faces. HOT 2
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 dlib-models.