How can I train the network using my own datasets?

[ReedZyd]

I used your model file, but got an error of about 8-10 years old. I want to re-use the data set for training. What should I do?

[YOKE]

Thanks for your work! Could you share the script of train/val? @siriusdemon

[siriusdemon]

Refer to its Home Page , you can find the dataset and train/val prototxt. @ReedZyd @YOKE

I used your model file, but got an error of about 8-10 years old. I want to re-use the data set for training. What should I do?

For your problem, you can follow the origin paper: crop the face firstly, then apply the dex network to the cropped face.

[cliobeach]

do you have the code for the hole project? including face cropping and training.

[siriusdemon]

Nope.

For face cropping, you can use PCN or facessh or any other face detector you can find. PCN has already provided a face cropping function.

For face training, you can refer to Home Page for more details.

[cliobeach]

thanks, i will try later

---Original--- From: "Sirius Demon"[email protected] Date: Thu, Jun 27, 2019 11:14 AM To: "siriusdemon/pytorch-DEX"[email protected]; Cc: "cliobeach"[email protected];"Comment"[email protected]; Subject: Re: [siriusdemon/pytorch-DEX] How can I train the network using my own datasets? (#2)

No yeah.

For face cropping, you can use PCN or facessh or any other face detector you can find. PCN has already provided a face cropping function.

For face training, you can refer to Home Page for more details.

— You are receiving this because you commented. Reply to this email directly, view it on GitHub, or mute the thread.

[cliobeach]

thanks，i will try later。

---Original--- From: "Sirius Demon"[email protected] Date: Thu, Jun 27, 2019 11:14 AM To: "siriusdemon/pytorch-DEX"[email protected]; Cc: "cliobeach"[email protected];"Comment"[email protected]; Subject: Re: [siriusdemon/pytorch-DEX] How can I train the network using my own datasets? (#2)

No yeah.

For face cropping, you can use PCN or facessh or any other face detector you can find. PCN has already provided a face cropping function.

For face training, you can refer to Home Page for more details.

— You are receiving this because you commented. Reply to this email directly, view it on GitHub, or mute the thread.