-
Notifications
You must be signed in to change notification settings - Fork 501
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Training time #44
Comments
There is not many options. |
Hi, may I know how many layers for the CNN? And how can I check how many
layers? Thank you
…On Tue, 17 Jul 2018 at 5:58 PM, Yusuke Uchida ***@***.***> wrote:
There is not many options.
Use smaller training images, buy a good GPU machine, or try Google
Colaboratory with GPU.
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#44 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AnaCZYz2cGhlBxCZJedbxSfhYymorle9ks5uHbVZgaJpZM4VSUNg>
.
|
Depth of the model can be set in |
Okay. I take UTKFace as my training data, UTKFace consists only 20000++k
images, but when I train the model with 30 epoch, it take 1 and half days
for only run 2 epoch. Can I know what is the problem?
…On Mon, 23 Jul 2018 at 11:54 PM, Yusuke Uchida ***@***.***> wrote:
Depth of the model can be set in train.py by depth argument.
Default value is 16.
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#44 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AnaCZf6-nK5TkJd_6yiKhOAvREZTfANIks5uJfGlgaJpZM4VSUNg>
.
|
Did you train the model using CPU? |
I’m using laptop.
…On Tue, 24 Jul 2018 at 1:37 AM, Yusuke Uchida ***@***.***> wrote:
Did you train the model using CPU?
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#44 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AnaCZU31nohA_UGcnnK4YpdRcSxRD3wSks5uJgnngaJpZM4VSUNg>
.
|
Please train network using a machine with GPU as the first my comment. |
I have another question which is how can I get the age (value) and gender from the person who testing in front the webcam? I am doing Final year project, which I want get the data(age and gender) from them for doing some recommendation purpose based on their age and gender . |
Please carefully read |
I am new in python. I training the data from UTFFace, but it too very long time. Any method that can train the data in short time? Thank you.
The text was updated successfully, but these errors were encountered: