-
Notifications
You must be signed in to change notification settings - Fork 8
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
Model Prediction #3
Comments
you can just change the dataloader and train based on your own data. After that you can simply inference based on your teained model. |
So my problem is I cannot find model variable for using model.load_state_dict. How should I solve it ? |
Hi we have just updated the checkpoint on the Github |
Hi, Sorry for a bunch of questions.
For my understanding, Training with p256 will save the model in
Encoder_KD_ckpt, Am I right?
Thank tou
ในวันที่ พฤ. 9 มิ.ย. 2022 เวลา 13:58 Yu Tian ***@***.***>
เขียนว่า:
… So my problem is I cannot find model variable for using
model.load_state_dict. How should I solve it ?
Hi we have just updated the checkpoint on the Github
https://github.com/tianyu0207/IGD/blob/main/Encoder_KD_ckpt
—
Reply to this email directly, view it on GitHub
<#3 (comment)>, or
unsubscribe
<https://github.com/notifications/unsubscribe-auth/ARJ3SNZNVCVDHZUILAHLIT3VOGIXTANCNFSM5XJ6D7WQ>
.
You are receiving this because you authored the thread.Message ID:
***@***.***>
|
Is there an inference code for new test images? Thanks |
How to make a model's prediction on new images? Thanks
The text was updated successfully, but these errors were encountered: