-
Notifications
You must be signed in to change notification settings - Fork 35
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
Load model with keras #9
Comments
Hi, there are implementations like this that may help. |
Mmmm I dont think so. The predicted mask is way different from the original mask. I just want to load U2NET.pth weights into keras model. The original weights |
I have been able to convert to a TensorFlow .pb saved model (using ONNX) if that helps, but currently I am unable to convert to Keras h5. I will try again when I get more time. |
Yeah same. From pth to onnx can be done. But I havent found a way to make it .h5. Btw, thanks for helping me with this |
No problem |
Yeah! I got that error complaining about upsampling layers. And sure, if you could share you will make me big favour ^^ Thank you very much dude |
I made this repository : U-2-Net-Keras. You can find both the Keras h5 saved model as well as the notebook I used to make it. With the code in the inference cell of the notebook, you should get the right results. |
Omg sorry I am derping. Im new here. How can I give u stars? |
There are buttons at the top of the page, (watch, star and fork), you can just click star |
I mean, probably your code works perfectly. I think i am just idiot. Could I add you to discord by chance? |
Oh I just noticed... You uploaded U2NETP... Could I ask for U2NET? |
For U2NET, you can just download the original weight file to the colab in the repo, then just change u2netp to u2net in the setup cell. Either way, I'll also upload the Keras h5 for it, probably tomorrow. |
Hi.
Is there anyway i can load this model using keras.models.load_model?
Pls i will really appreciate it
The text was updated successfully, but these errors were encountered: