-
Notifications
You must be signed in to change notification settings - Fork 110
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
I will be grateful if model visualization script is collected in a test file, I tried to reproduce the test results after training model but failed. #50
Comments
What's the error message? |
rendering_views = utils.binvox_visualizatino.get_volume_views(gv, os.path.join(img_dir), epoch_idx) should be changed to rendering_views = utils.binvox_visualization.get_volume_views(gv, os.path.join(img_dir), epoch_idx) |
Moreover, cfg.CONST.WEIGHTS = pretrained/Pix2Vox-A-ShapeNet.pth should be changed to cfg.CONST.WEIGHTS = 'pretrained/Pix2Vox-A-ShapeNet.pth' |
Try to use OpenCV instead of Pillow. Change img1_np = np.asarray(Image.open(img1_path)) to img1_np = cv2.imread(img1_path) I'm not sure whether it will help. Maybe the orders of RGB won't affect the final reconstruction result. |
There're TOO MANY TYPOS in your code. Please check it carefully before asking questions. Try to change raw_features, generated_volum = decoder(image_features) to raw_features, generated_volume = decoder(image_features) |
So,Can you provide the complete code for the single view test ?thx |
Greetings, |
how to reproduce results. how can we create a demo file to test trained models and visualize results. I tried to reproduce the test results from trained weights but failed.
@hzxie @kondela @aashishbohra10
Thank you in advance.
Originally posted by @ahmedshingaly in #28 (comment)
The text was updated successfully, but these errors were encountered: