Thomas Paul

The x and y coordinates in true_boxes are expressed relative to image dimensions in L256- `true_boxes[..., 0:2] = boxes_xy/input_shape[::-1] ` Then these values are used in L297- `y_true[l][b, j, i,...

Possible bug in using Batch normalisation

1

- `training` parameter is not given while initialising `tf.layers.batch_normalization`. The `training` parameter defaults to `False`. Hence while training the moving mean and moving variance won't be updated. - Since this...

Inference FPS of audio driven generation

1

Hi, Thank you for sharing your work. Can you share an approximate FPS that you got while generating video driven by audio? Thanks, Thomas.

Bug in projection

4

While I was analyzing the output of the code by taking a bird's eye view, I saw that it doesn't match the expected output. When I did projection separately in...

What is the FPS of this mehod?

3

Given a trained model, what is the FPS at inference time? Any leads are very much appreciated. Thank you.

Hello, Thank you for sharing this list. I'm new to this and it has helped me a lot. I want to generate a photo-realistic avatar of myself and connect with...

Is this method realtime?

1

How much time does it take to predict a frame? Can I use it for making a real time chatbot?

Hi team, Thank you for sharing this amazing work. Raising this issue to see if I could update python packages to the latest versions available. If you want to create...