Imran Akbar

What would the correct to/from frequencies be for resampling from 44100 Hz to 16000 Hz? How is the sample rate different from the frequency? I'm looking at this example code...

ace2p model does not support GPU inference

1

Paddle version: 2.3.0-gpu Hub version: 2.2.0 Ace2p version: 1.1.0 code: import paddlehub as hub human_parser = hub.Module(name="ace2p") result = human_parser.segmentation(images=[cv2.imread('file.png')], use_gpu=True) error: ACE2P object has no attribute 'gpu_predictor'

How can we donate money to help fund development of this project? thanks

output image resolution doesn't match input

1

It seems like the output image that's inferred is sometimes of lower resolution than the input. For example, my input was 1280x720, but the output is 768x432. It looks like...

Please add a sample showing how to run a Docker image as a task in Python. Thank you

where is recorderWorker.js?

2

The homepage states "Defaults to 'js/recorderjs/recorderWorker.js'" but I can't find recorderWorker.js anywhere. Where is it? thanks

inference with output of 512x512

9

Great work, thank you for publishing this. I was wondering how to get the high-resolution video outputs (512x512) that you include on the project page. Do I just need to...

training code

2

thanks for this great work - do you know when you plan to release the training code by?

Where can I find the config for running inference on vid2vid with faces? There doesn't seem to be anything [here](https://github.com/NVlabs/imaginaire/tree/master/configs/projects/vid2vid). thanks

Blinking?

7

Thanks for this great repo. I tried the colab, but the resulting video doesn’t blink. Is that controllable from the pose file? I see there’s control over the eyes in...