ronghui19

A question about text and image encoding

1

1. when train the GAN, i did not see text encoding process. you store text in sample. ` right_images = sample['right_images'] right_embed = sample['right_embed'] wrong_images = sample['wrong_images'] right_images = Variable(right_images.float()).cuda()...

what does it look like? any example?

Question about how to generate systhesis dataset

2

import numpy as np import matplotlib.pyplot as plt import cv2 def create_grid(width=100, height=100): mr = width mc = height xx = np.arange(mr-1, -1, -1) yy = np.arange(0, mc, 1) [Y,...

how to prepare assert for generate my own dataset?

2

I successfully ran through the code. For now, i want to generate my own dataset. Can anyone guide me through about how to prepare asset. Like how to generate mesh,...

Have a look at this. It may inspire you. https://github.com/oulutan/ACAM_Demo

if i want to test the model on real video, how should i do?

1

I completed the training. Now i want to test it on real video. It seems i need to extract feature from video. But there is no such script that can...