PointGAN (90%)

ubuntu 18, python3.6.7

1. ์„ค์น˜

$ sudo apt-get install python3-opencv python3-tk
$ pip3 install http://download.pytorch.org/whl/cu80/torch-0.1.11.post5-cp27-none-linux_x86_64.whl 
$ pip3 install torchvision progressbar2


$ cd ~
$ git clone https://github.com/fxia22/pointGAN.git
$ cd pointGAN

$ bash build.sh #build C++ code for visualization
$ bash download.sh #download dataset

2. ๋ชจ๋ธ ์ƒ์„ฑ

$ python3 show_gan.py --model gan/modelG_10.pth # choose your own model

ํ•„์š”์‹œ ์ฃผ์„ ์ฒ˜๋ฆฌ print('[%d: %d/%d] train lossD: %f lossG: %f' %(epoch, i, num_batch, lossD.data[0], lossG.data[0]))

3. ๋ฐ์ดํ„ฐ ์ƒ์„ฑ

python3 show_gan.py --model gan/modelG_3.pth

ํ•„์š”์‹œ ์ˆ˜์ • gen = PointGen(num_points = 2500)

4. ์‚ฌ์šฉ์ž ํ•™์Šต ๋ฐ์ดํ„ฐ ํ™œ์šฉ

  1. synsetoffset2category.txt์— ํณ๋”๋ช…, Label๋ช… ์ถ”๊ฐ€ eg. 7777, human

  2. train_gan.py์˜ class_choice ๋ฅผ label๋ช…์œผ๋กœ ์ˆ˜์ • eg. class_choice = ['human']

Last updated