PointGAN (90%)
ubuntu 18, python3.6.7
1. ์ค์น
2. ๋ชจ๋ธ ์์ฑ
ํ์์ ์ฃผ์ ์ฒ๋ฆฌ
print('[%d: %d/%d] train lossD: %f lossG: %f' %(epoch, i, num_batch, lossD.data[0], lossG.data[0]))
3. ๋ฐ์ดํฐ ์์ฑ
ํ์์ ์์
gen = PointGen(num_points = 2500)
4. ์ฌ์ฉ์ ํ์ต ๋ฐ์ดํฐ ํ์ฉ
synsetoffset2category.txt์
ํณ๋๋ช , Label๋ช ์ถ๊ฐ
eg.7777
,human
train_gan.py
์class_choice
๋ฅผ label๋ช ์ผ๋ก ์์ eg.class_choice = ['human']
Last updated