|
import torch |
|
import argparse |
|
|
|
from nerf.provider import NeRFDataset |
|
from nerf.utils import * |
|
from optimizer import Shampoo |
|
|
|
from nerf.gui import NeRFGUI |
|
|
|
|
|
|
|
if __name__ == '__main__': |
|
|
|
parser = argparse.ArgumentParser() |
|
parser.add_argument('--text', default=None, help="text prompt") |
|
parser.add_argument('-O', action='store_true', help="equals --fp16 --cuda_ray --dir_text") |
|
parser.add_argument('--test', action='store_true', help="test mode") |
|
parser.add_argument('--workspace', type=str, default='workspace') |
|
parser.add_argument('--guidance', type=str, default='stable-diffusion', help='choose from [stable-diffusion, clip]') |
|
parser.add_argument('--seed', type=int, default=0) |
|
|
|
|
|
parser.add_argument('--iters', type=int, default=15000, help="training iters") |
|
parser.add_argument('--lr', type=float, default=1e-3, help="initial learning rate") |
|
parser.add_argument('--ckpt', type=str, default='latest') |
|
parser.add_argument('--cuda_ray', action='store_true', help="use CUDA raymarching instead of pytorch") |
|
parser.add_argument('--max_steps', type=int, default=1024, help="max num steps sampled per ray (only valid when using --cuda_ray)") |
|
parser.add_argument('--num_steps', type=int, default=256, help="num steps sampled per ray (only valid when not using --cuda_ray)") |
|
parser.add_argument('--upsample_steps', type=int, default=0, help="num steps up-sampled per ray (only valid when not using --cuda_ray)") |
|
parser.add_argument('--update_extra_interval', type=int, default=16, help="iter interval to update extra status (only valid when using --cuda_ray)") |
|
parser.add_argument('--max_ray_batch', type=int, default=4096, help="batch size of rays at inference to avoid OOM (only valid when not using --cuda_ray)") |
|
parser.add_argument('--albedo_iters', type=int, default=15000, help="training iters that only use albedo shading") |
|
|
|
parser.add_argument('--bg_radius', type=float, default=1.4, help="if positive, use a background model at sphere(bg_radius)") |
|
parser.add_argument('--density_thresh', type=float, default=10, help="threshold for density grid to be occupied") |
|
|
|
parser.add_argument('--fp16', action='store_true', help="use amp mixed precision training") |
|
parser.add_argument('--backbone', type=str, default='grid', help="nerf backbone, choose from [grid, tcnn, vanilla]") |
|
|
|
parser.add_argument('--w', type=int, default=64, help="render width for NeRF in training") |
|
parser.add_argument('--h', type=int, default=64, help="render height for NeRF in training") |
|
|
|
|
|
parser.add_argument('--bound', type=float, default=1, help="assume the scene is bounded in box(-bound, bound)") |
|
parser.add_argument('--dt_gamma', type=float, default=0, help="dt_gamma (>=0) for adaptive ray marching. set to 0 to disable, >0 to accelerate rendering (but usually with worse quality)") |
|
parser.add_argument('--min_near', type=float, default=0.1, help="minimum near distance for camera") |
|
parser.add_argument('--radius_range', type=float, nargs='*', default=[1.0, 1.5], help="training camera radius range") |
|
parser.add_argument('--fovy_range', type=float, nargs='*', default=[40, 70], help="training camera fovy range") |
|
parser.add_argument('--dir_text', action='store_true', help="direction-encode the text prompt, by appending front/side/back/overhead view") |
|
|
|
|
|
parser.add_argument('--gui', action='store_true', help="start a GUI") |
|
parser.add_argument('--W', type=int, default=800, help="GUI width") |
|
parser.add_argument('--H', type=int, default=800, help="GUI height") |
|
parser.add_argument('--radius', type=float, default=3, help="default GUI camera radius from center") |
|
parser.add_argument('--fovy', type=float, default=60, help="default GUI camera fovy") |
|
parser.add_argument('--light_theta', type=float, default=60, help="default GUI light direction") |
|
parser.add_argument('--light_phi', type=float, default=0, help="default GUI light direction") |
|
parser.add_argument('--max_spp', type=int, default=1, help="GUI rendering max sample per pixel") |
|
|
|
opt = parser.parse_args() |
|
|
|
if opt.O: |
|
opt.fp16 = True |
|
opt.cuda_ray = True |
|
opt.dir_text = True |
|
|
|
if opt.backbone == 'vanilla': |
|
from nerf.network import NeRFNetwork |
|
elif opt.backbone == 'tcnn': |
|
from nerf.network_tcnn import NeRFNetwork |
|
elif opt.backbone == 'grid': |
|
from nerf.network_grid import NeRFNetwork |
|
else: |
|
raise NotImplementedError(f'--backbone {opt.backbone} is not implemented!') |
|
|
|
print(opt) |
|
|
|
seed_everything(opt.seed) |
|
|
|
model = NeRFNetwork(opt) |
|
|
|
print(model) |
|
|
|
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') |
|
|
|
if opt.test: |
|
guidance = None |
|
|
|
trainer = Trainer('ngp', opt, model, guidance, device=device, workspace=opt.workspace, fp16=opt.fp16, use_checkpoint=opt.ckpt) |
|
|
|
if opt.gui: |
|
gui = NeRFGUI(opt, trainer) |
|
gui.render() |
|
|
|
else: |
|
test_loader = NeRFDataset(opt, device=device, type='test', H=opt.H, W=opt.W, size=100).dataloader() |
|
trainer.test(test_loader) |
|
|
|
|
|
else: |
|
|
|
if opt.guidance == 'stable-diffusion': |
|
from nerf.sd import StableDiffusion |
|
guidance = StableDiffusion(device) |
|
elif opt.guidance == 'clip': |
|
from nerf.clip import CLIP |
|
guidance = CLIP(device) |
|
else: |
|
raise NotImplementedError(f'--guidance {opt.guidance} is not implemented.') |
|
|
|
optimizer = lambda model: torch.optim.Adam(model.get_params(opt.lr), betas=(0.9, 0.99), eps=1e-15) |
|
|
|
|
|
train_loader = NeRFDataset(opt, device=device, type='train', H=opt.h, W=opt.w, size=100).dataloader() |
|
|
|
|
|
scheduler = lambda optimizer: optim.lr_scheduler.LambdaLR(optimizer, lambda iter: 0.01 ** min(iter / opt.iters, 1)) |
|
|
|
trainer = Trainer('ngp', opt, model, guidance, device=device, workspace=opt.workspace, optimizer=optimizer, ema_decay=0.95, fp16=opt.fp16, lr_scheduler=scheduler, use_checkpoint=opt.ckpt, eval_interval=1) |
|
|
|
if opt.gui: |
|
trainer.train_loader = train_loader |
|
|
|
gui = NeRFGUI(opt, trainer) |
|
gui.render() |
|
|
|
else: |
|
valid_loader = NeRFDataset(opt, device=device, type='val', H=opt.H, W=opt.W, size=5).dataloader() |
|
|
|
max_epoch = np.ceil(opt.iters / len(train_loader)).astype(np.int32) |
|
trainer.train(train_loader, valid_loader, max_epoch) |
|
|
|
|
|
test_loader = NeRFDataset(opt, device=device, type='test', H=opt.H, W=opt.W, size=100).dataloader() |
|
trainer.test(test_loader) |
|
trainer.save_mesh(resolution=256) |