gha / data_tool /test_generation.py
vegagoto123's picture
Add files using upload-large-folder tool
3217786 verified
Raw History Blame Contribute Delete
14.8 kB
#
# Copyright (C) 2023, Inria
# GRAPHDECO research group, https://team.inria.fr/graphdeco
# All rights reserved.
#
# This software is free for non-commercial, research and evaluation use
# under the terms of the LICENSE.md file.
#
# For inquiries contact george.drettakis@inria.fr
#
import os
import torch
import time
from random import randint
from utils.loss_utils import l1_loss, ssim
from gaussian_renderer import render, network_gui
import sys
from scene import Scene, GaussianModel, eghuman_dataset, collate_fn, Eghuman
from src.deform_model import Deform_Model
from scene.gaussian_nograd_model import GaussianModel_nograd
from scene.test_data import TestData
from utils.general_utils import safe_state
import uuid
from tqdm import tqdm
import numpy as np
from utils.image_utils import psnr
from argparse import ArgumentParser, Namespace
from arguments import ModelParams, PipelineParams, OptimizationParams
from utils.sh_utils import RGB2SH
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torchvision.models as models
import torch.nn as nn
import torchvision
from simple_knn._C import distCUDA2
# from torch_geometric.data import Data
# from torch_geometric.transforms import SamplePoints
try:
from torch.utils.tensorboard import SummaryWriter
TENSORBOARD_FOUND = False
except ImportError:
TENSORBOARD_FOUND = False
os.environ["CUDA_VISIBLE_DEVICES"] = "7"
os.environ['CUDA_LAUNCH_BLOCKING'] = '1'
def encoding_position(xyz_sample):
L = 10
posison_encoding = []
for i in range(L):
posison_encoding.append(torch.sin(2**i*np.pi*xyz_sample))
posison_encoding.append(torch.cos(2**i*np.pi*xyz_sample))
posison_encoding.append(torch.sin(2**L*np.pi*xyz_sample))
posison_encoding = torch.concat(posison_encoding, -1)
return posison_encoding
def requires_grad(model, flag=True):
for p in model.parameters():
p.requires_grad = flag
def gs_requires_grad(gs, flag):
for i in gs:
for p in i['params']:
p.requires_grad = flag
# gs._xyz_scale = gs._xyz_scale.detach()
# gs._align_R = gs._align_R.detach()
# gs._align_T = gs._align_T.detach()
# gs._features_dc = gs._features_dc.detach()
# gs._features_rest = gs._features_rest.detach()
# gs._opacity = gs._opacity.detach()
# gs._scaling = gs._scaling.detach()
# gs ._rotation = gs._rotation.detach()
def training(train_loader, dataset, opt, pipe, testing_iterations, saving_iterations, checkpoint_iterations, checkpoint, debug_from):
DeformModel = Deform_Model(dataset.data_device).to(dataset.data_device)
eghuman = Eghuman(opt, dataset.data_device, dataset.use_sh, dataset.sh_degree, dataset.checkpoint_path, dataset.deca_pretain_path, DeformModel.deformNet)
data_tool = TestData(dataset.data_device)
eghuman.feature_net.eval()
eghuman.gs_decoder.eval()
# eghuman.pose_flame.eval()
eghuman.deformNet.eval()
start_iter = eghuman.set_up()
iter = 0
if dataset.checkpoint_path is not None:
iter = start_iter + 1
for epoch in range(opt.epoch):
times = []
for step ,data_train in enumerate(train_loader):
gaussians = data_train[0]['gs']
scene = data_train[0]['sc']
dataset = data_train[0]['args']
data_length = data_train[0]['data_length']
first_iter = 0
tb_writer = prepare_output_and_logger(dataset)
if checkpoint:
(model_params, first_iter) = torch.load(checkpoint)
gaussians.restore(model_params, opt)
bg_color = [1, 1, 1] if dataset.white_background else [0, 0, 0]
background = torch.tensor(bg_color, dtype=torch.float32, device=dataset.data_device)
viewpoint_stack = None
first_iter += 1
# preframe_index = [i for i in range(30, len(scene.getTrainCameras().copy()), 30)]
preframe_index = [2,3,13]
viewpoint_stack = scene.getTrainCameras().copy()
input_img = []
input_transform = []
for frame_iter in range(len(preframe_index)):
input_viewpoint = viewpoint_stack[preframe_index[frame_iter]]
input_transform.append(input_viewpoint.full_proj_transform)
input_img.append(input_viewpoint.original_image.to(dataset.data_device))
input_img = torch.stack(input_img, 0)
flame_input = data_tool.image_crop(input_img[1, ...].permute(1, 2, 0).cpu().numpy())
for iteration in range(first_iter, opt.iterations + 1):
if network_gui.conn == None:
network_gui.try_connect()
while network_gui.conn != None:
try:
net_image_bytes = None
custom_cam, do_training, pipe.convert_SHs_python, pipe.compute_cov3D_python, keep_alive, scaling_modifer = network_gui.receive()
if custom_cam != None:
net_image = render(custom_cam, gaussians, pipe, background, scaling_modifer)["render"]
net_image_bytes = memoryview((torch.clamp(net_image, min=0, max=1.0) * 255).byte().permute(1, 2, 0).contiguous().cpu().numpy())
network_gui.send(net_image_bytes, dataset.source_path)
if do_training and ((iteration < int(opt.iterations)) or not keep_alive):
break
except Exception as e:
network_gui.conn = None
# init flame
eghuman.opt.zero_grad()
start_time = time.time()
parameters = eghuman.shape_flame(flame_input.to('cuda:7'))
codedict_shape = data_tool.decompose_code(parameters)
# codedict_pose = eghuman.pose_flame(flame_input, opt.n_eyes, opt.n_jaw, opt.n_neck, opt.n_person)
# codedict = {**codedict_shape, **codedict_pose}
codedict = codedict_shape
codedict['trans_params'] = eghuman.trans_params
DeformModel.example_init(codedict)
# Pick a person time sequeece
if not viewpoint_stack:
viewpoint_stack = scene.getTrainCameras().copy()
gt_viewpoint = viewpoint_stack.pop(randint(0, len(viewpoint_stack)-1))
# deform gaussians
verts_final, rot_delta, scale_coef, verts_flame = DeformModel.decode(codedict)
end_time = time.time()
execution_time = end_time - start_time
times.append(execution_time)
# print(f"代码段执行时间为: {execution_time} 秒")
if iteration == 1:
gaussians.create_from_verts(verts_flame[0])
gaussians.update_xyz_rot_scale(verts_flame[0], rot_delta[0], scale_coef[0])
else:
gaussians.update_xyz_rot_scale(verts_final[0], rot_delta[0], scale_coef[0])
# decoder gs parameters
point_uv, point_z = eghuman.uv_compute(gaussians.get_xyz, input_transform, input_img, dataset.data_device)
z_embedding = encoding_position(point_z)
feature_map = eghuman.feature_net(input_img.to('cuda:7'))
point_fc2d = eghuman.uv_sample(input_img, feature_map, point_uv)
gs_para = eghuman.gs_decoder(gaussians.get_xyz, point_fc2d, z_embedding)
gaussians._features_dc = gs_para['f_dc']
gaussians._opacity = gs_para['opacity']
gaussians._scaling = gs_para['scaling']
gaussians._rotation = gs_para['rotation']
if dataset.use_sh:
render_pkg = render(gt_viewpoint, gaussians, pipe, background)
else:
render_pkg = render(gt_viewpoint, gaussians, pipe, background, override_color = gaussians._features_dc)
image_parameter, _, _, _ = render_pkg["render"], render_pkg["viewspace_points"], render_pkg["visibility_filter"], render_pkg["radii"]
torchvision.utils.save_image(image_parameter, os.path.join('/data_160TB/2021/yangkun/gha-gaussian/train_imgs', '{0:05d}'.format(iteration) + "_rgb.png"))
# Loss
gt_image = (gt_viewpoint.original_image).to(dataset.data_device)
torchvision.utils.save_image(gt_image, os.path.join('/data_160TB/2021/yangkun/gha-gaussian/train_imgs', '{0:05d}'.format(iteration) + "_gt.png"))
# with open('/data_160TB/2021/yangkun/gha-gaussian/checkpoints/test/3_view_input/checkpoint_allviews_data_new_2loss_1104_x16/time_log.txt', 'a') as file:
# file.write(f'time: {execution_time}\n')
if (iteration in saving_iterations):
#save
print("\n[ITER {}] Saving FLAME".format(iteration))
scene.save(iteration, 'ply')
if dataset.type_3d == 'obj':
scene.save(iteration, dataset.type_3d)
if (iteration in checkpoint_iterations):
print("\n[ITER {}] Saving Checkpoint".format(iteration))
torch.save((gaussians.capture(), iteration), scene.model_path + "/chkpnt" + str(iteration) + ".pth")
times_avg = sum(times) / len(times)
# with open('/data_160TB/2021/yangkun/gha-gaussian/checkpoints/test/3_view_input/checkpoint_allviews_data_new_2loss_1104_x16/time_log.txt', 'a') as file:
# file.write(f'time_avg: {times_avg}\n')
print(times_avg)
def prepare_output_and_logger(args):
if not args.model_path:
if os.getenv('OAR_JOB_ID'):
unique_str=os.getenv('OAR_JOB_ID')
else:
unique_str = str(uuid.uuid4())
args.model_path = os.path.join("./output/", unique_str[0:10])
# Set up output folder
print("Output folder: {}".format(args.model_path))
os.makedirs(args.model_path, exist_ok = True)
with open(os.path.join(args.model_path, "cfg_args"), 'w') as cfg_log_f:
cfg_log_f.write(str(Namespace(**vars(args))))
# Create Tensorboard writer
tb_writer = None
if TENSORBOARD_FOUND:
tb_writer = SummaryWriter(args.model_path)
else:
print("Tensorboard not available: not logging progress")
return tb_writer
def training_report(tb_writer, iteration, Ll1, loss, l1_loss, elapsed, testing_iterations, scene : Scene, renderFunc, renderArgs):
if tb_writer:
tb_writer.add_scalar('train_loss_patches/l1_loss', Ll1.item(), iteration)
tb_writer.add_scalar('train_loss_patches/total_loss', loss.item(), iteration)
tb_writer.add_scalar('iter_time', elapsed, iteration)
# Report test and samples of training set
if iteration in testing_iterations:
torch.cuda.empty_cache()
validation_configs = ({'name': 'test', 'cameras' : scene.getTestCameras()},
{'name': 'train', 'cameras' : [scene.getTrainCameras()[idx % len(scene.getTrainCameras())] for idx in range(5, 30, 5)]})
for config in validation_configs:
if config['cameras'] and len(config['cameras']) > 0:
l1_test = 0.0
psnr_test = 0.0
for idx, viewpoint in enumerate(config['cameras']):
image = torch.clamp(renderFunc(viewpoint, scene.gaussians, *renderArgs)["render"], 0.0, 1.0)
gt_image = torch.clamp(viewpoint.original_image.to("cuda:7"), 0.0, 1.0)
if tb_writer and (idx < 5):
tb_writer.add_images(config['name'] + "_view_{}/render".format(viewpoint.image_name), image[None], global_step=iteration)
if iteration == testing_iterations[0]:
tb_writer.add_images(config['name'] + "_view_{}/ground_truth".format(viewpoint.image_name), gt_image[None], global_step=iteration)
l1_test += l1_loss(image, gt_image).mean().double()
psnr_test += psnr(image, gt_image).mean().double()
psnr_test /= len(config['cameras'])
l1_test /= len(config['cameras'])
print("\n[ITER {}] Evaluating {}: L1 {} PSNR {}".format(iteration, config['name'], l1_test, psnr_test))
if tb_writer:
tb_writer.add_scalar(config['name'] + '/loss_viewpoint - l1_loss', l1_test, iteration)
tb_writer.add_scalar(config['name'] + '/loss_viewpoint - psnr', psnr_test, iteration)
if tb_writer:
tb_writer.add_histogram("scene/opacity_histogram", scene.gaussians.get_opacity, iteration)
tb_writer.add_scalar('total_points', scene.gaussians.get_xyz.shape[0], iteration)
torch.cuda.empty_cache()
if __name__ == "__main__":
# Set up command line argument parser
parser = ArgumentParser(description="Training script parameters")
lp = ModelParams(parser)
op = OptimizationParams(parser)
pp = PipelineParams(parser)
parser.add_argument('--ip', type=str, default="127.0.0.2")
parser.add_argument('--port', type=int, default=6061)
parser.add_argument('--debug_from', type=int, default=-1)
parser.add_argument('--detect_anomaly', action='store_true', default=False)
parser.add_argument("--test_iterations", nargs="+", type=int, default=[])
parser.add_argument("--save_iterations", nargs="+", type=int, default=[1, 200, 500, 1_000, 2_000, 3_000, 4_000, 5_000, 6_000, 7_000, 8_000, 14_000, 30_000])
parser.add_argument("--quiet", action="store_true")
parser.add_argument("--checkpoint_iterations", nargs="+", type=int, default=[])
parser.add_argument("--start_checkpoint", type=str, default = None)
args = parser.parse_args(sys.argv[1:])
args.save_iterations.append(args.iterations)
print("Optimizing " + args.model_path)
# Initialize system state (RNG)
safe_state(args.quiet)
# Start GUI server, configure and run training
network_gui.init(args.ip, args.port)
torch.autograd.set_detect_anomaly(args.detect_anomaly)
dataset_train = eghuman_dataset(lp.extract(args), train = True)
dataloader_train = DataLoader(dataset=dataset_train, batch_size=1, shuffle=False, num_workers=0, collate_fn=collate_fn)
training(dataloader_train, lp.extract(args), op.extract(args), pp.extract(args), args.test_iterations, args.save_iterations, args.checkpoint_iterations, args.start_checkpoint, args.debug_from)
# All done
print("\nTraining complete.")