from auxiliary.my_utils import *
from functools import reduce
from auxiliary.model_atlasnet import *
import miou_shape
import useful_losses as loss
import my_utils
from my_utils import Max_k, Min_k
import ICP
import tqdm
from save_mesh_from_points_and_labels import *
import figure_2_3
import pdb
opt = argument_parser.parser()
my_utils.plant_seeds(randomized_seed=opt.randomize)
min_k = Min_k(opt.k_max_eval)
max_k = Max_k(opt.k_max_eval)
if opt.num_figure_3_4 > 0:
min_k_fig = Min_k(opt.num_figure_3_4)
max_k_fig = Max_k(opt.num_figure_3_4)
trainer = trainer.Trainer(opt)
trainer.build_dataset_train_for_matching()
trainer.build_dataset_test_for_matching()
trainer.build_network()
trainer.network.eval()
# =============DEFINE Criterions to evaluate======================================== #
NN_latent_space = True
crit = [
import sys
import auxiliary.argument_parser as argument_parser
import auxiliary.my_utils as my_utils
import time
import torch
from auxiliary.my_utils import yellow_print
"""
Main training script.
author : Thibault Groueix 01.11.2019
"""
opt = argument_parser.parser()
torch.cuda.set_device(opt.multi_gpu[0])
my_utils.plant_seeds(random_seed=opt.random_seed)
import training.trainer as trainer
trainer = trainer.Trainer(opt)
trainer.build_dataset()
trainer.build_network()
trainer.build_optimizer()
trainer.build_losses()
trainer.start_train_time = time.time()
if opt.demo:
with torch.no_grad():
trainer.demo(opt.demo_input_path)
sys.exit(0)
if opt.run_single_eval:
with torch.no_grad():
trainer.test_epoch()