def paint(self, img_file, save_path, nsampling):
for c, img in enumerate(image):
save = []
img_file = os.path.join(image_root, img)
for mask_width in [16, 32, 48, 64]:
dataset = data_loader.dataloader(self.opt,
img_file,
mask_width=mask_width)
for i, data in enumerate(islice(dataset, self.opt.how_many)):
self.model.set_input(data)
out = [(normalize(data['img']) * data['mask']).cuda()]
out.extend(self.model.test(save_path, nsampling))
save.extend(out)
# embed()
save_img_test(torch.cat(save), f"pretrained_task3_img{c}.png")
import os
from options.test_options import TestOptions
from dataloader.data_loader import dataloader
from model.models import create_model
from util.visualizer import Visualizer
from util import html
opt = TestOptions().parse()
dataset = dataloader(opt)
dataset_size = len(dataset) * opt.batchSize
print ('testing images = %d ' % dataset_size)
model = create_model(opt)
visualizer = Visualizer(opt)
web_dir = os.path.join(opt.results_dir, opt.name, '%s_%s' %(opt.phase, opt.which_epoch))
web_page = html.HTML(web_dir, 'Experiment = %s, Phase = %s, Epoch = %s' % (opt.name, opt.phase, opt.which_epoch))
# testing
for i,data in enumerate(dataset):
model.set_input(data)
model.test()
model.save_results(visualizer, web_page)
--img_target_file ../../data/akada/datasets/unreal2nyu/trainB \
--lab_source_file ../../data/akada/datasets/unreal2nyu/trainA_depth \
--lab_target_file ../../data/akada/datasets/unreal2nyu/trainB_depth \
--gpu_ids 1 --shuffle --flip --rotation --no_html --display_id -1 --norm instance
"""
import time
from options.train_options import TrainOptions
from dataloader.data_loader import dataloader
from model.models import create_model
from util.visualizer import Visualizer
opt = TrainOptions().parse()
dataset = dataloader(opt)
dataset_size = len(dataset) * opt.batch_size
print('training images = %d' % dataset_size)
# create datasets for Gaussian Process
labeled_dataset = None
unlabeled_dataset = None
if opt.gp:
labeled_dataset, unlabeled_dataset = dataloader(opt, gp=True)
print('The number of labeled training images for GP = %d' %
len(labeled_dataset))
print('The number of unlabeled training images for GP = %d' %
len(unlabeled_dataset))
model = create_model(opt, labeled_dataset, unlabeled_dataset)
visualizer = Visualizer(opt)
# python test.py --name wordattninpainting --img_file datasets/CUB_200_2011/valid.flist --results_dir results/wordattninpainting --how_many 200 --mask_file datasets/CUB_200_2011/test_mask.flist --mask_type 3 --no_shuffle --gpu_ids 0 --nsampling 1
from options import test_options
from dataloader import data_loader
from model import create_model
from util import visualizer
import torch
import os
if __name__=='__main__':
# get testing options
opt = test_options.TestOptions().parse()
# creat a dataset
dataset = data_loader.dataloader(opt)
dataset_size = len(dataset) * opt.batchSize
print('testing images = %d' % dataset_size)
# create a model
model = create_model(opt)
model.eval()
# create a visualizer
visualizer = visualizer.Visualizer(opt)
for i, data in enumerate(dataset):
with torch.no_grad():
model.set_input(data)
model.test()
truths = []
for file in os.listdir(opt.results_dir):
if file.endswith('_truth.png'):
truths.append(opt.results_dir + '/' + file)
def paint(self, img_file, save_path, nsampling):
dataset = data_loader.dataloader(self.opt, img_file)
for i, data in enumerate(islice(dataset, self.opt.how_many)):
self.model.set_input(data)
self.model.test(save_path, nsampling)
if __name__ == '__main__':
# get testing options
opt = test_options.TestOptions().parse()
# creat a dataset
##create input images directory
opt.img_file = 'nose_test'
util.mkdir(opt.img_file)
if not os.path.exists(opt.img_file):
os.makedirs(opt.img_file)
else:
for f in glob.glob(os.path.join(opt.img_file, '*')):
os.remove(f)
copyfile(opt.image1,
os.path.join(opt.img_file,
os.path.split(opt.image1)[-1]))
copyfile(opt.image2,
os.path.join(opt.img_file,
os.path.split(opt.image2)[-1]))
dataset = data_loader.dataloader(opt, True)
dataset_size = len(dataset) * opt.batchSize
print('testing images = %d' % dataset_size)
# create a model
model = create_model(opt)
model.eval()
# create a visualizer
visualizer = visualizer.Visualizer(opt)
for i, data in enumerate(islice(dataset, opt.how_many)):
model.set_input(data)
model.test()
