t5 = t5.reshape(10)
return t5
def save_img(img, save_path):
image_numpy = util.tensor2im(img)
util.save_image(image_numpy, save_path, create_dir=True)
return image_numpy
if __name__ == '__main__':
opt = TestOptions().parse()
data_info = data.dataset_info()
datanum = data_info.get_dataset(opt)[0]
folderlevel = data_info.folder_level[datanum]
dataloaders = data.create_dataloader_test(opt)
visualizer = Visualizer(opt)
iter_counter = IterationCounter(opt, len(dataloaders[0]) * opt.render_thread)
# create a webpage that summarizes the all results
testing_queue = Queue(10)
ngpus = opt.device_count
render_gpu_ids = list(range(ngpus - opt.render_thread, ngpus))
render_layer_list = []
import os
import math
import numpy as np
from PIL import Image
import skimage.transform as trans
import cv2
import torch
from data import dataset_info
from data.base_dataset import BaseDataset
import util.util as util
dataset_info = dataset_info()
class AllFaceDataset(BaseDataset):
@staticmethod
def modify_commandline_options(parser, is_train):
parser.add_argument('--no_pairing_check', action='store_true',
help='If specified, skip sanity check of correct label-image file pairing')
return parser
def cv2_loader(self, img_str):
img_array = np.frombuffer(img_str, dtype=np.uint8)
return cv2.imdecode(img_array, cv2.IMREAD_COLOR)
def fill_list(self, tmp_list):
length = len(tmp_list)
if length % self.opt.batchSize != 0:
end = math.ceil(length / self.opt.batchSize) * self.opt.batchSize
tmp_list = tmp_list + tmp_list[-1 * (end - length) :]
return tmp_list