os.environ["CUDA_VISIBLE_DEVICES"] = gpus
else:
gpus = ""
for i in range(len(args.gpus)):
gpus = gpus + args.gpus[i] + ","
os.environ["CUDA_VISIBLE_DEVICES"] = gpus[:-1]
torch.backends.cudnn.enabled = True # make sure to use cudnn for computational performance
test_folder = args.dataset_path + args.dataset_type + "/testing/frames"
# Loading dataset
test_dataset = DataLoader(test_folder,
transforms.Compose([
transforms.ToTensor(),
]),
resize_height=args.h,
resize_width=args.w,
time_step=args.t_length - 1)
test_size = len(test_dataset)
test_batch = data.DataLoader(test_dataset,
batch_size=args.test_batch_size,
shuffle=False,
num_workers=args.num_workers_test,
drop_last=False)
# Loading the trained model
model = torch.load(args.model_dir)
model.cuda()
# coding:utf-8
import tensorflow as tf
from model.mrcnn import MRCNN
from model.utils import DataLoader
from model.config import Config
config = Config()
with tf.Graph().as_default():
session_conf = tf.ConfigProto(
allow_soft_placement=config.allow_soft_placement,
log_device_placement=config.log_device_placement)
# prepare data set
dataloader = DataLoader()
num_classes = dataloader.numclass
word_embeddings1 = dataloader.word_embeddings1
word_embeddings2 = dataloader.word_embeddings2
# train_data = dataloader.trainset
# test_data = dataloader.testset
# testset_size = dataloader.testset_size
train_data_iter, train_size, train_num_batches = dataloader.batch_iter(
is_train=True,
batch_size=config.batch_size,
num_epochs=config.num_epochs,
oversample=False,
shuffle=True)
test_data_iter, test_size, test_num_batches = dataloader.batch_iter(
is_train=False,
batch_size=20,
