# settting
sets = parse_opts()
sets.target_type = "normal"
sets.phase = 'test'
# getting model
checkpoint = torch.load(sets.resume_path)
net, _ = generate_model(sets)
net.load_state_dict(checkpoint['state_dict'])
# data tensor
testing_data =BrainS18Dataset(sets.data_root, sets.img_list, sets)
data_loader = DataLoader(testing_data, batch_size=1, shuffle=False, num_workers=1, pin_memory=False)
# testing
img_names = [info.split(" ")[0] for info in load_lines(sets.img_list)]
masks = test(data_loader, net, img_names, sets)
# evaluation: calculate dice
label_names = [info.split(" ")[1] for info in load_lines(sets.img_list)]
Nimg = len(label_names)
dices = np.zeros([Nimg, sets.n_seg_classes])
for idx in range(Nimg):
label = nib.load(os.path.join(sets.data_root, label_names[idx]))
label = label.get_data()
dices[idx, :] = seg_eval(masks[idx], label, range(sets.n_seg_classes))
# print result
for idx in range(1, sets.n_seg_classes):
mean_dice_per_task = np.mean(dices[:, idx])
print('mean dice for class-{} is {}'.format(idx, mean_dice_per_task))
net.load_state_dict(checkpoint['state_dict'])
# data tensor
# testing_data =BrainS18Dataset(sets.data_root, sets.img_list, sets)
with open(sets.dataset_info, "r") as read_file:
dataset_info = json.load(read_file)[sets.dataset]
testing_data = BiMaskDataset(dataset_info, sets)
data_loader = DataLoader(testing_data,
batch_size=1,
shuffle=False,
num_workers=1,
pin_memory=False)
# testing
img_names = [
info.split("|")[0] for info in load_lines(dataset_info["fp_val"])
]
masks = test(data_loader, net, img_names, sets)
# evaluation: calculate dice
label_names = [
info.split("|")[1] for info in load_lines(dataset_info["fp_val"])
]
Nimg = len(label_names)
dices = np.zeros([Nimg, sets.n_seg_classes])
for idx in range(Nimg):
label = nib.load(label_names[idx])
label = label.get_data()
dices[idx, :] = seg_eval(masks[idx], label, range(sets.n_seg_classes))
# print result