test for net with asd&&dice

最新推荐文章于 2024-05-25 14:11:46 发布

为了待会去码头整点薯条

最新推荐文章于 2024-05-25 14:11:46 发布

阅读量312

点赞数

文章标签：深度学习 pytorch 人工智能

本文链接：https://blog.csdn.net/qq_43210029/article/details/129234985

版权

from init1011 import  Options
from Network.networks import build_net, update_learning_rate, build_UNETR, build_unet, build_vnet, build_swinUNet, build_HRNet
import logging
import sys
from glob import glob
import numpy as np
import torch
import nibabel as nib
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
import monai
from monai.data import list_data_collate, decollate_batch, CacheDataset
from monai.inferers import sliding_window_inference
from monai.metrics import DiceMetric, SurfaceDistanceMetric
from monai.transforms import (EnsureType, Compose, LoadImaged, AddChanneld, AsDiscrete, RandGaussianSmoothd,
                              CropForegroundd, SpatialPadd,
                              ScaleIntensityd, ToTensord, RandSpatialCropd, Rand3DElasticd, RandAffined, Spacingd,
                              RandShiftIntensityd,
                              RandGaussianNoised, RandAdjustContrastd, NormalizeIntensityd, RandFlipd, SaveImage,
                              EnsureChannelFirstd, KeepLargestConnectedComponent)
from monai.visualize import plot_2d_or_3d_image
from tqdm import tqdm
import glob
from time import time
import os

os.environ['CUDA_VISIBLE_DEVICES'] = '1'



def main():
    opt = Options().parse()
    # monai.config.print_config()
    logging.basicConfig(stream=sys.stdout, level=logging.INFO)
    device = torch.device("cuda")
    train_images = sorted(
        glob.glob(os.path.join(opt.images_folder,  "*.nii.gz")))
    train_labels = sorted(
        glob.glob(os.path.join(opt.labels_folder,  "*.nii.gz")))
    data_dicts = [
        {"image": image_name, "label": label_name}
        for image_name, label_name in zip(train_images, train_labels)
    ]
    val_dicts = data_dicts[0:20]


    print('Number of validating images per epoch:', len(val_dicts))


    # Creation of data directories for data_loader
    # Transforms for training and validation

    val_transforms = [
        LoadImaged(keys=['image', 'label']),
        EnsureChannelFirstd(keys=['image', 'label']),

        ]
    val_transforms = Compose(val_transforms)

    # Define CacheDataset and DataLoader for training and validation
    # create a training data loader

    val_ds = CacheDataset(
        data=val_dicts, transform=val_transforms, cache_num=6, cache_rate=1.0, num_workers=4)
    val_loader = DataLoader(val_ds, batch_size=1, num_workers=opt.workers, collate_fn=list_data_collate, pin_memory=True)
    # post_pred = Compose([EnsureType(),  AsDiscrete(argmax=True, to_onehot=6)])
    # post_label = Compose([EnsureType(),  AsDiscrete(to_onehot=6)])
    post_pred = Compose([EnsureType(),  AsDiscrete(argmax=True, to_onehot=6), KeepLargestConnectedComponent(is_onehot=True) ])
    post_label = Compose([EnsureType(),  AsDiscrete(to_onehot=6),KeepLargestConnectedComponent(is_onehot=True)])
    saver_ori = SaveImage(output_dir='/home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227', output_ext=".nii.gz", output_postfix="ori",print_log=True)
    saver_gt = SaveImage(output_dir='/home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227', output_ext=".nii.gz", output_postfix="gt",print_log=True)
    saver_seg = SaveImage(output_dir='/home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227', output_ext=".nii.gz", output_postfix="seg",print_log=True)


    # Create Model, Loss, Optimizer
    # build the network
    # if opt.network == 'nnunet':
    net = build_net()  # nn build_net
    #     print('net == nnunet')
    # elif opt.network == 'unetr':
    #     net = build_UNETR() # UneTR
    #     print('net == unetr')
    # elif opt.network == 'unet':
    #     net = build_unet() # unet3D
    # elif opt.network == 'vnet':
    #     net = build_vnet()
    # elif opt.network == 'HRNet':
    #     net = build_HRNet()
    # elif opt.network == 'swinUNetR':
    #     net = build_swinUNet()

    net.to(device)

    torch.backends.cudnn.benchmark = opt.benchmark  # for accelerating Convs
    dice_metric = DiceMetric(include_background=True, reduction="mean", get_not_nans=False)  # Mean Dice caculate
    dice_metric_batch = DiceMetric(include_background=True, reduction="mean_batch")

    asd_metric_channel = SurfaceDistanceMetric(include_background=False, reduction='mean_batch', symmetric=True)
    best_metric = -1
    metric_values = []
    metric_values_tb = []
    metric_values_tc = []
    metric_values_fb = []
    metric_values_lfc = []
    metric_values_rfc = []
    metric_values_bg = []
    val_time = time()

    # net.load_state_dict(torch.load(
    #     '/home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/best_metric_model_test_0822_HRNet.pth'))
    # print("Use pretrained model ! Attention")
    ckpt = torch.load('/home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/best_metrich_1018_monai_nnunet.pth')
    net.load_state_dict(ckpt["net"])


    net.eval()
    saver_flag = 1
    with torch.no_grad():
            pbar = tqdm(val_loader, ncols=50, dynamic_ncols=True)
            for val_data in pbar:
                # for val_data in val_loader:
                pbar.set_description(desc='Valid_Epoch ')
                val_inputs, val_labels = (
                        val_data["image"].to(device),
                        val_data["label"].to(device),
                )

                roi_size = opt.patch_size
                sw_batch_size = 4
                val_outputs = sliding_window_inference(
                        val_inputs, roi_size, sw_batch_size, net)
                val_outputs = [post_pred(i) for i in decollate_batch(val_outputs)]
                val_labels = [post_label(i) for i in decollate_batch(val_labels)]

                asd_metric_channel(y_pred=val_outputs, y=val_labels)
                    # compute metric for current iteration
                dice_metric(y_pred=val_outputs, y=val_labels)
                dice_metric_batch(y_pred=val_outputs, y=val_labels)

                print(val_inputs[0].shape, val_outputs[0].shape, val_labels[0].shape)
                saver_ori(val_inputs[0])
                saver_seg(torch.argmax(val_outputs[0], dim=0, keepdim=True))
                saver_gt(torch.argmax(val_labels[0], dim=0, keepdim=True))
                # if (saver_flag > 0):
                #         meta_data = decollate_batch(val_data["image_meta_dict"])
                #         saver_flag = 0
                #         print(val_inputs[0].shape, val_outputs[0].shape, val_labels[0].shape)
                #         saver_ori(val_inputs[0])
                #         saver_seg(torch.argmax(val_outputs[0], dim=0, keepdim=True))
                #         saver_gt(torch.argmax(val_labels[0], dim=0, keepdim=True))


                # aggregate the final mean dice result
                dice = dice_metric.aggregate().item()
                asd_channel = asd_metric_channel.aggregate()

                metric_values.append(dice)
                metric_batch = dice_metric_batch.aggregate()
                # print('metric_batch.shape', metric_batch.shape)
                metric_bg = metric_batch[0].item()
                metric_values_bg.append(metric_bg)
                metric_tb = metric_batch[1].item()
                metric_values_tb.append(metric_tb)
                metric_tc = metric_batch[2].item()
                metric_values_tc.append(metric_tc)
                metric_fb = metric_batch[3].item()
                metric_values_fb.append(metric_fb)
                metric_lfc = metric_batch[4].item()
                metric_values_lfc.append(metric_lfc)
                metric_rfc = metric_batch[5].item()
                metric_values_rfc.append(metric_rfc)
                print("channel wise Metric on original image spacing(no BG) asd: ", asd_channel)
                print(
                    f"\n  mean dice: {dice:.4f}"
                    f"\naverage dice:({metric_tb:.4f}, {metric_tc:.4f}, {metric_fb:.4f}, {metric_lfc:.4f}, {metric_rfc:.4f})"
                    f"\nbest mean dice: {best_metric:.4f}    "
                )
                # reset the status for next validation round
                dice_metric.reset()
                dice_metric_batch.reset()
                asd_metric_channel.reset()

    val_end = time()
    print('val takes:{:.4f}'.format(val_end - val_time))


if __name__ == "__main__":
    main()

ssh://dluser@10.1.15.80:22/home/dluser/anaconda3/envs/han/bin/python -u /home/dluser/.pycharm_helpers/pydev/pydevconsole.py --mode=server
import sys; print('Python %s on %s' % (sys.version, sys.platform))
sys.path.extend(['/home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation', '/home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation'])
Python 3.8.12 (default, Oct 12 2021, 13:49:34) 
Type 'copyright', 'credits' or 'license' for more information
IPython 8.1.1 -- An enhanced Interactive Python. Type '?' for help.
PyDev console: using IPython 8.1.1
Python 3.8.12 (default, Oct 12 2021, 13:49:34) 
[GCC 7.5.0] on linux
runfile('/home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/test_nnunet.py', wdir='/home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation')
/home/dluser/anaconda3/envs/han/lib/python3.8/site-packages/apex/pyprof/__init__.py:5: FutureWarning: pyprof will be removed by the end of June, 2022
  warnings.warn("pyprof will be removed by the end of June, 2022", FutureWarning)
Number of validating images per epoch: 20
Loading dataset: 100%|████████████████████████████| 6/6 [00:01<00:00,  3.66it/s]
Valid_Epoch :   0%|                                      | 0/20 [00:00<?, ?it/s](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-27 09:03:06,043 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9001104/9001104_ori.nii.gz
2023-02-27 09:03:07,635 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9001104/9001104_seg.nii.gz
2023-02-27 09:03:08,318 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9001104/9001104_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.6459, 0.8600, 0.4706, 0.5777, 0.5863], dtype=torch.float64)
  mean dice: 0.9187
average dice:(0.9834, 0.8437, 0.9877, 0.8352, 0.8660)
best mean dice: -1.0000    
Valid_Epoch :   5%|█▌                            | 1/20 [00:12<03:55, 12.39s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-27 09:03:16,624 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9002430/9002430_ori.nii.gz
2023-02-27 09:03:18,247 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9002430/9002430_seg.nii.gz
2023-02-27 09:03:18,865 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9002430/9002430_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.5648, 0.7418, 0.4880, 0.7244, 0.5877], dtype=torch.float64)
  mean dice: 0.9361
average dice:(0.9860, 0.8952, 0.9875, 0.8538, 0.8979)
best mean dice: -1.0000    
Valid_Epoch :  10%|███                           | 2/20 [00:22<03:24, 11.34s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-27 09:03:26,398 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9002817/9002817_ori.nii.gz
2023-02-27 09:03:28,139 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9002817/9002817_seg.nii.gz
2023-02-27 09:03:29,012 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9002817/9002817_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.5254, 0.7947, 0.6037, 0.6451, 0.9014], dtype=torch.float64)
  mean dice: 0.9153
average dice:(0.9859, 0.8654, 0.9829, 0.8417, 0.8193)
best mean dice: -1.0000    
Valid_Epoch :  15%|████▌                         | 3/20 [00:33<03:04, 10.86s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-27 09:03:37,266 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9003430/9003430_ori.nii.gz
2023-02-27 09:03:38,936 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9003430/9003430_seg.nii.gz
2023-02-27 09:03:39,606 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9003430/9003430_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.5746, 0.7382, 0.5988, 0.6855, 0.5969], dtype=torch.float64)
  mean dice: 0.9329
average dice:(0.9856, 0.8826, 0.9839, 0.8427, 0.9061)
best mean dice: -1.0000    
Valid_Epoch :  20%|██████                        | 4/20 [00:43<02:51, 10.70s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-27 09:03:48,039 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9004175/9004175_ori.nii.gz
2023-02-27 09:03:49,681 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9004175/9004175_seg.nii.gz
2023-02-27 09:03:50,413 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9004175/9004175_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.4072, 0.6133, 0.5097, 0.4696, 0.6760], dtype=torch.float64)
  mean dice: 0.9482
average dice:(0.9905, 0.9073, 0.9879, 0.9090, 0.8979)
best mean dice: -1.0000    
Valid_Epoch :  25%|███████▌                      | 5/20 [00:54<02:40, 10.71s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-27 09:03:58,465 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9005075/9005075_ori.nii.gz
2023-02-27 09:04:00,107 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9005075/9005075_seg.nii.gz
2023-02-27 09:04:00,764 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9005075/9005075_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.4548, 0.6454, 1.3741, 0.6340, 0.7473], dtype=torch.float64)
  mean dice: 0.9302
average dice:(0.9884, 0.8974, 0.9775, 0.8511, 0.8703)
best mean dice: -1.0000    
Valid_Epoch :  30%|█████████                     | 6/20 [01:04<02:28, 10.59s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-27 09:04:08,772 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9005132/9005132_ori.nii.gz
2023-02-27 09:04:10,371 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9005132/9005132_seg.nii.gz
2023-02-27 09:04:11,091 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9005132/9005132_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.5885, 0.6685, 0.4580, 0.5217, 0.5561], dtype=torch.float64)
  mean dice: 0.9335
average dice:(0.9836, 0.8852, 0.9874, 0.8607, 0.8868)
best mean dice: -1.0000    
Valid_Epoch :  35%|██████████▌                   | 7/20 [01:15<02:16, 10.51s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-27 09:04:19,119 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9006723/9006723_ori.nii.gz
2023-02-27 09:04:20,722 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9006723/9006723_seg.nii.gz
2023-02-27 09:04:21,421 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9006723/9006723_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.5942, 0.6461, 0.4737, 0.6869, 0.6592], dtype=torch.float64)
  mean dice: 0.9236
average dice:(0.9850, 0.8986, 0.9879, 0.8006, 0.8727)
best mean dice: -1.0000    
Valid_Epoch :  40%|████████████                  | 8/20 [01:25<02:05, 10.46s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-27 09:04:29,379 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9007827/9007827_ori.nii.gz
2023-02-27 09:04:31,034 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9007827/9007827_seg.nii.gz
2023-02-27 09:04:31,715 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9007827/9007827_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.4456, 0.7327, 0.5130, 0.6401, 0.4618], dtype=torch.float64)
  mean dice: 0.9171
average dice:(0.9880, 0.8589, 0.9857, 0.7748, 0.8983)
best mean dice: -1.0000    
Valid_Epoch :  45%|█████████████▌                | 9/20 [01:35<01:54, 10.40s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-27 09:04:39,201 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9008561/9008561_ori.nii.gz
2023-02-27 09:04:40,861 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9008561/9008561_seg.nii.gz
2023-02-27 09:04:41,552 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9008561/9008561_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.5171, 0.6085, 0.4757, 0.5902, 0.5105], dtype=torch.float64)
  mean dice: 0.9243
average dice:(0.9844, 0.8867, 0.9860, 0.8151, 0.8772)
best mean dice: -1.0000    
Valid_Epoch :  50%|██████████████▌              | 10/20 [01:45<01:42, 10.24s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-27 09:04:49,260 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9011115/9011115_ori.nii.gz
2023-02-27 09:04:50,948 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9011115/9011115_seg.nii.gz
2023-02-27 09:04:51,628 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9011115/9011115_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.6068, 0.6694, 0.8554, 0.6810, 0.6034], dtype=torch.float64)
  mean dice: 0.9250
average dice:(0.9837, 0.8832, 0.9803, 0.8163, 0.8899)
best mean dice: -1.0000    
Valid_Epoch :  55%|███████████████▉             | 11/20 [01:55<01:31, 10.18s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-27 09:04:59,050 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9011420/9011420_ori.nii.gz
2023-02-27 09:05:00,610 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9011420/9011420_seg.nii.gz
2023-02-27 09:05:01,317 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9011420/9011420_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.5305, 0.6061, 0.5535, 0.4992, 0.7425], dtype=torch.float64)
  mean dice: 0.9366
average dice:(0.9846, 0.9038, 0.9843, 0.8851, 0.8655)
best mean dice: -1.0000    
Valid_Epoch :  60%|█████████████████▍           | 12/20 [02:05<01:20, 10.02s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-27 09:05:09,249 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9012867/9012867_ori.nii.gz
2023-02-27 09:05:10,930 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9012867/9012867_seg.nii.gz
2023-02-27 09:05:11,792 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9012867/9012867_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.6591, 0.9748, 1.0138, 1.1164, 0.7795], dtype=torch.float64)
  mean dice: 0.9029
average dice:(0.9831, 0.8486, 0.9731, 0.7577, 0.8597)
best mean dice: -1.0000    
Valid_Epoch :  65%|██████████████████▊          | 13/20 [02:16<01:11, 10.22s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-27 09:05:20,028 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9013161/9013161_ori.nii.gz
2023-02-27 09:05:21,661 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9013161/9013161_seg.nii.gz
2023-02-27 09:05:22,332 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9013161/9013161_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([1.1974, 1.1241, 0.8562, 1.8523, 1.2829], dtype=torch.float64)
  mean dice: 0.8202
average dice:(0.9718, 0.8070, 0.9763, 0.4904, 0.6812)
best mean dice: -1.0000    
Valid_Epoch :  70%|████████████████████▎        | 14/20 [02:26<01:01, 10.27s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-27 09:05:29,716 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9013798/9013798_ori.nii.gz
2023-02-27 09:05:31,410 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9013798/9013798_seg.nii.gz
2023-02-27 09:05:32,038 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9013798/9013798_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.4999, 0.5937, 0.4512, 0.5656, 0.5230], dtype=torch.float64)
  mean dice: 0.9289
average dice:(0.9851, 0.8940, 0.9870, 0.8411, 0.8704)
best mean dice: -1.0000    
Valid_Epoch :  75%|█████████████████████▊       | 15/20 [02:36<00:50, 10.11s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-27 09:05:39,682 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9015718/9015718_ori.nii.gz
2023-02-27 09:05:41,264 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9015718/9015718_seg.nii.gz
2023-02-27 09:05:41,951 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9015718/9015718_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.4039, 0.5966, 0.4720, 0.6226, 0.6747], dtype=torch.float64)
  mean dice: 0.9316
average dice:(0.9896, 0.8964, 0.9873, 0.8446, 0.8741)
best mean dice: -1.0000    
Valid_Epoch :  80%|███████████████████████▏     | 16/20 [02:46<00:40, 10.03s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-27 09:05:49,684 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9016403/9016403_ori.nii.gz
2023-02-27 09:05:51,351 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9016403/9016403_seg.nii.gz
2023-02-27 09:05:52,026 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9016403/9016403_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.5063, 0.7911, 0.7598, 0.6321, 0.6905], dtype=torch.float64)
  mean dice: 0.9152
average dice:(0.9864, 0.8439, 0.9776, 0.8206, 0.8661)
best mean dice: -1.0000    
Valid_Epoch :  85%|████████████████████████▋    | 17/20 [02:56<00:30, 10.06s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-27 09:06:00,598 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9016918/9016918_ori.nii.gz
2023-02-27 09:06:02,239 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9016918/9016918_seg.nii.gz
2023-02-27 09:06:02,944 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9016918/9016918_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.6371, 0.6553, 0.4927, 0.5466, 0.6706], dtype=torch.float64)
  mean dice: 0.9173
average dice:(0.9838, 0.8817, 0.9874, 0.8169, 0.8373)
best mean dice: -1.0000    
Valid_Epoch :  90%|██████████████████████████   | 18/20 [03:06<00:20, 10.30s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-27 09:06:10,398 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9017909/9017909_ori.nii.gz
2023-02-27 09:06:12,030 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9017909/9017909_seg.nii.gz
2023-02-27 09:06:12,727 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9017909/9017909_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.4593, 0.6146, 0.5515, 0.6566, 0.6394], dtype=torch.float64)
  mean dice: 0.9299
average dice:(0.9874, 0.8978, 0.9842, 0.8535, 0.8589)
best mean dice: -1.0000    
Valid_Epoch :  95%|███████████████████████████▌ | 19/20 [03:16<00:10, 10.17s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-27 09:06:20,193 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9019287/9019287_ori.nii.gz
2023-02-27 09:06:21,865 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9019287/9019287_seg.nii.gz
2023-02-27 09:06:22,518 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0227/9019287/9019287_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.5001, 0.6803, 0.4675, 0.4171, 0.5164], dtype=torch.float64)
  mean dice: 0.9449
average dice:(0.9858, 0.8906, 0.9868, 0.9033, 0.9063)
best mean dice: -1.0000    
Valid_Epoch : 100%|█████████████████████████████| 20/20 [03:26<00:00, 10.33s/it]
val takes:206.7463

未应用后处理
ssh://dluser@10.1.15.80:22/home/dluser/anaconda3/envs/han/bin/python -u /home/dluser/.pycharm_helpers/pydev/pydevconsole.py --mode=server
import sys; print('Python %s on %s' % (sys.version, sys.platform))
sys.path.extend(['/home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation', '/home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation'])
Python 3.8.12 (default, Oct 12 2021, 13:49:34) 
Type 'copyright', 'credits' or 'license' for more information
IPython 8.1.1 -- An enhanced Interactive Python. Type '?' for help.
PyDev console: using IPython 8.1.1
Python 3.8.12 (default, Oct 12 2021, 13:49:34) 
[GCC 7.5.0] on linux
runfile('/home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/test_nnunet.py', wdir='/home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation')
/home/dluser/anaconda3/envs/han/lib/python3.8/site-packages/apex/pyprof/__init__.py:5: FutureWarning: pyprof will be removed by the end of June, 2022
  warnings.warn("pyprof will be removed by the end of June, 2022", FutureWarning)
Number of validating images per epoch: 20
Loading dataset: 100%|████████████████████████████| 6/6 [00:01<00:00,  3.40it/s]
Valid_Epoch :   0%|                                      | 0/20 [00:01<?, ?it/s](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-26 22:25:43,200 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9001104/9001104_ori.nii.gz
2023-02-26 22:25:44,853 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9001104/9001104_seg.nii.gz
2023-02-26 22:25:45,472 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9001104/9001104_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.8578, 0.8604, 9.4379, 3.4626, 0.5652], dtype=torch.float64)
average dice:(0.9830, 0.8437, 0.9694, 0.8291, 0.8673)
best mean dice: -1.0000    
Valid_Epoch :   5%|█▌                            | 1/20 [00:14<04:37, 14.60s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-26 22:25:53,906 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9002430/9002430_ori.nii.gz
2023-02-26 22:25:55,692 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9002430/9002430_seg.nii.gz
2023-02-26 22:25:56,367 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9002430/9002430_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.5664, 0.7432, 0.8165, 1.5421, 1.2619], dtype=torch.float64)
average dice:(0.9860, 0.8952, 0.9870, 0.8526, 0.8954)
best mean dice: -1.0000    
Valid_Epoch :  10%|███                           | 2/20 [00:25<03:43, 12.39s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-26 22:26:03,596 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9002817/9002817_ori.nii.gz
2023-02-26 22:26:05,389 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9002817/9002817_seg.nii.gz
2023-02-26 22:26:06,218 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9002817/9002817_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.5254, 0.7965, 1.2126, 0.9873, 0.9014], dtype=torch.float64)
average dice:(0.9859, 0.8653, 0.9822, 0.8410, 0.8193)
best mean dice: -1.0000    
Valid_Epoch :  15%|████▌                         | 3/20 [00:35<03:12, 11.34s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-26 22:26:15,235 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9003430/9003430_ori.nii.gz
2023-02-26 22:26:16,888 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9003430/9003430_seg.nii.gz
2023-02-26 22:26:17,578 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9003430/9003430_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([1.1545, 0.7443, 4.0185, 1.0587, 0.6190], dtype=torch.float64)
average dice:(0.9854, 0.8826, 0.9829, 0.8422, 0.9060)
best mean dice: -1.0000    
Valid_Epoch :  20%|██████                        | 4/20 [00:46<03:00, 11.25s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-26 22:26:27,866 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9004175/9004175_ori.nii.gz
2023-02-26 22:26:29,515 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9004175/9004175_seg.nii.gz
2023-02-26 22:26:30,224 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9004175/9004175_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.4173, 0.6188, 1.0841, 1.5294, 1.4841], dtype=torch.float64)
average dice:(0.9904, 0.9073, 0.9877, 0.9069, 0.8957)
best mean dice: -1.0000    
Valid_Epoch :  25%|███████▌                      | 5/20 [00:59<02:56, 11.76s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-26 22:26:41,978 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9005075/9005075_ori.nii.gz
2023-02-26 22:26:43,594 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9005075/9005075_seg.nii.gz
2023-02-26 22:26:44,264 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9005075/9005075_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([1.7287, 0.7187, 1.9660, 2.9844, 3.1267], dtype=torch.float64)
average dice:(0.9847, 0.8969, 0.9772, 0.8446, 0.8615)
best mean dice: -1.0000    
Valid_Epoch :  30%|█████████                     | 6/20 [01:13<02:55, 12.54s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-26 22:26:52,312 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9005132/9005132_ori.nii.gz
2023-02-26 22:26:53,985 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9005132/9005132_seg.nii.gz
2023-02-26 22:26:54,610 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9005132/9005132_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.5885, 0.6701, 0.6685, 0.9361, 0.7349], dtype=torch.float64)
average dice:(0.9836, 0.8852, 0.9873, 0.8600, 0.8856)
best mean dice: -1.0000    
Valid_Epoch :  35%|██████████▌                   | 7/20 [01:23<02:33, 11.82s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-26 22:27:03,026 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9006723/9006723_ori.nii.gz
2023-02-26 22:27:04,799 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9006723/9006723_seg.nii.gz
2023-02-26 22:27:05,488 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9006723/9006723_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.7307, 0.6881, 0.6341, 0.7456, 0.8609], dtype=torch.float64)
average dice:(0.9849, 0.8983, 0.9879, 0.8005, 0.8714)
best mean dice: -1.0000    
Valid_Epoch :  40%|████████████                  | 8/20 [01:34<02:18, 11.53s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-26 22:27:13,106 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9007827/9007827_ori.nii.gz
2023-02-26 22:27:14,744 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9007827/9007827_seg.nii.gz
2023-02-26 22:27:15,364 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9007827/9007827_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.5067, 0.7347, 0.6339, 1.0193, 0.4699], dtype=torch.float64)
average dice:(0.9880, 0.8588, 0.9855, 0.7736, 0.8982)
best mean dice: -1.0000    
Valid_Epoch :  45%|█████████████▌                | 9/20 [01:44<02:01, 11.00s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-26 22:27:29,344 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9008561/9008561_ori.nii.gz
2023-02-26 22:27:31,086 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9008561/9008561_seg.nii.gz
2023-02-26 22:27:31,791 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9008561/9008561_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([8.6006, 0.6209, 4.9823, 2.8870, 1.5957], dtype=torch.float64)
average dice:(0.9658, 0.8866, 0.9820, 0.8063, 0.8711)
best mean dice: -1.0000    
Valid_Epoch :  50%|██████████████▌              | 10/20 [02:00<02:06, 12.68s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-26 22:27:39,279 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9011115/9011115_ori.nii.gz
2023-02-26 22:27:41,021 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9011115/9011115_seg.nii.gz
2023-02-26 22:27:41,699 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9011115/9011115_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.6068, 0.6697, 1.4392, 2.1689, 1.1655], dtype=torch.float64)
average dice:(0.9837, 0.8832, 0.9799, 0.8133, 0.8874)
best mean dice: -1.0000    
Valid_Epoch :  55%|███████████████▉             | 11/20 [02:10<01:46, 11.84s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-26 22:27:55,265 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9011420/9011420_ori.nii.gz
2023-02-26 22:27:56,869 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9011420/9011420_seg.nii.gz
2023-02-26 22:27:57,557 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9011420/9011420_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([5.6295, 0.6892, 7.2790, 1.4690, 1.9595], dtype=torch.float64)
average dice:(0.9785, 0.9032, 0.9764, 0.8829, 0.8608)
best mean dice: -1.0000    
Valid_Epoch :  60%|█████████████████▍           | 12/20 [02:26<01:44, 13.06s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-26 22:28:05,500 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9012867/9012867_ori.nii.gz
2023-02-26 22:28:07,114 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9012867/9012867_seg.nii.gz
2023-02-26 22:28:07,763 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9012867/9012867_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.6663, 0.9860, 3.6149, 7.4864, 9.7302], dtype=torch.float64)
average dice:(0.9830, 0.8485, 0.9724, 0.7568, 0.8332)
best mean dice: -1.0000    
Valid_Epoch :  65%|██████████████████▊          | 13/20 [02:36<01:25, 12.19s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-26 22:28:15,887 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9013161/9013161_ori.nii.gz
2023-02-26 22:28:17,501 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9013161/9013161_seg.nii.gz
2023-02-26 22:28:18,175 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9013161/9013161_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([ 1.2636,  1.0896,  2.6831, 11.3575,  1.3126], dtype=torch.float64)
average dice:(0.9717, 0.8086, 0.9713, 0.4651, 0.6802)
best mean dice: -1.0000    
Valid_Epoch :  70%|████████████████████▎        | 14/20 [02:47<01:10, 11.69s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-26 22:28:30,369 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9013798/9013798_ori.nii.gz
2023-02-26 22:28:32,031 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9013798/9013798_seg.nii.gz
2023-02-26 22:28:32,682 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9013798/9013798_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([7.5471, 0.6629, 8.8858, 4.6256, 0.5281], dtype=torch.float64)
average dice:(0.9669, 0.8938, 0.9726, 0.8295, 0.8704)
best mean dice: -1.0000    
Valid_Epoch :  75%|█████████████████████▊       | 15/20 [03:01<01:02, 12.50s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-26 22:28:40,645 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9015718/9015718_ori.nii.gz
2023-02-26 22:28:42,279 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9015718/9015718_seg.nii.gz
2023-02-26 22:28:42,905 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9015718/9015718_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.4039, 0.5966, 0.8078, 1.2860, 1.4592], dtype=torch.float64)
average dice:(0.9896, 0.8964, 0.9871, 0.8426, 0.8714)
best mean dice: -1.0000    
Valid_Epoch :  80%|███████████████████████▏     | 16/20 [03:12<00:47, 11.83s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-26 22:28:51,822 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9016403/9016403_ori.nii.gz
2023-02-26 22:28:53,459 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9016403/9016403_seg.nii.gz
2023-02-26 22:28:54,132 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9016403/9016403_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([3.1630, 0.8609, 1.2632, 0.6821, 1.2471], dtype=torch.float64)
average dice:(0.9854, 0.8427, 0.9768, 0.8204, 0.8574)
best mean dice: -1.0000    
Valid_Epoch :  85%|████████████████████████▋    | 17/20 [03:23<00:34, 11.65s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-26 22:29:05,036 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9016918/9016918_ori.nii.gz
2023-02-26 22:29:06,919 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9016918/9016918_seg.nii.gz
2023-02-26 22:29:07,759 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9016918/9016918_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.9621, 0.6914, 2.1194, 3.3150, 1.7989], dtype=torch.float64)
average dice:(0.9835, 0.8814, 0.9870, 0.8094, 0.8309)
best mean dice: -1.0000    
Valid_Epoch :  90%|██████████████████████████   | 18/20 [03:37<00:24, 12.28s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-26 22:29:15,181 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9017909/9017909_ori.nii.gz
2023-02-26 22:29:16,898 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9017909/9017909_seg.nii.gz
2023-02-26 22:29:17,528 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9017909/9017909_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([0.6562, 1.0182, 1.0472, 0.8551, 0.7059], dtype=torch.float64)
average dice:(0.9865, 0.8913, 0.9840, 0.8531, 0.8588)
best mean dice: -1.0000    
Valid_Epoch :  95%|███████████████████████████▌ | 19/20 [03:46<00:11, 11.49s/it](1, 160, 384, 384) (6, 160, 384, 384) (6, 160, 384, 384)
2023-02-26 22:29:28,083 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9019287/9019287_ori.nii.gz
2023-02-26 22:29:29,828 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9019287/9019287_seg.nii.gz
2023-02-26 22:29:30,685 INFO image_writer.py:194 - writing: /home/dluser/dataset/nnUNetFrame/Pytorch--3D-Medical-Images-Segmentation/checkpoint/0226/9019287/9019287_gt.nii.gz
channel wise Metric on original image spacing(no BG) asd:  tensor([ 5.5959,  0.6880, 16.5183,  1.3181,  0.5840], dtype=torch.float64)
average dice:(0.9774, 0.8906, 0.9789, 0.9009, 0.9062)
best mean dice: -1.0000    
Valid_Epoch : 100%|█████████████████████████████| 20/20 [03:59<00:00, 12.00s/it]
val takes:240.0662