不知道如何生成采样位置：

Question

统一采样器中的尺寸是如何生成的？我尝试调试图像大小，它似乎适用于某些迭代，但不适用于其他迭代。任何想法如何解决这个问题。我的配置如下：

[自定义]

• 类数：14

• output_prob：真

• label_normalisation：真

• softmax：真

• min_sampling_ratio: 0

• 强制标签：(0, 1)

• rand_samples: 0

• min_numb_labels: 1

• proba_connect: 真

• evaluation_units：前景

• 图像：（'图像'，）

• 标签：('label',)

• 重量：()

• 采样器：()

• 推断：()

名称：net_segment

[配置文件]

• 路径：/home/ubuntu/niftynet/extensions/deepmedic/deepmedic_all_task_renambed_labels.ini

[图片]

• csv_file:

• path_to_search: /home/ubuntu/med_deacthalon/Task_all_same_names/imagesTr_1

• filename_contains: ()

• filename_not_contains: ('lung',)

• interp_order: 3

• 加载器：无

• pixdim: (1.0, 1.0, 1.0)

• axcodes: ('A', 'R', 'S')

• spatial_window_size: (51, 51, 51)

[标签]

-csv_file:

• path_to_search: /home/ubuntu/med_deacthalon/Task_all_same_names/labelsTr_1

• filename_contains: ()

• filename_not_contains: ('lung',)

• interp_order: 3

• 加载器：无

• pixdim: (1.0, 1.0, 1.0)

• axcodes: ('A', 'R', 'S')

• spatial_window_size: (9, 9, 9)

[系统]

• cuda_devices: ""

• 线程数：2

• num_gpus: 1

• model_dir：/home/ubuntu/models_nifty/deepmedic/all_task_same_name_rename_labels

• dataset_split_file: ./dataset_split.csv

• 动作：训练

[网络]

• 姓名：deepmedic

• activation_function: relu

• batch_size: 32

• 衰减：0.0

• reg_type: L2

• volume_padding_size: (21, 21, 21)

• volume_padding_mode：最小

• window_sampling：统一

• queue_length：128

• multimod_foreground_type：和

• histogram_ref_file: histogram_standardisation_alltask.txt

• norm_type：百分位数

• 截止值：(0.01, 0.99)

• foreground_type: otsu_plus

• 标准化：错误

• 美白：是的

• normalise_foreground_only: True

• weight_initializer: he_normal

• bias_initializer：零

• keep_prob: 1.0

• weight_initializer_args：{}

• bias_initializer_args：{}

[训练]

• 优化器：亚当

• sample_per_volume：32

• 旋转角度：(-10.0, 10.0)

• rotation_angle_x: ()

• rotation_angle_y: ()

• rotation_angle_z: ()

• scaling_percentage: (-10.0, 10.0)

• random_flipping_axes：-1

• do_elastic_deformation: False

• num_ctrl_points: 4

• deformation_sigma：15

• proportion_to_deform：0.5

• lr：0.001

• loss_type：骰子

• starting_iter: 0

• save_every_n: 45

• tensorboard_every_n：20

• max_iter: 10

• 最大检查点数：20

• validation_every_n: -1

• validation_max_iter: 1

• exclude_fraction_for_validation：0.0

• exclude_fraction_for_inference：0.0

[推断]

• spatial_window_size: (57, 57, 57)

• inference_iter: -1

• dataset_to_infer：

• save_seg_dir: ./deepmedic/alltask_newname

• 输出后缀：_niftynet_out

• output_interp_order: 0

• 边框：(36, 36, 36)

CRITICAL:niftynet: Don't know how to generate sampling locations: Spatial dimensions of the grouped input sources are not consistent. {(477, 451, 187), (391, 369, 147)} Exception in thread Thread-2: Traceback (most recent call last): File "/home/ubuntu/anaconda3/envs/python3/lib/python3.6/threading.py", line 916, in _bootstrap_inner self.run() File "/home/ubuntu/anaconda3/envs/python3/lib/python3.6/threading.py", line 864, in run self._target(*self._args, **self._kwargs) File "/home/ubuntu/niftynet/NiftyNet/niftynet/engine/image_window_buffer.py", line 148, in _push for output_dict in self(): File "/home/ubuntu/niftynet/NiftyNet/niftynet/engine/sampler_uniform.py", line 81, in layer_op self.window.n_samples) File "/home/ubuntu/niftynet/NiftyNet/niftynet/engine/sampler_uniform.py", line 151, in _spatial_coordinates_generator _infer_spatial_size(img_sizes, win_sizes) File "/home/ubuntu/niftynet/NiftyNet/niftynet/engine/sampler_uniform.py", line 238, in _infer_spatial_size raise NotImplementedError NotImplementedError

Answer 1

问题在这里解决：https://github.com/NifTK/NiftyNet/issues/170

在配置文件中设置pixdim 时，摘要图像和标签应在其标题中存储相同的体素间距值。