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:
[风俗]
类数:14
输出概率:真
标签标准化:真
软最大:真
min_sampling_ratio: 0
强制标签:(0, 1)
rand_samples:0
min_numb_labels:1
proba_connect:真
评估单位:前景
图像:('图像',)
标签:('标签',)
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
文件名包含:()
filename_not_contains: ('肺',)
interp_order:3
装载机:无
pixdim: (1.0, 1.0, 1.0)
轴码:('A','R','S')
空间窗口大小:(51、51、51)
[标签]
-csv_file:
path_to_search: /home/ubuntu/med_deacthalon/Task_all_same_names/labelsTr_1
文件名包含:()
filename_not_contains: ('肺',)
interp_order:3
装载机:无
pixdim: (1.0, 1.0, 1.0)
轴码:('A','R','S')
空间窗口大小:(9、9、9)
[系统]
cuda_devices:“”
线程数:2
num_gpus:1
模型目录:/home/ubuntu/models_nifty/deepmedic/all_task_same_name_rename_labels
dataset_split_file: ./dataset_split.csv
动作:火车
[网络]
名称:深度医学
激活函数:relu
批量大小:32
衰减:0.0
reg_type:L2
volume_padding_size: (21, 21, 21)
volume_padding_mode:最小
window_sampling:统一
队列长度:128
multimod_foreground_type:和
histogram_ref_file: histogram_standardisation_alltask.txt
norm_type:百分位数
截止:(0.01,0.99)
前景类型:otsu_plus
标准化:错误
美白:真
normalise_foreground_only:真
weight_initializer: he_normal
偏差初始化器:零
保持概率:1.0
weight_initializer_args:{}
偏差初始化器参数:{}
[训练]
优化师:亚当
sample_per_volume: 32
旋转角度:(-10.0,10.0)
旋转角度x:()
旋转角度y:()
旋转角度z:()
scaling_percentage: (-10.0, 10.0)
随机翻转轴:-1
do_elastic_deformation: 假
num_ctrl_points:4
变形西格玛:15
比例变形:0.5
LR:0.001
loss_type: 骰子
起始迭代器:0
save_every_n:45
张量板_每个_n:20
最大迭代器:10
最大检查点:20
验证_每个_n:-1
验证最大迭代器:1
exclude_fraction_for_validation:0.0
exclude_fraction_for_inference:0.0
[推理]
空间窗口大小:(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
边界:(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