项目场景：

最近在用UNETR做医学图像分割，在用官方的tutorial跑自己的数据集时出现了报错不能训练

问题描述

例如：在前面的transform设置，dataset和dataloader都能正常运行，在训练的时候下面这句代码

global_step, dice_val_best, global_step_best = train(global_step, train_loader, dice_val_best, global_step_best)

报错如下：

RuntimeError: Caught RuntimeError in DataLoader worker process 0.
Original Traceback (most recent call last):File "/opt/conda/lib/python3.8/site-packages/monai/transforms/transform.py", line 89, in apply_transformreturn _apply_transform(transform, data, unpack_items)File "/opt/conda/lib/python3.8/site-packages/monai/transforms/transform.py", line 53, in _apply_transformreturn transform(parameters)File "/opt/conda/lib/python3.8/site-packages/monai/transforms/croppad/dictionary.py", line 1171, in __call__self.randomize(label, fg_indices, bg_indices, image)File "/opt/conda/lib/python3.8/site-packages/monai/transforms/croppad/dictionary.py", line 1153, in randomizeself.centers = generate_pos_neg_label_crop_centers(File "/opt/conda/lib/python3.8/site-packages/monai/transforms/utils.py", line 512, in generate_pos_neg_label_crop_centerscenters.append(correct_crop_centers(center, spatial_size, label_spatial_shape, allow_smaller))File "/opt/conda/lib/python3.8/site-packages/monai/transforms/utils.py", line 439, in correct_crop_centersraise ValueError("The size of the proposed random crop ROI is larger than the image size.")
ValueError: The size of the proposed random crop ROI is larger than the image size.The above exception was the direct cause of the following exception:Traceback (most recent call last):File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 198, in _worker_loopdata = fetcher.fetch(index)File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetchdata = [self.dataset[idx] for idx in possibly_batched_index]File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 44, in <listcomp>data = [self.dataset[idx] for idx in possibly_batched_index]File "/opt/conda/lib/python3.8/site-packages/monai/data/dataset.py", line 97, in __getitem__return self._transform(index)File "/opt/conda/lib/python3.8/site-packages/monai/data/dataset.py", line 807, in _transformdata = apply_transform(_transform, data)File "/opt/conda/lib/python3.8/site-packages/monai/transforms/transform.py", line 113, in apply_transformraise RuntimeError(f"applying transform {transform}") from e
RuntimeError: applying transform <monai.transforms.croppad.dictionary.RandCropByPosNegLabeld object at 0x7f3c221e9340>

不知道怎么解决把num_works改为了0依然报错。
查了这句报错：ValueError: The size of the proposed random crop ROI is larger than the image size参考.说是该错误是由于ROI裁剪过大而无法覆盖整个输入图像体积造成的。它与网络架构无关，但与数据加载器相关。于是找到transform设置中把spatial_size=(96, 96, 96)改成spatial_size=(48, 48, 48)

train_transforms = Compose([LoadImaged(keys=["image", "label"]),AddChanneld(keys=["image", "label"]),Orientationd(keys=["image", "label"], axcodes="RAS"),Spacingd(keys=["image", "label"],pixdim=(1.5, 1.5, 2.0),mode=("bilinear", "nearest"),),ScaleIntensityRanged(keys=["image"],a_min=-175,a_max=250,b_min=0.0,b_max=1.0,clip=True,),CropForegroundd(keys=["image", "label"], source_key="image"),RandCropByPosNegLabeld(keys=["image", "label"],label_key="label",
#             spatial_size=(96, 96, 96),spatial_size=(48, 48, 48),pos=1,neg=1,num_samples=4,image_key="image",image_threshold=0,),RandFlipd(keys=["image", "label"],spatial_axis=[0],prob=0.10,),RandFlipd(keys=["image", "label"],spatial_axis=[1],prob=0.10,),RandFlipd(keys=["image", "label"],spatial_axis=[2],prob=0.10,),RandRotate90d(keys=["image", "label"],prob=0.10,max_k=3,),RandShiftIntensityd(keys=["image"],offsets=0.10,prob=0.50,),ToTensord(keys=["image", "label"]),]
)

但是训练模型时又报了新的错误，报错信息如下：

RuntimeError: The size of tensor a (27) must match the size of tensor b (216) at non-singleton dimension 1

原因分析：

ROI裁剪尺寸大于图片本身了，

解决方案：

在调用UNETR模型时，参数img_size=(96, 96, 96)改为img_size=(32, 32, 32)

RuntimeError: applying transform ＜monai.transforms.croppad.dictionary.RandCropByPosNegLabeld object相关推荐

python transform方法_Python transforms.BboxTransformFrom方法代码示例
# 需要导入模块: from matplotlib import transforms [as 别名] # 或者: from matplotlib.transforms import BboxTran ...
取消打印Tensorflow中的无用信息，如tensorflow:AutoGraph could not transform ＜*＞ and will run it as-is、加载CUDA信息等
取消打印Tensorflow中的无用信息,如WARNING:tensorflow:AutoGraph could not transform bound method BatchNorm.call o ...
【无标题】Python学习中的小问题1＜built-in method lower of str object at 0x0000026B858CF8F0
这里写自定义目录标题生成一个适合你的列表创建一个表格设定内容居中.居左.居右 SmartyPants 创建一个自定义列表如何创建一个注脚注释也是必不可少的 KaTeX数学公式新的甘特图功能 ...
成功解决＜pandas.core.groupby.generic.DataFrameGroupBy object at 0x0000024489925F60＞
成功解决<pandas.core.groupby.generic.DataFrameGroupBy object at 0x0000024489925F60> 目录解决问题解决方法解 ...
monai.tansforms.xxx 常用函数作用
1.monai.transforms.LoadPNG(image_only=False, dtype=<class 'numpy.float32'>) 作用:加载常用的2维图像,格式包括 ...
Transforms CTM, 转换矩阵
Quartz转换实现的原理:Quartz把绘图分成两个部分, 用户空间,即和设备无关, 设备空间, 用户空间和设备空间中间存在一个转换矩阵 : CTM 本章实质是讲解CTM Quartz提供的3大功能 ...
torchvision.transforms 的CenterCrop()：在图片的中间区域进行裁剪
pytorch中transform函数 torchvision.transforms是pytorch中的图像预处理包一般用Compose把多个步骤整合到一起: 比如说 transforms.Comp ...
Pytorch专题实战——数据转换(Dataset Transforms)
文章目录 1.导入必要模块 2.定义数据处理类 3.定义numpy转化为tensor类 4.定义乘法转化类 5.打印结果 5.1.未转化前 5.2.tensor转化 5.3.乘法转化 1.导入必要模块 ...
ABP +VUE Elment 通用高级查询（右键菜单）设计+LINQ通用类Expression＜Func＜TFields, bool＞＞方法
ABP +VUE Elment 通用高级查询(右键菜单)设计+LINQ通用类Expression 1. 目前需要用VUE实现源cs系统报表的右键菜单所有和自定义查询功能. 1.1 CS端的右键菜单效果 ...

RuntimeError: applying transform ＜monai.transforms.croppad.dictionary.RandCropByPosNegLabeld object

项目场景：

问题描述

原因分析：

解决方案：

RuntimeError: applying transform ＜monai.transforms.croppad.dictionary.RandCropByPosNegLabeld object相关推荐

最新文章

热门文章