TDIT-haha / StoneSegmentator

0 stars 0 forks source link

运行 python bigImgSeg.py 报错 #8

Closed cgliu2000 closed 1 year ago

cgliu2000 commented 1 year ago

(segstone) root@autodl-container-d04f44a835-2d5c31f5:~/project/StoneSegmentator/tools/splitSeg# python bigImgSeg.py Traceback (most recent call last): File "bigImgSeg.py", line 5, in import torch File "/root/miniconda3/envs/segstone/lib/python3.8/site-packages/torch/init.py", line 229, in from torch._C import * # noqa: F403 ImportError: /root/miniconda3/envs/segstone/lib/python3.8/site-packages/torch/lib/libtorch_cuda.so: undefined symbol: cudaGraphInstantiateWithFlags, version libcudart.so.11.0 (segstone) root@autodl-container-d04f44a835-2d5c31f5:~/project/StoneSegmentator/tools/splitSeg# image

OroChippw commented 1 year ago

在哪个服务器上面运行的?这个bug是怎么触发的?之前我更换服务器应该已经解决这个环境问题了,而且流程已经全部走通过一次了

cgliu2000 commented 1 year ago

3090那个服务器,没换

OroChippw commented 1 year ago

3090那个服务器,没换

你输入以下几个指令分别截图以下结果给我们看看 1、pip list ,这个不用全部截,就看看torch 和torchvision的版本就行了 2、nvcc -V 3、nvidia-smi

cgliu2000 commented 1 year ago

还要请问labelme怎么调整标注的问题,需要用哪个文件夹(似乎只能打开images)

cgliu2000 commented 1 year ago

image image ![Uploading image.png…]()

cgliu2000 commented 1 year ago

image

OroChippw commented 1 year ago

你中间是否在SAM项目中运行了pip install -r requirements的指令 我给你初始化环境的torch版本是1.11.0 + cu113 ,在你使用SAM的时候里面的requirements会要求使用torch2.0.x以上的版本 ,那个是用于将SAM模型从torch转化为onnx用的,这样子就会引起冲突

OroChippw commented 1 year ago

image

labelme我许久没用过了 ,如果你是要打开保存标签的文件夹 ,应该是labels,如果不对的话换成json就好了,多试试

cgliu2000 commented 1 year ago

你中间是否在SAM项目中运行了pip install -r requirements的指令 我给你初始化环境的torch版本是1.11.0 + cu113 ,在你使用SAM的时候里面的requirements会要求使用torch2.0.x以上的版本 ,那个是用于将SAM模型从torch转化为onnx用的,这样子就会引起冲突

在你最后一次修改代码之后,我自己尝试跑的时候,运行过一次pip install -r requirements

cgliu2000 commented 1 year ago

image

labelme我许久没用过了 ,如果你是要打开保存标签的文件夹 ,应该是labels,如果不对的话换成json就好了,多试试

打开jsons文件夹是空的。打开单个json文件是不允许打开的。究竟要怎么打开标注嘛…… image

OroChippw commented 1 year ago

你运行的requirements.txt内容给我看看

cgliu2000 commented 1 year ago

你运行的requirements.txt内容给我看看

现在重新运行requirements.txt吗?

OroChippw commented 1 year ago

你运行的requirements.txt内容给我看看

现在重新运行requirements.txt吗?

不用 打开requirements.txt里面的内容粘贴给我看看

cgliu2000 commented 1 year ago

torch torchvision certifi charset-normalizer coloredlogs contourpy cycler flatbuffers fonttools gitdb GitPython humanfriendly idna importlib-resources kiwisolver matplotlib mpmath numpy onnx onnxruntime-gpu opencv-python packaging pandas Pillow protobuf psutil pyparsing python-dateutil pytz PyYAML requests scipy seaborn six smmap sympy thop tqdm typing_extensions tzdata urllib3 zipp labelme pandas seaborn

YOLOv5 requirements

Usage: pip install -r requirements.txt

Base ------------------------------------------------------------------------

gitpython>=3.1.30 matplotlib>=3.3 numpy>=1.18.5 opencv-python>=4.1.1 Pillow>=7.1.2 psutil # system resources PyYAML>=5.3.1 requests>=2.23.0 scipy>=1.4.1 thop>=0.1.1 # FLOPs computation torch>=1.7.0 # see https://pytorch.org/get-started/locally (recommended) torchvision>=0.8.1 tqdm>=4.64.0

ultralytics>=8.0.100

protobuf<=3.20.1 # https://github.com/ultralytics/yolov5/issues/8012

Logging ---------------------------------------------------------------------

tensorboard>=2.4.1

clearml>=1.2.0

comet

Plotting --------------------------------------------------------------------

pandas>=1.1.4 seaborn>=0.11.0

Export ----------------------------------------------------------------------

coremltools>=6.0 # CoreML export

onnx>=1.10.0 # ONNX export

onnx-simplifier>=0.4.1 # ONNX simplifier

nvidia-pyindex # TensorRT export

nvidia-tensorrt # TensorRT export

scikit-learn<=1.1.2 # CoreML quantization

tensorflow>=2.4.0 # TF exports (-cpu, -aarch64, -macos)

tensorflowjs>=3.9.0 # TF.js export

openvino-dev # OpenVINO export

Deploy ----------------------------------------------------------------------

setuptools>=65.5.1 # Snyk vulnerability fix

tritonclient[all]~=2.24.0

Extras ----------------------------------------------------------------------

ipython # interactive notebook

mss # screenshots

albumentations>=1.0.3

pycocotools>=2.0.6 # COCO mAP

cgliu2000 commented 1 year ago

torch torchvision certifi charset-normalizer coloredlogs contourpy cycler flatbuffers fonttools gitdb GitPython humanfriendly idna importlib-resources kiwisolver matplotlib mpmath numpy onnx onnxruntime-gpu opencv-python packaging pandas Pillow protobuf psutil pyparsing python-dateutil pytz PyYAML requests scipy seaborn six smmap sympy thop tqdm typing_extensions tzdata urllib3 zipp labelme pandas seaborn

YOLOv5 requirements

Usage: pip install -r requirements.txt

Base ------------------------------------------------------------------------

gitpython>=3.1.30 matplotlib>=3.3 numpy>=1.18.5 opencv-python>=4.1.1 Pillow>=7.1.2 psutil # system resources PyYAML>=5.3.1 requests>=2.23.0 scipy>=1.4.1 thop>=0.1.1 # FLOPs computation torch>=1.7.0 # see https://pytorch.org/get-started/locally (recommended) torchvision>=0.8.1 tqdm>=4.64.0

ultralytics>=8.0.100

protobuf<=3.20.1 # https://github.com/ultralytics/yolov5/issues/8012

Logging ---------------------------------------------------------------------

tensorboard>=2.4.1

clearml>=1.2.0

comet

Plotting --------------------------------------------------------------------

pandas>=1.1.4 seaborn>=0.11.0

Export ----------------------------------------------------------------------

coremltools>=6.0 # CoreML export

onnx>=1.10.0 # ONNX export

onnx-simplifier>=0.4.1 # ONNX simplifier

nvidia-pyindex # TensorRT export

nvidia-tensorrt # TensorRT export

scikit-learn<=1.1.2 # CoreML quantization

tensorflow>=2.4.0 # TF exports (-cpu, -aarch64, -macos)

tensorflowjs>=3.9.0 # TF.js export

openvino-dev # OpenVINO export

Deploy ----------------------------------------------------------------------

setuptools>=65.5.1 # Snyk vulnerability fix

tritonclient[all]~=2.24.0

Extras ----------------------------------------------------------------------

ipython # interactive notebook

mss # screenshots

albumentations>=1.0.3

pycocotools>=2.0.6 # COCO mAP

TDIT-haha commented 1 year ago

@lugushaoye labelme的使用我会简单录制一个视频讲解下使用的方式针对我们的项目,这样应该能解决你的问题。至于环境问题,鉴于你的情况,我会重新查看下,目前我建议你在环境中执行pip install torchvision==0.14.0,再试试

cgliu2000 commented 1 year ago

image 版本改了。我再试试

OroChippw commented 1 year ago

image 版本改了。我再试试

试试 如果仍然存在问题 继续反馈给我们