运行 python bigImgSeg.py 报错 #8
Comments
|
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 |
|
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 |
|
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） |
|
|
|
|
|
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 |
|
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 |
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 |
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…… |
|
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 |
|
torch YOLOv5 requirementsUsage: pip install -r requirements.txtBase ------------------------------------------------------------------------gitpython>=3.1.30 ultralytics>=8.0.100protobuf<=3.20.1 # ultralytics/yolov5#8012Logging ---------------------------------------------------------------------tensorboard>=2.4.1clearml>=1.2.0cometPlotting --------------------------------------------------------------------pandas>=1.1.4 Export ----------------------------------------------------------------------coremltools>=6.0 # CoreML exportonnx>=1.10.0 # ONNX exportonnx-simplifier>=0.4.1 # ONNX simplifiernvidia-pyindex # TensorRT exportnvidia-tensorrt # TensorRT exportscikit-learn<=1.1.2 # CoreML quantizationtensorflow>=2.4.0 # TF exports (-cpu, -aarch64, -macos)tensorflowjs>=3.9.0 # TF.js exportopenvino-dev # OpenVINO exportDeploy ----------------------------------------------------------------------setuptools>=65.5.1 # Snyk vulnerability fix tritonclient[all]~=2.24.0Extras ----------------------------------------------------------------------ipython # interactive notebookmss # screenshotsalbumentations>=1.0.3pycocotools>=2.0.6 # COCO mAP |
1 similar comment
|
torch YOLOv5 requirementsUsage: pip install -r requirements.txtBase ------------------------------------------------------------------------gitpython>=3.1.30 ultralytics>=8.0.100protobuf<=3.20.1 # ultralytics/yolov5#8012Logging ---------------------------------------------------------------------tensorboard>=2.4.1clearml>=1.2.0cometPlotting --------------------------------------------------------------------pandas>=1.1.4 Export ----------------------------------------------------------------------coremltools>=6.0 # CoreML exportonnx>=1.10.0 # ONNX exportonnx-simplifier>=0.4.1 # ONNX simplifiernvidia-pyindex # TensorRT exportnvidia-tensorrt # TensorRT exportscikit-learn<=1.1.2 # CoreML quantizationtensorflow>=2.4.0 # TF exports (-cpu, -aarch64, -macos)tensorflowjs>=3.9.0 # TF.js exportopenvino-dev # OpenVINO exportDeploy ----------------------------------------------------------------------setuptools>=65.5.1 # Snyk vulnerability fix tritonclient[all]~=2.24.0Extras ----------------------------------------------------------------------ipython # interactive notebookmss # screenshotsalbumentations>=1.0.3pycocotools>=2.0.6 # COCO mAP |
|
@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 |
|
|
试试 如果仍然存在问题 继续反馈给我们 |
(segstone) root@autodl-container-d04f44a835-2d5c31f5:
/project/StoneSegmentator/tools/splitSeg# python bigImgSeg.py/project/StoneSegmentator/tools/splitSeg#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:
The text was updated successfully, but these errors were encountered: