Panoptic driving Perception (HybridNets-ONNX)

#ONNX-HybridNets-Multitask-Road-Detection

https://github.com/ibaiGorordo/ONNX-HybridNets-Multitask-Road-Detection

#pretrained weights

https://github.com/PINTO0309/PINTO_model_zoo/tree/main/276_HybridNets

https://drive.google.com/uc?export=download&id=1r1jDtJhi-5KfyMOee0CEbAC-N_hmf8t7

#How do you run a ONNX model on a GPU?

https://stackoverflow.com/questions/64452013/how-do-you-run-a-onnx-model-on-a-gpu

sip2@sip2-2021:~$ cd catkin_od/src/object_detection/scripts/

sip2@sip2-2021:~/catkin_od/src/object_detection/scripts$ git clone https://github.com/ibaiGorordo/ONNX-HybridNets-Multitask-Road-Detection.git
Cloning into 'ONNX-HybridNets-Multitask-Road-Detection'...
remote: Enumerating objects: 109, done.
remote: Counting objects: 100% (109/109), done.
remote: Compressing objects: 100% (81/81), done.
remote: Total 109 (delta 54), reused 57 (delta 18), pack-reused 0
Receiving objects: 100% (109/109), 20.49 MiB | 11.02 MiB/s, done.
Resolving deltas: 100% (54/54), done.

sip2@sip2-2021:~/catkin_od/src/object_detection/scripts/ONNX-HybridNets-Multitask-Road-Detection/models$ tar -zxvf resources.tar.gz

sip2@sip2-2021:~/catkin_od/src/object_detection/scripts/ONNX-HybridNets-Multitask-Road-Detection $source ~/anaconda3/etc/profile.d/conda.sh sip2@sip2-2021:~/catkin_od/src/object_detection/scripts/ONNX-HybridNets-Multitask-Road-Detection$ conda info --e
# conda environments:
#
base                  * /home/sip2/anaconda3
py38-test                /home/sip2/anaconda3/envs/py38-test
py38-torch1-12-1         /home/sip2/anaconda3/envs/py38-torch1-12-1
py38-torch1-12-1-gpu-od     /home/sip2/anaconda3/envs/py38-torch1-12-1-gpu-od
py38-torch1-12-1-gpu-yolopv2     /home/sip2/anaconda3/envs/py38-torch1-12-1-gpu-yolopv2
py38-torch1-12-1-pythonrobotics     /home/sip2/anaconda3/envs/py38-torch1-12-1-pythonrobotics

sip2@sip2-2021:~/catkin_od/src/object_detection/scripts/ONNX-HybridNets-Multitask-Road-Detection $conda create -n py38-torch1-12-1-gpu-hybridnets-onnx --clone py38-torch1-12-1 Source: /home/sip2/anaconda3/envs/py38-torch1-12-1 Destination: /home/sip2/anaconda3/envs/py38-torch1-12-1-gpu-hybridnets-onnx Packages: 65 Files: 0 Preparing transaction: done Verifying transaction: | SafetyError: The package for pytorch located at /home/sip2/anaconda3/pkgs/pytorch-1.12.1-py3.8_cuda11.6_cudnn8.3.2_0 appears to be corrupted. The path 'lib/python3.8/site-packages/torch/nn/modules/upsampling.py' has an incorrect size. reported size: 11056 bytes actual size: 11005 bytes done Executing transaction: - By downloading and using the CUDA Toolkit conda packages, you accept the terms and conditions of the CUDA End User License Agreement (EULA): https://docs.nvidia.com/cuda/eula/index.html done # # To activate this environment, use # #$ conda activate py38-torch1-12-1-gpu-hybridnets-onnx
#
# To deactivate an active environment, use
#
# $ conda deactivate

sip2@sip2-2021:~/catkin_od/src/object_detection/scripts/ONNX-HybridNets-Multitask-Road-Detection $conda activate py38-torch1-12-1-gpu-hybridnets-onnx (py38-torch1-12-1-gpu-hybridnets-onnx) sip2@sip2-2021:~/catkin_od/src/object_detection/scripts/ONNX-HybridNets-Multitask-Road-Detection$ pip install -r requirements.txt
Collecting opencv-python
Using cached opencv_python-4.6.0.66-cp36-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (60.9 MB)
Collecting onnx
Downloading onnx-1.12.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (13.1 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 13.1/13.1 MB 14.4 MB/s eta 0:00:00
Collecting onnxruntime
Downloading onnxruntime-1.12.1-cp38-cp38-manylinux_2_27_x86_64.whl (4.9 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 4.9/4.9 MB 15.8 MB/s eta 0:00:00
Collecting onnxoptimizer
Downloading onnxoptimizer-0.3.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (601 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 601.1/601.1 kB 16.4 MB/s eta 0:00:00
Collecting onnxruntime-gpu
Downloading onnxruntime_gpu-1.12.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (111.0 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 111.0/111.0 MB 13.9 MB/s eta 0:00:00
Collecting imread-from-url
Downloading imread_from_url-0.1.3.tar.gz (7.6 kB)
Preparing metadata (setup.py) ... done
Requirement already satisfied: numpy>=1.14.5 in /home/sip2/anaconda3/envs/py38-torch1-12-1-gpu-hybridnets-onnx/lib/python3.8/site-packages (from opencv-python->-r requirements.txt (line 1)) (1.23.1)
Requirement already satisfied: typing-extensions>=3.6.2.1 in /home/sip2/.local/lib/python3.8/site-packages (from onnx->-r requirements.txt (line 2)) (4.3.0)
Collecting protobuf<=3.20.1,>=3.12.2
Downloading protobuf-3.20.1-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.whl (1.0 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.0/1.0 MB 13.8 MB/s eta 0:00:00
Collecting packaging
Using cached packaging-21.3-py3-none-any.whl (40 kB)
Collecting sympy
Downloading sympy-1.11.1-py3-none-any.whl (6.5 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 6.5/6.5 MB 17.0 MB/s eta 0:00:00
Collecting flatbuffers
Downloading flatbuffers-2.0.7-py2.py3-none-any.whl (26 kB)
Collecting coloredlogs
Downloading coloredlogs-15.0.1-py2.py3-none-any.whl (46 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 46.0/46.0 kB 17.7 MB/s eta 0:00:00
Requirement already satisfied: Pillow>=6.1.0 in /home/sip2/anaconda3/envs/py38-torch1-12-1-gpu-hybridnets-onnx/lib/python3.8/site-packages (from imread-from-url->-r requirements.txt (line 6)) (8.2.0)
Requirement already satisfied: requests>=2.22.0 in /home/sip2/anaconda3/envs/py38-torch1-12-1-gpu-hybridnets-onnx/lib/python3.8/site-packages (from imread-from-url->-r requirements.txt (line 6)) (2.28.1)
Collecting fake-useragent>=0.1.11
Downloading fake-useragent-0.1.11.tar.gz (13 kB)
Preparing metadata (setup.py) ... done
Requirement already satisfied: certifi>=2017.4.17 in /home/sip2/anaconda3/envs/py38-torch1-12-1-gpu-hybridnets-onnx/lib/python3.8/site-packages (from requests>=2.22.0->imread-from-url->-r requirements.txt (line 6)) (2022.6.15.2)
Requirement already satisfied: urllib3<1.27,>=1.21.1 in /home/sip2/anaconda3/envs/py38-torch1-12-1-gpu-hybridnets-onnx/lib/python3.8/site-packages (from requests>=2.22.0->imread-from-url->-r requirements.txt (line 6)) (1.26.11)
Requirement already satisfied: charset-normalizer<3,>=2 in /home/sip2/anaconda3/envs/py38-torch1-12-1-gpu-hybridnets-onnx/lib/python3.8/site-packages (from requests>=2.22.0->imread-from-url->-r requirements.txt (line 6)) (2.1.1)
Requirement already satisfied: idna<4,>=2.5 in /home/sip2/anaconda3/envs/py38-torch1-12-1-gpu-hybridnets-onnx/lib/python3.8/site-packages (from requests>=2.22.0->imread-from-url->-r requirements.txt (line 6)) (3.3)
Collecting humanfriendly>=9.1
Downloading humanfriendly-10.0-py2.py3-none-any.whl (86 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 86.8/86.8 kB 24.5 MB/s eta 0:00:00
Collecting pyparsing!=3.0.5,>=2.0.2
Using cached pyparsing-3.0.9-py3-none-any.whl (98 kB)
Collecting mpmath>=0.19
Downloading mpmath-1.2.1-py3-none-any.whl (532 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 532.6/532.6 kB 17.0 MB/s eta 0:00:00
Building wheels for collected packages: imread-from-url, fake-useragent
Building wheel for imread-from-url (setup.py) ... done
Created wheel for imread-from-url: filename=imread_from_url-0.1.3-py3-none-any.whl size=6625 sha256=2cafb17e6e289393d121f8b52ed46ac88c935acb4259c4ebfac9b3ccbe13bbc1
Stored in directory: /home/sip2/.cache/pip/wheels/71/41/3d/3aa650f3ff41087c512c1ff373a3afd3e998efc501f0aca034
Building wheel for fake-useragent (setup.py) ... done
Created wheel for fake-useragent: filename=fake_useragent-0.1.11-py3-none-any.whl size=13481 sha256=9afe0dbc45ebbd06bc108187c08b14d0db1866a3abeb318c0f414150996bb355
Stored in directory: /home/sip2/.cache/pip/wheels/a0/b8/b7/8c942b2c5be5158b874a88195116b05ad124bac795f6665e65
Successfully built imread-from-url fake-useragent
Installing collected packages: mpmath, flatbuffers, fake-useragent, sympy, pyparsing, protobuf, opencv-python, humanfriendly, packaging, onnx, imread-from-url, coloredlogs, onnxruntime-gpu, onnxruntime, onnxoptimizer
Successfully installed coloredlogs-15.0.1 fake-useragent-0.1.11 flatbuffers-2.0.7 humanfriendly-10.0 imread-from-url-0.1.3 mpmath-1.2.1 onnx-1.12.0 onnxoptimizer-0.3.1 onnxruntime-1.12.1 onnxruntime-gpu-1.12.1 opencv-python-4.6.0.66 packaging-21.3 protobuf-3.20.1 pyparsing-3.0.9 sympy-1.11.1

idNets-Multitask-Road-Detection $pip install youtube_dl Collecting youtube_dl Downloading youtube_dl-2021.12.17-py2.py3-none-any.whl (1.9 MB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.9/1.9 MB 12.3 MB/s eta 0:00:00 Installing collected packages: youtube_dl Successfully installed youtube_dl-2021.12.17 (py38-torch1-12-1-gpu-hybridnets-onnx) sip2@sip2-2021:~/catkin_od/src/object_detection/scripts/ONNX-HybridNets-Multitask-Road-Detection$ pip install git+https://github.com/zizo-pro/pafy@b8976f22c19e4ab5515cacbfae0a3970370c102b
Collecting git+https://github.com/zizo-pro/pafy@b8976f22c19e4ab5515cacbfae0a3970370c102b
Cloning https://github.com/zizo-pro/pafy (to revision b8976f22c19e4ab5515cacbfae0a3970370c102b) to /tmp/pip-req-build-23j70lt7
Running command git clone --filter=blob:none --quiet https://github.com/zizo-pro/pafy /tmp/pip-req-build-23j70lt7
Running command git rev-parse -q --verify 'sha^b8976f22c19e4ab5515cacbfae0a3970370c102b'
Running command git fetch -q https://github.com/zizo-pro/pafy b8976f22c19e4ab5515cacbfae0a3970370c102b
Resolved https://github.com/zizo-pro/pafy to commit b8976f22c19e4ab5515cacbfae0a3970370c102b
Preparing metadata (setup.py) ... done
Building wheels for collected packages: pafy
Building wheel for pafy (setup.py) ... done
Created wheel for pafy: filename=pafy-0.5.5-py2.py3-none-any.whl size=35687 sha256=d9f418757c08a419527fcacb3cec8dea29927c2931eb745f8d841cfd4e8c88bd
Stored in directory: /home/sip2/.cache/pip/wheels/c5/db/e1/eb8f267dbfc00df1c24754a1424071b1c1ad8e93443a4aa8bf
Successfully built pafy
Installing collected packages: pafy
Successfully installed pafy-0.5.5

(py38-torch1-12-1-gpu-hybridnets-onnx) sip2@sip2-2021:~/catkin_od/src/object_detection/scripts/ONNX-HybridNets-Multitask-Road-Detection$ python video_bird_eye_view_road_detection.py

Anaconda을 이용하여 ROS + Tensorflow 함께 사용하기

-- CUDA, cuDNN 버전확인 https://stackoverflow.com/questions/41714757/how-to-find-cuda-version-in-ubuntu/42122965

$nvcc --version cuda8.0, cudnn6.0 -- 아나콘다 python2.7 버전 인스톨 https://www.anaconda.com/download/#linux python3.x이랑 ROS 같이 써보려고 했는데, 아직 실력이 부족해서 그런지 실패..$ bash Anaconda2-5.3.0-Linux-x86_64.sh

$source ~/.bashrc$ python -V Python 2.7.15 :: Anaconda, Inc.

$conda create -n tf14 pip python=2.7$ source activate tf14 -- ROS 관련 패키지 인스톨 (tf14)

$pip install --upgrade pip (tf14)$ pip install -U rosinstall msgpack empy defusedxml netifaces --CUDA, cuDNN, CPU/GPU을 사양에 맞춰서 tensorflow download https://github.com/mind/wheels#mkl (tf14)

$pip install tensorflow-1.4.0-cp27-cp27mu-linux_x86_64.whl 잘 설치가 되었는지 Hello, tensorflow 실행 (tf14)$ python Python 2.7.15 |Anaconda, Inc.| (default, May 1 2018, 23:32:55) [GCC 7.2.0] on linux2 Type "help", "copyright", "credits" or "license" for more information. >>> i...

日常生活

このブログを検索

Panoptic driving Perception (HybridNets-ONNX)

ラベル

コメント

コメントを投稿

このブログの人気の投稿

[참고] ROS kinetic에서 WebCam 사용하기 (Ubuntu 16.04)

[vscode] TImeout waiting for debugger connection

Anaconda을 이용하여 ROS + Tensorflow 함께 사용하기