opencv-ai / oak-model-samples Goto Github PK

View Code? Open in Web Editor NEW

71.0 71.0 23.0 338 KB

Python 98.94% Shell 1.06%

oak-model-samples's People

Contributors

Stargazers

Watchers

oak-model-samples's Issues

Unable to run emotion_recognition_retail - attributeError: args

I have OAK-D and I am able to run other samples from depthAI on my OAK-D device.
I am running on mac.

Followed the steps provided in blog.

I get the following output -

2021-09-28 15:21:56.790 | WARNING | modelplace_api.utils::13 - The 'pycocotools' package wasn't found. Slow encoding and decoding are used for the RLE mask.
Traceback (most recent call last):
File "/Users/i036148/oak-model-samples/emotion_recognition_retail/main.py", line 3, in
from modelplace_api.visualization import draw_emotion_recognition_one_frame
File "/Users/i036148/.espressif/python_env/idf4.4_py3.9_env/lib/python3.9/site-packages/modelplace_api/init.py", line 4, in
import modelplace_api.visualization
File "/Users/i036148/.espressif/python_env/idf4.4_py3.9_env/lib/python3.9/site-packages/modelplace_api/visualization.py", line 9, in
from .objects import (
File "/Users/i036148/.espressif/python_env/idf4.4_py3.9_env/lib/python3.9/site-packages/modelplace_api/objects.py", line 64, in
class Pose(pydantic.BaseModel):
File "/Users/i036148/.espressif/python_env/idf4.4_py3.9_env/lib/python3.9/site-packages/pydantic/main.py", line 246, in new
fields[ann_name] = inferred = ModelField.infer(
File "/Users/i036148/.espressif/python_env/idf4.4_py3.9_env/lib/python3.9/site-packages/pydantic/fields.py", line 310, in infer
return cls(
File "/Users/i036148/.espressif/python_env/idf4.4_py3.9_env/lib/python3.9/site-packages/pydantic/fields.py", line 272, in init
self.prepare()
File "/Users/i036148/.espressif/python_env/idf4.4_py3.9_env/lib/python3.9/site-packages/pydantic/fields.py", line 364, in prepare
self.type_analysis()
File "/Users/i036148/.espressif/python_env/idf4.4_py3.9_env/lib/python3.9/site-packages/pydantic/fields.py", line 453, in type_analysis
self.type = self.type.args[0]
File "/usr/local/Cellar/[email protected]/3.9.7/Frameworks/Python.framework/Versions/3.9/lib/python3.9/typing.py", line 706, in getattr
raise AttributeError(attr)
AttributeError: args

facial_landmarks_35_adas AssertionError

Ubuntu 20.10 and Python 3.8.

My guess is that Python 3.8 is the problem.

~/Repositories/oak-model-samples/facial_landmarks_35_adas
$ python3 main.py -cam
[14442C10A1E2F0D000] [39.276] [NeuralNetwork(4)] [warning] Network compiled for 4 shaves, maximum available 16, compiling for 8 shaves likely will yield in better performance
[14442C10A1E2F0D000] [1.986] [NeuralNetwork(4)] [warning] Network compiled for 4 shaves, maximum available 13, compiling for 6 shaves likely will yield in better performance
[14442C10A1E2F0D000] [2.028] [NeuralNetwork(1)] [warning] Network compiled for 4 shaves, maximum available 13, compiling for 6 shaves likely will yield in better performance
[14442C10A1E2F0D000] [2.037] [NeuralNetwork(4)] [warning] The issued warnings are orientative, based on optimal settings for a single network, if multiple networks are running in parallel the optimal settings may vary
[14442C10A1E2F0D000] [2.037] [NeuralNetwork(1)] [warning] The issued warnings are orientative, based on optimal settings for a single network, if multiple networks are running in parallel the optimal settings may vary
Traceback (most recent call last):
  File "main.py", line 17, in <module>
    main()
  File "main.py", line 13, in main
    inference(model_cls, root_model_path, visualization)
  File "/home/drew/Repositories/oak-model-samples/facial_landmarks_35_adas/oak_inference_utils/inference.py", line 65, in inference
    inference_results = process_cam(model, visualization_func)
  File "/home/drew/Repositories/oak-model-samples/facial_landmarks_35_adas/oak_inference_utils/inference.py", line 50, in process_cam
    ret, proceed = process_frame(image, model, visualization_func)
  File "/home/drew/Repositories/oak-model-samples/facial_landmarks_35_adas/oak_inference_utils/inference.py", line 14, in process_frame
    ret = model.process_sample(Image.fromarray(image))
  File "/home/drew/Repositories/oak-model-samples/facial_landmarks_35_adas/oak_inference_utils/base_model.py", line 165, in process_sample
    data = self.preprocess([image])
  File "/home/drew/Repositories/oak-model-samples/facial_landmarks_35_adas/facial_landmarks_35_adas/model.py", line 34, in preprocess
    face_bboxes = self.get_first_stage_result(data)
  File "/home/drew/Repositories/oak-model-samples/facial_landmarks_35_adas/oak_inference_utils/base_model.py", line 260, in get_first_stage_result
    first_stage_output = self.first_stage.forward(
  File "/home/drew/Repositories/oak-model-samples/facial_landmarks_35_adas/facial_landmarks_35_adas/face_processing.py", line 94, in forward
    assert wait_for_results(out_queue)
AssertionError

Is OAK-1 capable of providing depth data?

Hi there,

I have read through both OAK-1 and OAK-D.

It seems that they both are able to provide depth data.

Could you please confirm this?

Windows installation commands for OpenPose

This is related with OpenPose example, but I think it will affect the other examples too.

################
Set up a package:

2.1 python3 setup.py bdist_wheel && rm -R build/ *.egg-info

2.2 pip3 install dist/*.whl -f https://artifacts.luxonis.com/artifactory/luxonis-python-snapshot-local/depthai/ && rm -R dist/

################

This commands do not work on Windows.
"rm" needs to be replaced by "del"
Also, "python3" does not work on Windows, it should be "python".
I am having problems translating this command to Windows CMD... Unable to install the dist and to execute those commands.
Could you please provide an installation guide for Windows?

Thanks!

PD: I am a newbie.

Blob files not cloning as expected

Ubuntu 20.10
Python 3.8
DepthAI 0.0.2.1+87247bfb645027a30c68191d88fe1b69b70e39ac
Git 2.27.0

I don't know if this is by design or a problem, but blob files aren't cloning as expected.

I cloned this repo using:

git clone https://github.com/opencv-ai/oak-model-samples.git

But all "checkpoint/*blob" files are actually text files similar to:

version https://git-lfs.github.com/spec/v1
oid sha256:ae7da3959157fde405376d9aa53147c4130c475119f012f33e5f22dac880adb4
size 1341888

To get the samples to work I have to return to GitHub and browse to a "checkpoint" folder like "https://github.com/opencv-ai/oak-model-samples/tree/main/facial_landmarks_35_adas/checkpoint", select a blob file, and then click "view raw" to download it to the respective checkpoint folder.

ModuleNotFoundError: No module named 'loguru'

Hi,

basically every sample i tried gives me the following error:
lightweight_openpose\modelplace_api\utils.py", line 5, in
from loguru import logger
ModuleNotFoundError: No module named 'loguru'

I am currently running a windows 10 system with an oak-d camera connected to it.
I followed the install instructions and ran the setup.py

Checking via pip loguru should be installed:
pip install loguru
Requirement already satisfied: loguru in c:\program files\python39\lib\site-packages (0.5.1)
Requirement already satisfied: win32-setctime>=1.0.0 in c:\program files\python39\lib\site-packages (from loguru) (1.0.3)
Requirement already satisfied: colorama>=0.3.4 in c:\program files\python39\lib\site-packages (from loguru) (0.4.4)

What am i missing?

lightweight_openpose video error

Ubuntu 20.10
Python 3.8
DepthAI 0.0.2.1+87247bfb645027a30c68191d88fe1b69b70e39ac

Looks like the video is broken. Error is: "moov atom not found".
The sample runs when using only the camera.

~/Repositories/oak-model-samples/lightweight_openpose
$ pip3 install wheel && python3 setup.py bdist_wheel && rm -R build/ *.egg-info
Defaulting to user installation because normal site-packages is not writeable
Requirement already satisfied: wheel in /home/drew/.local/lib/python3.8/site-packages (0.36.2)
running bdist_wheel
running build
running build_py
creating build
creating build/lib
creating build/lib/lightweight_openpose
copying lightweight_openpose/utils.py -> build/lib/lightweight_openpose
copying lightweight_openpose/model.py -> build/lib/lightweight_openpose
copying lightweight_openpose/__init__.py -> build/lib/lightweight_openpose
creating build/lib/oak_inference_utils
copying oak_inference_utils/inference.py -> build/lib/oak_inference_utils
copying oak_inference_utils/args_parser.py -> build/lib/oak_inference_utils
copying oak_inference_utils/base_model.py -> build/lib/oak_inference_utils
copying oak_inference_utils/__init__.py -> build/lib/oak_inference_utils
installing to build/bdist.linux-x86_64/wheel
running install
running install_lib
creating build/bdist.linux-x86_64
creating build/bdist.linux-x86_64/wheel
creating build/bdist.linux-x86_64/wheel/oak_inference_utils
copying build/lib/oak_inference_utils/inference.py -> build/bdist.linux-x86_64/wheel/oak_inference_utils
copying build/lib/oak_inference_utils/args_parser.py -> build/bdist.linux-x86_64/wheel/oak_inference_utils
copying build/lib/oak_inference_utils/base_model.py -> build/bdist.linux-x86_64/wheel/oak_inference_utils
copying build/lib/oak_inference_utils/__init__.py -> build/bdist.linux-x86_64/wheel/oak_inference_utils
creating build/bdist.linux-x86_64/wheel/lightweight_openpose
copying build/lib/lightweight_openpose/utils.py -> build/bdist.linux-x86_64/wheel/lightweight_openpose
copying build/lib/lightweight_openpose/model.py -> build/bdist.linux-x86_64/wheel/lightweight_openpose
copying build/lib/lightweight_openpose/__init__.py -> build/bdist.linux-x86_64/wheel/lightweight_openpose
running install_egg_info
running egg_info
creating lightweight_openpose.egg-info
writing lightweight_openpose.egg-info/PKG-INFO
writing dependency_links to lightweight_openpose.egg-info/dependency_links.txt
writing requirements to lightweight_openpose.egg-info/requires.txt
writing top-level names to lightweight_openpose.egg-info/top_level.txt
writing manifest file 'lightweight_openpose.egg-info/SOURCES.txt'
reading manifest file 'lightweight_openpose.egg-info/SOURCES.txt'
writing manifest file 'lightweight_openpose.egg-info/SOURCES.txt'
Copying lightweight_openpose.egg-info to build/bdist.linux-x86_64/wheel/lightweight_openpose-0.2.0-py3.8.egg-info
running install_scripts
adding license file "LICENSE" (matched pattern "LICEN[CS]E*")
creating build/bdist.linux-x86_64/wheel/lightweight_openpose-0.2.0.dist-info/WHEEL
creating 'dist/lightweight_openpose-0.2.0-py3-none-any.whl' and adding 'build/bdist.linux-x86_64/wheel' to it
adding 'lightweight_openpose/__init__.py'
adding 'lightweight_openpose/model.py'
adding 'lightweight_openpose/utils.py'
adding 'oak_inference_utils/__init__.py'
adding 'oak_inference_utils/args_parser.py'
adding 'oak_inference_utils/base_model.py'
adding 'oak_inference_utils/inference.py'
adding 'lightweight_openpose-0.2.0.dist-info/LICENSE'
adding 'lightweight_openpose-0.2.0.dist-info/METADATA'
adding 'lightweight_openpose-0.2.0.dist-info/WHEEL'
adding 'lightweight_openpose-0.2.0.dist-info/top_level.txt'
adding 'lightweight_openpose-0.2.0.dist-info/RECORD'
removing build/bdist.linux-x86_64/wheel

~/Repositories/oak-model-samples/lightweight_openpose
$ pip3 install dist/*.whl -f https://artifacts.luxonis.com/artifactory/luxonis-python-snapshot-local/depthai/ && rm -R dist/
Defaulting to user installation because normal site-packages is not writeable
Looking in links: https://artifacts.luxonis.com/artifactory/luxonis-python-snapshot-local/depthai/
Processing ./dist/lightweight_openpose-0.2.0-py3-none-any.whl
Collecting modelplace-api[vis]@ https://github.com/opencv-ai/modelplace-api/archive/v0.4.7.zip
  Using cached https://github.com/opencv-ai/modelplace-api/archive/v0.4.7.zip
  Installing build dependencies ... done
  Getting requirements to build wheel ... done
    Preparing wheel metadata ... done
Requirement already satisfied: depthai==0.0.2.1+87247bfb645027a30c68191d88fe1b69b70e39ac in /home/drew/.local/lib/python3.8/site-packages (from lightweight-openpose==0.2.0) (0.0.2.1+87247bfb645027a30c68191d88fe1b69b70e39ac)
Requirement already satisfied: pydantic==1.5.1 in /home/drew/.local/lib/python3.8/site-packages (from modelplace-api[vis]@ https://github.com/opencv-ai/modelplace-api/archive/v0.4.7.zip->lightweight-openpose==0.2.0) (1.5.1)
Requirement already satisfied: loguru==0.5.1 in /home/drew/.local/lib/python3.8/site-packages (from modelplace-api[vis]@ https://github.com/opencv-ai/modelplace-api/archive/v0.4.7.zip->lightweight-openpose==0.2.0) (0.5.1)
Requirement already satisfied: numpy>=1.16.4 in /home/drew/.local/lib/python3.8/site-packages (from modelplace-api[vis]@ https://github.com/opencv-ai/modelplace-api/archive/v0.4.7.zip->lightweight-openpose==0.2.0) (1.17.5)
Requirement already satisfied: Pillow==7.1.2 in /home/drew/.local/lib/python3.8/site-packages (from modelplace-api[vis]@ https://github.com/opencv-ai/modelplace-api/archive/v0.4.7.zip->lightweight-openpose==0.2.0) (7.1.2)
Requirement already satisfied: imageio==2.9.0 in /home/drew/.local/lib/python3.8/site-packages (from modelplace-api[vis]@ https://github.com/opencv-ai/modelplace-api/archive/v0.4.7.zip->lightweight-openpose==0.2.0) (2.9.0)
Requirement already satisfied: opencv-python<5.0,>=4.2.0.34 in /home/drew/.local/lib/python3.8/site-packages (from modelplace-api[vis]@ https://github.com/opencv-ai/modelplace-api/archive/v0.4.7.zip->lightweight-openpose==0.2.0) (4.5.1.48)
Requirement already satisfied: sk-video==1.1.10 in /home/drew/.local/lib/python3.8/site-packages (from modelplace-api[vis]@ https://github.com/opencv-ai/modelplace-api/archive/v0.4.7.zip->lightweight-openpose==0.2.0) (1.1.10)
Requirement already satisfied: pycocotools==2.0.2 in /home/drew/.local/lib/python3.8/site-packages (from modelplace-api[vis]@ https://github.com/opencv-ai/modelplace-api/archive/v0.4.7.zip->lightweight-openpose==0.2.0) (2.0.2)
Requirement already satisfied: matplotlib>=2.1.0 in /usr/lib/python3/dist-packages (from pycocotools==2.0.2->modelplace-api[vis]@ https://github.com/opencv-ai/modelplace-api/archive/v0.4.7.zip->lightweight-openpose==0.2.0) (3.3.0)
Requirement already satisfied: setuptools>=18.0 in /home/drew/.local/lib/python3.8/site-packages (from pycocotools==2.0.2->modelplace-api[vis]@ https://github.com/opencv-ai/modelplace-api/archive/v0.4.7.zip->lightweight-openpose==0.2.0) (54.2.0)
Requirement already satisfied: cython>=0.27.3 in /home/drew/.local/lib/python3.8/site-packages (from pycocotools==2.0.2->modelplace-api[vis]@ https://github.com/opencv-ai/modelplace-api/archive/v0.4.7.zip->lightweight-openpose==0.2.0) (0.29.22)
Requirement already satisfied: scipy in /home/drew/.local/lib/python3.8/site-packages (from sk-video==1.1.10->modelplace-api[vis]@ https://github.com/opencv-ai/modelplace-api/archive/v0.4.7.zip->lightweight-openpose==0.2.0) (1.4.1)
Installing collected packages: lightweight-openpose
Successfully installed lightweight-openpose-0.2.0

~/Repositories/oak-model-samples/lightweight_openpose
$ python3 main.py -vid ./demo.mp4
Traceback (most recent call last):
  File "main.py", line 17, in <module>
    main()
  File "main.py", line 13, in main
    inference(model_cls, root_model_path, visualization)
  File "/home/drew/Repositories/oak-model-samples/lightweight_openpose/oak_inference_utils/inference.py", line 59, in inference
    model.model_load()
  File "/home/drew/Repositories/oak-model-samples/lightweight_openpose/oak_inference_utils/base_model.py", line 82, in model_load
    self.create_pipeline(model_blob)
  File "/home/drew/Repositories/oak-model-samples/lightweight_openpose/oak_inference_utils/base_model.py", line 73, in create_pipeline
    self.model_blob.setBlobPath(model_blob)
RuntimeError: BlobReader error: File does not seem to be a supported neural network blob

~/Repositories/oak-model-samples/lightweight_openpose
$ python3 main.py -vid ./demo.mp4
[mov,mp4,m4a,3gp,3g2,mj2 @ 0x2570440] moov atom not found

~/Repositories/oak-model-samples/lightweight_openpose
$ python3 main.py -cam

ModuleNotFoundError: No module named 'modelplace_api'

Try to run yolov4_tiny as suggested: python3 main.py -cam -vid

Traceback (most recent call last):
File "main.py", line 3, in
from modelplace_api.visualization import draw_detections_one_frame
ModuleNotFoundError: No module named 'modelplace_api'

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.

Jobs

Jooble