bharatsubedi / alpr-yolov5 Goto Github PK

cap = cv2.VideoCapture('./video.mp4')
net = cv2.dnn.readNetFromONNX("./detection_best.onnx")

img = cv2.resize(img, (640,640))
blob = cv2.dnn.blobFromImage(img,scalefactor= 1/255,size=(640,640),mean=[0,0,0],swapRB= True, crop= False)

Error
error: (-2:Unspecified error) Can't create layer "/model.0/conv/act/HardSigmoid_output_0" of type "HardSigmoid" in function 'getLayerInstance'

Change
weights_reco ='recognition_model/final_weights/recognition_best.pt'
to
weights_reco ='recognition_model/final_weight/recognition_best.pt'

in ALPR-Yolov5/end-t-end-test/combine_test.py

install requirements and run end-t-end-test gives error:

AttributeError: 'Hardswish' object has no attribute 'inplace'

all models in correct place.

ubuntu 18 and python 3.8.5

Traceback (most recent call last): File "combine_test.py", line 117, in <module> detect() File "combine_test.py", line 77, in detect _ = model_reco(img.half() if half else img) if device.type != 'cpu' else None File "/home/alp2080/Projects/Yolov5_StrongSORT_OSNet/venvStrongSort/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "/data/dProjects/ALPR-Yolov5/end-t-end-test/models/yolo.py", line 107, in forward return self.forward_once(x, profile) # single-scale inference, train File "/data/dProjects/ALPR-Yolov5/end-t-end-test/models/yolo.py", line 127, in forward_once x = m(x) # run File "/home/alp2080/Projects/Yolov5_StrongSORT_OSNet/venvStrongSort/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "/data/dProjects/ALPR-Yolov5/end-t-end-test/models/common.py", line 87, in forward return self.conv(torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1)) File "/home/alp2080/Projects/Yolov5_StrongSORT_OSNet/venvStrongSort/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "/data/dProjects/ALPR-Yolov5/end-t-end-test/models/common.py", line 29, in forward return self.act(self.bn(self.conv(x))) File "/home/alp2080/Projects/Yolov5_StrongSORT_OSNet/venvStrongSort/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "/home/alp2080/Projects/Yolov5_StrongSORT_OSNet/venvStrongSort/lib/python3.8/site-packages/torch/nn/modules/activation.py", line 472, in forward return F.hardswish(input, self.inplace) File "/home/alp2080/Projects/Yolov5_StrongSORT_OSNet/venvStrongSort/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1207, in __getattr__ raise AttributeError("'{}' object has no attribute '{}'".format( AttributeError: 'Hardswish' object has no attribute 'inplace'

Package Version

absl-py 1.2.0
asttokens 2.1.0
backcall 0.2.0
beautifulsoup4 4.11.1
cachetools 5.2.0
certifi 2022.6.15
charset-normalizer 2.1.0
cycler 0.11.0
Cython 0.29.30
decorator 5.1.1
easydict 1.9
executing 1.2.0
filelock 3.7.1
flake8 4.0.1
fonttools 4.34.4
future 0.18.2
gdown 4.5.1
google-auth 2.9.1
google-auth-oauthlib 0.4.6
grpcio 1.47.0
h5py 3.7.0
idna 3.3
imageio 2.19.5
importlib-metadata 4.12.0
ipython 8.6.0
isort 4.3.21
jedi 0.18.1
kiwisolver 1.4.4
Markdown 3.4.1
matplotlib 3.5.2
matplotlib-inline 0.1.6
mccabe 0.6.1
numpy 1.23.1
oauthlib 3.2.0
onnx 1.12.0
opencv-python 4.6.0.66
packaging 21.3
pafy 0.5.5
pandas 1.4.3
parso 0.8.3
pexpect 4.8.0
pickleshare 0.7.5
Pillow 9.2.0
pip 20.0.2
pkg-resources 0.0.0
prompt-toolkit 3.0.32
protobuf 3.19.4
psutil 5.9.4
ptyprocess 0.7.0
pure-eval 0.2.2
pyasn1 0.4.8
pyasn1-modules 0.2.8
pycodestyle 2.8.0
pyflakes 2.4.0
Pygments 2.13.0
pyparsing 3.0.9
PySocks 1.7.1
python-dateutil 2.8.2
pytz 2022.1
PyYAML 6.0
requests 2.28.1
requests-oauthlib 1.3.1
rsa 4.8
scipy 1.8.1
seaborn 0.11.2
setuptools 44.0.0
six 1.16.0
soupsieve 2.3.2.post1
stack-data 0.6.1
tb-nightly 2.10.0a20220719
tensorboard 2.11.0
tensorboard-data-server 0.6.1
tensorboard-plugin-wit 1.8.1
thop 0.1.1.post2209072238
torch 1.12.0
torchvision 0.13.0
tqdm 4.64.0
traitlets 5.5.0
typing-extensions 4.3.0
urllib3 1.26.10
wcwidth 0.2.5
Werkzeug 2.1.2
wheel 0.37.1
yacs 0.1.8
yapf 0.32.0
youtube-dl 2020.12.2
zipp 3.8.1

Hello Bharat Subedi,
First of all, thank you for your project that you developed with Yolov5 and presented on github.
I need your support on the License Plate Recognition System. Is it possible to train our own model on synthetic data?

Hi, sorry for I can not test my video, is this combine model is support video? I am looking forward your reply thank you.

it can't detect far image, accuracy is not so good for far image or frame how can i improve it

Hi, i tried and it works. Good work.
Can i select vocabulary? Only certain chars?

this line:
pred = model(img, augment=False)[0]

gives error:
'Hardswish' object has no attribute 'inplace'

probably because torch,torchvision versions.

can you fix it?

where i can find this file?

Can't get attribute 'C3' on <module 'models.common' from 'E:\TestPy\ALPR-Yolov5-master\end-t-end-test\models\common.py'>

Hello, I really thank you for what you did.
I need help implementing my own license plate recognition system.
I implemented plate detection using yolo and with the help of your codes and it works very well.
But for plate recognition(charcter recognition), my dataset includes characters separated from the license plate. That is, for each example of the numbers 0 to 9, I have about 1000 data, so I don't have the entire license plate.
In order to be able to implement this application, how should I label and use these codes to implement the plate recognition part?

Hello, thank you for your amazing implementation
How to use this implementation on CPU ?
It'll be much appreciated if you help me with this,
Thank you

Hi, I appreciate your project, can I ask you how to change the input image to input video? I also need rtsp input? Can you help me? Thank you!!!

I am facing this error when trying to run combine_test.py

device: cpu
Fusing layers...
Fusing layers...
Traceback (most recent call last):
File "/content/drive/MyDrive/Brain Station 23/RnD Lab/Augustus/License Plate detection/ALPR-Yolov5/end-t-end-test/combine_test.py", line 116, in
detect()
File "/content/drive/MyDrive/Brain Station 23/RnD Lab/Augustus/License Plate detection/ALPR-Yolov5/end-t-end-test/combine_test.py", line 95, in detect
pred = model(img, augment=False)[0]
File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/content/drive/MyDrive/Brain Station 23/RnD Lab/Augustus/License Plate detection/ALPR-Yolov5/end-t-end-test/models/yolo.py", line 107, in forward
return self.forward_once(x, profile) # single-scale inference, train
File "/content/drive/MyDrive/Brain Station 23/RnD Lab/Augustus/License Plate detection/ALPR-Yolov5/end-t-end-test/models/yolo.py", line 127, in forward_once
x = m(x) # run
File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/content/drive/MyDrive/Brain Station 23/RnD Lab/Augustus/License Plate detection/ALPR-Yolov5/end-t-end-test/models/common.py", line 87, in forward
return self.conv(torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1))
File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/content/drive/MyDrive/Brain Station 23/RnD Lab/Augustus/License Plate detection/ALPR-Yolov5/end-t-end-test/models/common.py", line 29, in forward
return self.act(self.bn(self.conv(x)))
File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/activation.py", line 461, in forward
return F.hardswish(input, self.inplace)
File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1178, in getattr
type(self).name, name))
AttributeError: 'Hardswish' object has no attribute 'inplace'