Comments (4)
@Vincen-31 Your issue, including the one from OP, is all because of the git LFS object not being pulled properly. If you do not install git-lfs when doing git clone
, or directly download via the Download ZIP
button, the models (git-lfs objects) will not be fetched properly. Typically speaking, a deep learning model is at least several megabytes (one exception in opencv zoo is face_detection_yunet, which is ~330KB), but you can observe that the not-properly-fetched models are always 131B. And if you open those non-properly-fetched models with your text editor, you can see something as follows:
version https://git-lfs.github.com/spec/v1
oid sha256:176794409ae5e9d44b268297b1c480ba7f6df9f793a81d22eac4520aaf331594
size 119815
I can see there are two methods to download models properly:
- Install git-lfs as said in the front page readme and run
git clone https://github.com/opencv/opencv_zoo.git
to get the whole opencv zoo with all models. - Click into the model you want to download and click the
download
button in the webpage. Example: https://github.com/opencv/opencv_zoo/blob/master/models/face_detection_yunet/face_detection_yunet_2022mar.onnx.
from opencv_zoo.
@fengyuentau Thanks for your reply. I have fixed the problem by following your instrction.
from opencv_zoo.
Actually, I have the similar error.
- I have already downloaded the .onnx files by downloading zip and checked the path in demo.py.
- I have tried running code with absolute path of .onnx files.
- I deploy the object_tracking_dasiamrpn with python 3.6 3.8 and opencv 4.5.4.58 4.6.0.66, but failed.
Hardware:
os : ubuntu 18.04 x64
when I run python demo.py , I get the follow error:
Traceback (most recent call last):
File "demo.py", line 54, in
model = DaSiamRPN(
File "/home/milab/Projects/PycharmProjects/pythonProject/opencv_zoo/models/object_tracking_dasiamrpn/dasiamrpn.py", line 24, in init
self._model = cv.TrackerDaSiamRPN.create(self._param)
cv2.error: OpenCV(4.6.0) /io/opencv/modules/dnn/src/onnx/onnx_importer.cpp:260: error: (-210:Unsupported format or combination of formats) Failed to parse ONNX model: object_tracking_dasiamrpn_model_2021nov.onnx in function 'ONNXImporter'
Please help me.
from opencv_zoo.
I guess you need to install git-lfs to pull lfs objects (.onnx files).
from opencv_zoo.
Related Issues (20)
- 请问为什么没有提供rpn的量化版本,是不支持siam网络量化嘛? HOT 6
- AttributeError: module 'cv2' has no attribute 'TrackerVit_Params' HOT 9
- K-best BB VitTracker (feature/Question) HOT 3
- VitTracker weights (question) HOT 10
- Mediapipe pose estimation performance HOT 5
- Refreshing template in Vit (Question) HOT 4
- Dynamic Input Shape? HOT 2
- Lack of charsets in models\text_recognition_crnn HOT 8
- `quantize-ort.py` doesn't reproduce the quantized models in the repos HOT 3
- Is it possible to parallelize face detection process using the face_detection_yunet model in C++? HOT 6
- How to process output of face detection network when batch of images is used as network input? HOT 7
- SFace: Quantized model is slower HOT 2
- 为什么输入的两张相同的图片经过处理以后维度会不一样 HOT 10
- 求助求助,随便选两个图片对比的相似度都很高。 HOT 3
- Add Java demos (Last update on 2024-04-07) HOT 4
- I can't run the yunet_2023mar in OpenCV4.9.0 HOT 2
- Face Anti-Spoofing opencv HOT 1
- 总是报错 HOT 1
- 奇怪的问题 HOT 1
- SFaceRecognizer model face recognition C++ test failed HOT 2
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.
from opencv_zoo.