Yolov5 OpenCV error: (-215:Assertion failed) whilst using .onnx

Question

I've just created a yolov5 model, and exported it in the onnx format so it is usable with opencv but I keep getting the error:

[ERROR:0] global D:\a\opencv-python\opencv-python\opencv\modules\dnn\src\dnn.cpp (3554) cv::dnn::dnn4_v20211004::Net::Impl::getLayerShapesRecursively OPENCV/DNN: [Reshape]:(466): getMemoryShapes() throws exception. inputs=1 outputs=1/1 blobs=0 [ERROR:0] global D:\a\opencv-python\opencv-python\opencv\modules\dnn\src\dnn.cpp (3557) cv::dnn::dnn4_v20211004::Net::Impl::getLayerShapesRecursively input[0] = [ 1 24 52 52 ] [ERROR:0] global D:\a\opencv-python\opencv-python\opencv\modules\dnn\src\dnn.cpp (3561) cv::dnn::dnn4_v20211004::Net::Impl::getLayerShapesRecursively output[0] = [ ] [ERROR:0] global D:\a\opencv-python\opencv-python\opencv\modules\dnn\src\dnn.cpp (3567) cv::dnn::dnn4_v20211004::Net::Impl::getLayerShapesRecursively Exception message: OpenCV(4.5.4) D:\a\opencv-python\opencv-python\opencv\modules\dnn\src\layers\reshape_layer.cpp:106: error: (-215:Assertion failed) total(srcShape, srcRange.start, srcRange.end) == maskTotal in function 'cv::dnn::computeShapeByReshapeMask'

here is the code:

onnx_model = onnx.load('best.onnx')
onnx.checker.check_model(onnx_model)
net = cv.dnn.readNetFromONNX('best.onnx')


classes = []

with open("coco-dataset.labels", "r") as f:
    classes = [line.strip() for line in f.readlines()]

layerNames = net.getLayerNames()
outputLayers=[]
for i in net.getUnconnectedOutLayers():
    outputLayers.append(layerNames[i-1])




bounding_box = {'top': 0, 'left': 0, 'width': 1920, 'height': 1080}
sct = mss()

while True:
    screenShot = sct.grab(bounding_box)
    img_np = np.array(screenShot)
    frame = cv.cvtColor(img_np, cv.COLOR_RGBA2RGB)
    frame_id += 1
    height, width, channels= frame.shape


    blob = cv.dnn.blobFromImage(frame, 0.0039216, (416, 416), (0, 0, 0), True, crop=False)


    cv.imshow("Image", frame)

    net.setInput(blob)

(THIS IS THE ERROR LINE)

    outs = net.forward(outputLayers)

I'm not sure if it is just my understanding of onnx, or if there is a fix I haven't picked up on.

Any help is appreciated!

Muhammad Rizwan Munawar · Answer 1 · 2021-12-11T10:08:17.040

6

Until now latest version of OpenCV (4.5.4), OpenCV unable to load onnx file without simplification operation. You have exported yolov5 pt file to onnx file with below command.

 python export.py --weights .\best.pt

Try to export pt file to onnx file with below commands.

For Ubuntu:

python export.py --weights .\yolov5s.pt --include onnx --simplify

For Windows

pip install onnx
pip install onnx-simplifier 
python export.py --weights .\yolov5s.pt --include onnx --simplify

and then load created onnx file with OpenCV, OpenCV will read that onnx successfully.

Also change you model size to (640,640) in blobfromimage function.

edited Dec 11 '21 at 10:08

answered Dec 10 '21 at 09:54

Muhammad Rizwan Munawar

672
4
14

1

Thanks for the help! sadly it still produces the same error, I have tried downgrading and upgrading but I still can't get it to work. – Matthew Bevilacqua Dec 10 '21 at 18:04
if this line [net = cv.dnn.readNetFromONNX('best.onnx') ] will not produce any error, its means model readed successfully. – Muhammad Rizwan Munawar Dec 10 '21 at 18:08
Also, What is your modelsize? 640 or 416? – Muhammad Rizwan Munawar Dec 10 '21 at 18:10
I just rolled back the version of opencv, and it is producing a new error "error: (-204:Requested object was not found) Blob not found in const blobs in function 'cv::dnn::dnn4_v20191202::ONNXImporter::getBlob'", in the [net = cv.dnn.readNetFromONNX('best.onnx') ] line. – Matthew Bevilacqua Dec 10 '21 at 18:34
my modelsize is 640. – Matthew Bevilacqua Dec 10 '21 at 18:35
oh, silly mistake, my blobFromImage function was written incorrectly. Thanks for your help! – Matthew Bevilacqua Dec 10 '21 at 18:38
ok cool. Welcome – Muhammad Rizwan Munawar Dec 11 '21 at 10:07
Upgrading to OpenCV 4.6.0, solved the error for me. – Kevin Patel Sep 26 '22 at 02:13

Yolov5 OpenCV error: (-215:Assertion failed) whilst using .onnx

1 Answers1