Hi jakaskerl
Thanks for the reply. And thanks for sharing the examples.
For the yolo code using Camera node, I didn't have issue showing the preview as long as I took out the XLinkOut for the NN. So I think I created the preview correctly. But once I create the stream for NN, it shows the misconfiguration error. Even when I took out the queue for the NN, it still shows the error. It looks like somehow linking the preview from Camera node to detection network causes the problem.
It will be very helpful if there is a working YOLO object detection example using Camera node.
I also attached below the complete script and I hope it can help pinpoint the issue.
from pathlib import Path
import sys
import cv2
import depthai as dai
import numpy as np
import time
import blobconverter
# tiny yolo v4 label texts
labelMap = [
"person", "bicycle", "car", "motorbike", "aeroplane", "bus", "train",
"truck", "boat", "traffic light", "fire hydrant", "stop sign", "parking meter", "bench",
"bird", "cat", "dog", "horse", "sheep", "cow", "elephant",
"bear", "zebra", "giraffe", "backpack", "umbrella", "handbag", "tie",
"suitcase", "frisbee", "skis", "snowboard", "sports ball", "kite", "baseball bat",
"baseball glove", "skateboard", "surfboard", "tennis racket", "bottle", "wine glass", "cup",
"fork", "knife", "spoon", "bowl", "banana", "apple", "sandwich",
"orange", "broccoli", "carrot", "hot dog", "pizza", "donut", "cake",
"chair", "sofa", "pottedplant", "bed", "diningtable", "toilet", "tvmonitor",
"laptop", "mouse", "remote", "keyboard", "cell phone", "microwave", "oven",
"toaster", "sink", "refrigerator", "book", "clock", "vase", "scissors",
"teddy bear", "hair drier", "toothbrush"
]
# Create pipeline
pipeline = dai.Pipeline()
# Define sources and outputs
camRgb: dai.node.Camera = pipeline.create(dai.node.Camera)
detectionNetwork = pipeline.create(dai.node.YoloDetectionNetwork)
xoutRgb = pipeline.create(dai.node.XLinkOut)
nnOut = pipeline.create(dai.node.XLinkOut)
xoutRgb.setStreamName("rgb")
nnOut.setStreamName("nn")
# Properties
camRgb.setSize((1280, 800))
camRgb.setPreviewSize(416, 416)
camRgb.setFps(40)
camRgb.setBoardSocket(dai.CameraBoardSocket.RGB)
# Network specific settings
detectionNetwork.setConfidenceThreshold(0.8)
detectionNetwork.setNumClasses(80)
detectionNetwork.setCoordinateSize(4)
detectionNetwork.setAnchors([10, 14, 23, 27, 37, 58, 81, 82, 135, 169, 344, 319])
detectionNetwork.setAnchorMasks({"side26": [1, 2, 3], "side13": [3, 4, 5]})
detectionNetwork.setIouThreshold(0.5)
detectionNetwork.setBlobPath(blobconverter.from_zoo(name="yolo-v3-tiny-tf", shaves=6))
detectionNetwork.setNumInferenceThreads(2)
detectionNetwork.input.setBlocking(False)
# Linking
camRgb.preview.link(detectionNetwork.input)
camRgb.preview.link(xoutRgb.input)
detectionNetwork.out.link(nnOut.input)
# Connect to device and start pipeline
with dai.Device(pipeline) as device:
# Output queues will be used to get the rgb frames and nn data from the outputs defined above
qRgb = device.getOutputQueue(name="rgb", maxSize=4, blocking=False)
qDet = device.getOutputQueue(name="nn", maxSize=4, blocking=False)
frame = None
detections = []
startTime = time.monotonic()
counter = 0
color2 = (255, 255, 255)
# nn data, being the bounding box locations, are in <0..1> range - they need to be normalized with frame width/height
def frameNorm(frame, bbox):
normVals = np.full(len(bbox), frame.shape[0])
normVals[::2] = frame.shape[1]
return (np.clip(np.array(bbox), 0, 1) * normVals).astype(int)
def displayFrame(name, frame):
color = (255, 0, 0)
for detection in detections:
bbox = frameNorm(frame, (detection.xmin, detection.ymin, detection.xmax, detection.ymax))
cv2.putText(frame, labelMap[detection.label], (bbox[0] + 10, bbox[1] + 20), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255)
cv2.putText(frame, f"{int(detection.confidence * 100)}%", (bbox[0] + 10, bbox[1] + 40), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255)
cv2.rectangle(frame, (bbox[0], bbox[1]), (bbox[2], bbox[3]), color, 2)
# Show the frame
cv2.imshow(name, frame)
while True:
inRgb = qRgb.tryGet()
inDet = qDet.tryGet()
if inRgb is not None:
frame = inRgb.getCvFrame()
cv2.putText(frame, "NN fps: {:.2f}".format(counter / (time.monotonic() - startTime)),
(2, frame.shape[0] - 4), cv2.FONT_HERSHEY_TRIPLEX, 0.4, color2)
if inDet is not None:
detections = inDet.detections
counter += 1
if frame is not None:
displayFrame("rgb", frame)
if cv2.waitKey(1) == ord('q'):
break
Thanks
Lincoln
