ValueError: 'LCM48' is not in list

JohnCherbini

Hi all, trying to get my own model running on the OAK-1.

Does this look familiar to anyone?

Thanks!

jetson@jetson-desktop:~/depthai-experiments/gen2-yolo/device-decoding$ python main.py --config model/best.json

config: model/best.json

Closing OAK camera

Traceback (most recent call last):

File "main.py", line 14, in <module>

oak.start(blocking=True)

File "/home/jetson/.local/lib/python3.8/site-packages/depthai_sdk/oak_camera.py", line 268, in start

self.build() # Build the pipeline

File "/home/jetson/.local/lib/python3.8/site-packages/depthai_sdk/oak_camera.py", line 354, in build

component.update_device_info(self.pipeline, self.oak.device, self.pipeline.getOpenVINOVersion())

File "/home/jetson/.local/lib/python3.8/site-packages/depthai_sdk/components/camera_component.py", line 110, in _update_device_info

self.node.setResolution(getClosesResolution(sensor_name, width=1300))

File "/home/jetson/.local/lib/python3.8/site-packages/depthai_sdk/components/camera_helper.py", line 236, in getClosesResolution

for res in cameraSensor(sensorName).resolutions:

File "/home/jetson/.local/lib/python3.8/site-packages/depthai_sdk/components/camera_helper.py", line 197, in cameraSensor

return cameraSensors[cameraSensors.index(sensorName.upper())]

ValueError: 'LCM48' is not in list

jakaskerl

Hi JohnCherbini
Can you add a MRE?

Thanks,
Jaka

JohnCherbini

Followed some links on MREs and I think this should get us there?

Here's a link to the directory, tarballed with the model included.

https://drive.google.com/drive/folders/1YK50GO7qOlfX6SFsmhSPseZDlOb7byz0?usp=sharing

It's an OAK-1 camera that's working great with a startup that looks like this (thanks for the efforts!):

def run(self):

# Connect to device and start pipeline

with dai.Device(self.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)

while True:

if self.SYNC_NN:

inRgb = qRgb.get()

inDet = qDet.get()

else:

inRgb = qRgb.tryGet()

inDet = qDet.tryGet()

if inRgb is not None:

frame = inRgb.getCvFrame()

jakaskerl

Hi JohnCherbini
I think you might be using an older version of depthai_sdk. Can you confirm this is the case? Current version is 1.12.

Thanks,
Jaka