DepthAI Pipeline Graph Error

yishu_corpex

I am getting the following error for many DepthAi pipeline scripts I try to generate the pipeline graph for.

Pipeline schema retrieved
Program exited.
0. MonoCamera.out (16) -> StereoDepth.left (24)
1. MonoCamera.out (20) -> StereoDepth.right (25)
2. ColorCamera.preview (5) -> SpatialDetectionNetwork.in (9)
3. StereoDepth.depth (27) -> SpatialDetectionNetwork.inputDepth (10)
4. SpatialDetectionNetwork.passthrough (12) -> XLinkOut.in (40)
5. SpatialDetectionNetwork.out (11) -> XLinkOut.in (41)
6. SpatialDetectionNetwork.passthroughDepth (14) -> XLinkOut.in (42)
Traceback (most recent call last):
  File "C:\Users\Yishu\anaconda3\envs\emvs_test\lib\runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "C:\Users\Yishu\anaconda3\envs\emvs_test\lib\runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "C:\Users\Yishu\anaconda3\envs\emvs_test\Scripts\pipeline_graph.exe\__main__.py", line 7, in <module>
  File "C:\Users\Yishu\anaconda3\envs\emvs_test\lib\site-packages\depthai_pipeline_graph\pipeline_graph.py", line 375, in main
    p.cmd_tool(args)
  File "C:\Users\Yishu\anaconda3\envs\emvs_test\lib\site-packages\depthai_pipeline_graph\pipeline_graph.py", line 221, in cmd_tool
    self.create_graph(schema)
  File "C:\Users\Yishu\anaconda3\envs\emvs_test\lib\site-packages\depthai_pipeline_graph\pipeline_graph.py", line 301, in create_graph
    src_port = [p for p in self.ports if p.find_node(src_node_id, src_group, src_name)][0]
IndexError: list index out of range

Following are the packages and there respective version I have that are being used to execute the DepthAI pipeline graph.

depthai                      2.25.0.0
depthai-pipeline-graph       0.0.5
PySide2                      5.15.2.1

I am sharing the script for which I am trying to generate the pipeline graph but am getting the above error.

#!/usr/bin/env python3

from pathlib import Path
import sys
import cv2
import depthai as dai
import numpy as np
import time
import json

'''
Spatial Tiny-yolo example
  Performs inference on RGB camera and retrieves spatial location coordinates: x,y,z relative to the center of depth map.
  Can be used for tiny-yolo-v3 or tiny-yolo-v4 networks
'''

# Initial delay to alow the PoE Cameras to reset
print("Delay Started")
time.sleep(17)
print("Delay Completed")

# Get argument first
nnBlobPath = "path to model blob file"
configPath = "path to model config file"
#str((Path(__file__).parent / Path('../models/yolo-v4-tiny-tf_openvino_2021.4_6shave.blob')).resolve().absolute())

if not Path(nnBlobPath).exists():
    import sys
    raise FileNotFoundError(f'Required file/s not found, please run "{sys.executable} install_requirements.py"')

with open(configPath) as f:
    config = json.load(f)
nnConfig = config.get("nn_config", {})

# parse input shape
if "input_size" in nnConfig:
    W, H = tuple(map(int, nnConfig.get("input_size").split('x')))

# extract metadata
metadata = nnConfig.get("NN_specific_metadata", {})
classes = metadata.get("classes", {})
coordinates = metadata.get("coordinates", {})
anchors = metadata.get("anchors", {})
anchorMasks = metadata.get("anchor_masks", {})
iouThreshold = metadata.get("iou_threshold", {})
confidenceThreshold = metadata.get("confidence_threshold", {})

# Tiny yolo v3/4 label texts
# parse labels
nnMappings = config.get("mappings", {})
labelMap = nnMappings.get("labels", {})
print("Labels: ", labelMap)

syncNN = True

# Create pipeline
pipeline = dai.Pipeline()

# Define sources and outputs
camRgb = pipeline.create(dai.node.ColorCamera)
spatialDetectionNetwork = pipeline.create(dai.node.YoloSpatialDetectionNetwork)
monoLeft = pipeline.create(dai.node.MonoCamera)
monoRight = pipeline.create(dai.node.MonoCamera)
stereo = pipeline.create(dai.node.StereoDepth)
nnNetworkOut = pipeline.create(dai.node.XLinkOut)

xoutRgb = pipeline.create(dai.node.XLinkOut)
xoutNN = pipeline.create(dai.node.XLinkOut)
xoutDepth = pipeline.create(dai.node.XLinkOut)

xoutRgb.setStreamName("rgb")
xoutNN.setStreamName("detections")
xoutDepth.setStreamName("depth")
nnNetworkOut.setStreamName("nnNetwork")

# Properties
camRgb.setPreviewSize(W, H)
camRgb.setResolution(dai.ColorCameraProperties.SensorResolution.THE_12_MP)
camRgb.setInterleaved(False)
camRgb.setColorOrder(dai.ColorCameraProperties.ColorOrder.BGR)

monoLeft.setResolution(dai.MonoCameraProperties.SensorResolution.THE_400_P)
monoLeft.setCamera("left")
monoRight.setResolution(dai.MonoCameraProperties.SensorResolution.THE_400_P)
monoRight.setCamera("right")

# setting node configs
stereo.setDefaultProfilePreset(dai.node.StereoDepth.PresetMode.HIGH_DENSITY)
# Align depth map to the perspective of RGB camera, on which inference is done
stereo.setDepthAlign(dai.CameraBoardSocket.CAM_A)
stereo.setOutputSize(monoLeft.getResolutionWidth(), monoLeft.getResolutionHeight())
stereo.setSubpixel(True)

spatialDetectionNetwork.setBlobPath(nnBlobPath)
spatialDetectionNetwork.setConfidenceThreshold(confidenceThreshold)
spatialDetectionNetwork.input.setBlocking(False)
spatialDetectionNetwork.setBoundingBoxScaleFactor(0.5)
spatialDetectionNetwork.setDepthLowerThreshold(100)
spatialDetectionNetwork.setDepthUpperThreshold(5000)

# Yolo specific parameters
spatialDetectionNetwork.setNumClasses(classes)
spatialDetectionNetwork.setCoordinateSize(coordinates)
spatialDetectionNetwork.setAnchors(anchors)
spatialDetectionNetwork.setAnchorMasks(anchorMasks)
spatialDetectionNetwork.setIouThreshold(iouThreshold)

# Linking
monoLeft.out.link(stereo.left)
monoRight.out.link(stereo.right)

camRgb.preview.link(spatialDetectionNetwork.input)
if syncNN:
    spatialDetectionNetwork.passthrough.link(xoutRgb.input)
else:
    camRgb.preview.link(xoutRgb.input)

spatialDetectionNetwork.out.link(xoutNN.input)

stereo.depth.link(spatialDetectionNetwork.inputDepth)
spatialDetectionNetwork.passthroughDepth.link(xoutDepth.input)
spatialDetectionNetwork.outNetwork.link(nnNetworkOut.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
    previewQueue = device.getOutputQueue(name="rgb", maxSize=4, blocking=False)
    detectionNNQueue = device.getOutputQueue(name="detections", maxSize=4, blocking=False)
    depthQueue = device.getOutputQueue(name="depth", maxSize=4, blocking=False)
    networkQueue = device.getOutputQueue(name="nnNetwork", maxSize=4, blocking=False)

    startTime = time.monotonic()
    counter = 0
    fps = 0
    color = (255, 255, 255)
    printOutputLayersOnce = True

    while True:
        inPreview = previewQueue.get()
        inDet = detectionNNQueue.get()
        depth = depthQueue.get()
        inNN = networkQueue.get()

        if printOutputLayersOnce:
            toPrint = 'Output layer names:'
            for ten in inNN.getAllLayerNames():
                toPrint = f'{toPrint} {ten},'
            print(toPrint)
            printOutputLayersOnce = False

        frame = inPreview.getCvFrame()
        depthFrame = depth.getFrame() # depthFrame values are in millimeters

        depth_downscaled = depthFrame[::4]
        if np.all(depth_downscaled == 0):
            min_depth = 0  # Set a default minimum depth value when all elements are zero
        else:
            min_depth = np.percentile(depth_downscaled[depth_downscaled != 0], 1)
        max_depth = np.percentile(depth_downscaled, 99)
        depthFrameColor = np.interp(depthFrame, (min_depth, max_depth), (0, 255)).astype(np.uint8)
        depthFrameColor = cv2.applyColorMap(depthFrameColor, cv2.COLORMAP_JET)

        counter+=1
        current_time = time.monotonic()
        if (current_time - startTime) > 1 :
            fps = counter / (current_time - startTime)
            counter = 0
            startTime = current_time

        detections = inDet.detections

        # If the frame is available, draw bounding boxes on it and show the frame
        height = frame.shape[0]
        width  = frame.shape[1]
        color_spool = (255, 0, 0)
        color_person = (0, 255, 0)
        color_text = (45, 255, 255)
        for detection in detections:
            roiData = detection.boundingBoxMapping
            roi = roiData.roi
            roi = roi.denormalize(depthFrameColor.shape[1], depthFrameColor.shape[0])
            topLeft = roi.topLeft()
            bottomRight = roi.bottomRight()
            xmin = int(topLeft.x)
            ymin = int(topLeft.y)
            xmax = int(bottomRight.x)
            ymax = int(bottomRight.y)
            cv2.rectangle(depthFrameColor, (xmin, ymin), (xmax, ymax), color, 1)

            # Denormalize bounding box
            x1 = int(detection.xmin * width)
            x2 = int(detection.xmax * width)
            y1 = int(detection.ymin * height)
            y2 = int(detection.ymax * height)
            try:
                label = labelMap[detection.label]
            except:
                label = detection.label
                if label == 'spool':
                    color_det = color_spool
                else:
                    color_det = color_person
            cv2.putText(frame, str(label), (x1 + 10, y1 + 20), cv2.FONT_HERSHEY_TRIPLEX, 0.5, color_text)
            cv2.putText(frame, "{:.2f}".format(detection.confidence*100), (x1 + 10, y1 + 35), cv2.FONT_HERSHEY_TRIPLEX, 0.5, color_text)
            cv2.putText(frame, f"X: {int(detection.spatialCoordinates.x)} mm", (x1 + 10, y1 + 50), cv2.FONT_HERSHEY_TRIPLEX, 0.5, color_text)
            cv2.putText(frame, f"Y: {int(detection.spatialCoordinates.y)} mm", (x1 + 10, y1 + 65), cv2.FONT_HERSHEY_TRIPLEX, 0.5, color_text)
            cv2.putText(frame, f"Z: {int(detection.spatialCoordinates.z)} mm", (x1 + 10, y1 + 80), cv2.FONT_HERSHEY_TRIPLEX, 0.5, color_text)

            cv2.rectangle(frame, (x1, y1), (x2, y2), color, cv2.FONT_HERSHEY_SIMPLEX)

        cv2.putText(frame, "NN fps: {:.2f}".format(fps), (2, frame.shape[0] - 4), cv2.FONT_HERSHEY_TRIPLEX, 0.4, color)
        cv2.namedWindow("depth", cv2.WINDOW_NORMAL)
        cv2.imshow("depth", depthFrameColor)
        cv2.namedWindow("rgb", cv2.WINDOW_NORMAL)
        cv2.imshow("rgb", frame)

        if cv2.waitKey(1) == ord('q'):
            break

Looks like the list in the src_port assignment is an empty list because of which the access to the 0th element gives this index out of range error. This tool is really useful for debugging. However I'm unable to get around this error itself for generating the pipeline graph. I hope you can help me out with resolving this error.

Thanks & Regards
Yishu

jakaskerl

Hi @yishu_corpex
The there is a problem with schema dump generated by depthai. The node SpatialDetectionNetwork does not have outNetwork output so the graph fails. This has to be added in the FW.

Thanks,
Jaka

yishu_corpex

Hi @jakaskerl

Thanks for checking it out. Let me know if it is resolved soon.

Thanks,
Yishu