search

ibaiGorordo / TfLite-Ultra-Fast-Lane-Detection-Inference

Example scripts for the detection of lanes using the ultra fast lane detection model in Tensorflow Lite.
MIT License
21 stars 2 forks source link

ValueError: operands could not be broadcast together with shapes (200,18,4) (100,1,1) #4

Closed yomamdde closed 1 year ago

yomamdde commented 1 year ago

I encountered an error while running the lane detection script.

2023-07-13 16:38:19.233089: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.10.2 Traceback (most recent call last): File "/home/nvidia/Downloads/TfLite-Ultra-Fast-Lane-Detection-Inference/videoLaneDetection.py", line 32, in <module> output_img = lane_detector.detect_lanes(frame) File "/home/nvidia/Downloads/TfLite-Ultra-Fast-Lane-Detection-Inference/ultrafastLaneDetector/ultrafastLaneDetector.py", line 79, in detect_lanes self.lanes_points, self.lanes_detected = self.process_output(output, self.cfg) File "/home/nvidia/Downloads/TfLite-Ultra-Fast-Lane-Detection-Inference/ultrafastLaneDetector/ultrafastLaneDetector.py", line 135, in process_output loc = np.sum(prob * idx, axis=0) ValueError: operands could not be broadcast together with shapes (200,18,4) (100,1,1)

It would be really helpful if you could look into this issue and recommend a solution.

yomamdde commented 1 year ago

I solved it. I downloaded the wrong model(tusimple-> culane).