"Segmentation fault" error with coral Dev Board + external Coral ML Accelerator (USB) - Yolov5su

[MECHAAMER]

Description

I'm encountering a "Segmentation fault" error while trying to run a segmented YOLOv5s model on my Coral Dev Board with an external Coral ML Accelerator (USB). I followed the recommended steps to export, compile, and segment the model using edgetpu_compiler.

I follow these steps:

1. I trained Yolov5su model, then I exported the model as tflite - 8int by using:
   model.export()

2. then I use the edgetpu_compiler to compile the tflite model and segmented it into 2 models:
   edgetpu_compiler model.tflite --num_segments=2

3. then I get 12 files, 8 models and 4 logs, the models are:
   1- best_float32_segment_0_of_2.tflite
   2- best_float32_segment_1_of_2.tflite
   3- best_float32_segment_0_of_2_edgetpu.tflite
   4- best_float32_segment_1_of_2_edgetpu.tflite
   5- best_full_integer_quant_segment_0_of_2.tflite
   6- best_full_integer_quant_segment_1_of_2.tflite
   7- best_full_integer_quant_segment_0_of_2_edgetpu.tflite
   8- best_full_integer_quant_segment_1_of_2_edgetpu.tflite

I transfer the "best_full_integer_quant_segment_0_of_2_edgetpu.tflite" and
"best_full_integer_quant_segment_1_of_2_edgetpu.tflite" to the coral board and I tried to run the models to detect object in a video, the code:

import argparse
import re
import threading
import time

import numpy as np
import cv2

from pycoral.adapters import classify
from pycoral.adapters import common
import pycoral.pipeline.pipelined_model_runner as pipeline
from pycoral.utils.dataset import read_label_file
from pycoral.utils.edgetpu import list_edge_tpus
from pycoral.utils.edgetpu import make_interpreter


def _get_devices(num_devices):
  edge_tpus = list_edge_tpus()

  if len(edge_tpus) < num_devices:
    raise RuntimeError(
        'Not enough Edge TPUs detected, expected %d, detected %d.' %
        (num_devices, len(edge_tpus)))

  num_pci_devices = sum(1 for device in edge_tpus if device['type'] == 'pci')

  return ['pci:%d' % i for i in range(min(num_devices, num_pci_devices))] + [
      'usb:%d' % i for i in range(max(0, num_devices - num_pci_devices))
  ]


def _make_runner(model_paths, devices):
  """Constructs PipelinedModelRunner given model paths and devices."""
  print('Using devices: ', devices)
  print('Using models: ', model_paths)
   
  print("  hey runner   1")
  if len(model_paths) != len(devices):
    raise ValueError('# of devices and #of model_paths should match')
  
  print("  hey runner   2", model_paths[0], devices[1])
 
  interpreters = []
  interpreter = make_interpreter(model_paths[0], devices[0])
  print("  hey runner   3")
  interpreter.allocate_tensors()
  print("  hey runner   4")
  interpreters.append(interpreter)
  print("  hey runner   5", model_paths[1], devices[0])
  
  interpreter2 = make_interpreter(model_paths[1], devices[1])
  print("  hey runner   6")
  interpreter.allocate_tensors()
  interpreter2.allocate_tensors()
  print("  hey runner   7")
  interpreters.append(interpreter2)
  print("  hey runner   8")

  return pipeline.PipelinedModelRunner(interpreters)


def main():
  parser = argparse.ArgumentParser(
      formatter_class=argparse.ArgumentDefaultsHelpFormatter)
  parser.add_argument(
      '-m',
      '--models',
      required=True,
      help=('File path template of .tflite model segments, e.g.,'
            'inception_v3_299_quant_segment_%d_of_2_edgetpu.tflite'))
  parser.add_argument(
      '-i', '--input', required=True, help='Image to be classified.')
  parser.add_argument('-l', '--labels', help='File path of labels file.')
  parser.add_argument(
      '-k',
      '--top_k',
      type=int,
      default=1,
      help='Max number of classification results')
  parser.add_argument(
      '-t',
      '--threshold',
      type=float,
      default=0.0,
      help='Classification score threshold')
  parser.add_argument(
      '-c',
      '--count',
      type=int,
      default=1,
      help='Number of times to run inference')
  args = parser.parse_args()
  labels = {0:"pedestrian", 1:"people", 2:"bicycle", 3:"car", 4:"van", 5:"truck", 6:"tricycle", 7:"awning-tricycle", 8:"bus", 9:"motor"}
  print("hey lets begin   1")
  result = re.search(r'^.*_segment_%d_of_(?P<num_segments>[0-9]+)_.*.tflite',
                     args.models)
  print("hey lets begin   2")

  if not result:
    print("hey lets begin    3")

    raise ValueError(
        '--models should follow *_segment%d_of_[num_segments]_*.tflite pattern')
  print("hey lets begin    4")

  num_segments = int(result.group('num_segments'))
  model_paths = [args.models % i for i in range(num_segments)]
  print("hey lets begin    5")

  devices = _get_devices(num_segments)

  print("hey lets begin    6")

  runner = _make_runner(model_paths, devices)
  
  print("hey lets begin      7")


  # Get the input name and size
  size = common.input_size(runner.interpreters()[0])
  
  print("hey lets begin     8")

  name = common.input_details(runner.interpreters()[0], 'name')
 
  print("hey lets begin    9")

  cap = cv2.VideoCapture(args.input)
  
  print("hey lets begin    10")

  if not cap.isOpened():
      print("Error opening video capture device")
      return
  
  print("hey lets begin    11")

  while True:
      ret, frame = cap.read()
      if not ret:
          break

      # Preprocess the frame
      height, width, _ = frame.shape
      new_height = int(640 * height / width)
      image = cv2.resize(frame, (640, new_height))

      # Run inference
      runner.push({name: image})
      
      output_details = runner.interpreters()[-1].get_output_details()[0]
      scale, zero_point = output_details['quantization']
  
      result = runner.pop()

      if result:
          # Process the results
          values, = result.values()
          scores = scale * (values[0].astype(np.int64) - zero_point)
          classes, scores = classify.get_classes_from_scores(result[0], args.top_k, args.threshold)
          
          for klass in classes:
              print('%s: %.5f' % (labels.get(klass.id, klass.id), klass.score))
          
          print('-------RESULTS--------')
      else:
          print("No results")

if __name__ == '__main__':
  main()

3. then I try execute the python file:

python3 test2tpu.py -m best_full_integer_quant_segment_%d_of_2_edgetpu.tflite -i "/coral/720p/Busy Road.mp4"

the output that I get:

hey lets begin 1
hey lets begin 2
hey lets begin 4
hey lets begin 5
hey lets begin 6
Using devices: ['pci:0', 'usb:0']
Using models: ['best_full_integer_quant_segment_0_of_2_edgetpu.tflite', 'best_full_integer_quant_segment_1_of_2_edgetpu.tflite']
hey runner 1
hey runner 2 best_full_integer_quant_segment_0_of_2_edgetpu.tflite usb:0
hey runner 3
hey runner 4
hey runner 5 best_full_integer_quant_segment_1_of_2_edgetpu.tflite pci:0
Segmentation fault

Note:
pycoral version: 2.0.0

Click to expand!

Issue Type

support

Operating System

_LInux Mendel 5.3 _

Coral Device

Coral dev board

Other Devices

USB ML Accelerator

Programming Language

Python3.7

Relevant Log Output

No response