I am currently working on a program that uses an online OCR API. This API takes 2-5 seconds to send me a processed image, so instead of making the user wait for all images to be processed, the user can start working on the first image while the rest are processed on a different instance of python using multiprocessing. I have been using multiprocessing.Pipe() to send values back and forth. The code is here:
import multiprocessing as mp
# importing cv2, PIL, os, json, other stuff
def image_processor():
# processes the first image in the list, then moves the remaining images to a different python instance:
p_conn, c_conn = mp.Pipe()
p = mp.Process(target=Processing.worker, args=([c_conn, images, path], 5))
p.start()
while True:
out = p_conn.recv()
if not out:
break
else:
im_data.append(out)
p_conn.send(True)
class Processing:
def worker(data, mode, headers=0):
# (some if statements go here)
elif mode == 5:
print(data[0])
for im_name in data[1]:
if data[1].index(im_name) != 0:
im_path = f'{data[2]}\{im_name}' # find image path
im = pil_img.open(im_path).convert('L') # open and grayscale image with PIL
os.rename(im_path, f'{data[2]}\Archive\{im_name}') # move original to archive
im_grayscale = f'{data[2]}\g_{im_name}' # create grayscale image path
im.save(im_grayscale) # save grayscale image
ocr_data = json.loads(bl.Visual.OCR.ocr_space_file(im_grayscale)).get('ParsedResults')[0].get('ParsedText').splitlines()
print(ocr_data)
data[0].send([im_name, f'{data[2]}\Archive\{im_name}', ocr_data])
data[0].recv()
data[0].send(False)
This leaves me with the following traceback:
Process Process-1:
Traceback (most recent call last):
File "C:\Users\BruhK\AppData\Local\Programs\Python\Python310\lib\multiprocessing\process.py", line 315, in _bootstrap
self.run()
File "C:\Users\BruhK\AppData\Local\Programs\Python\Python310\lib\multiprocessing\process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "c:\Users\BruhK\PycharmProjects\pythonProject\FleetFeet-OCR-Final.py", line 275, in worker
data[0].send([{im_name}, f'{data[2]}\Archive\{im_name}', ocr_data])
File "C:\Users\BruhK\AppData\Local\Programs\Python\Python310\lib\multiprocessing\connection.py", line 211, in send
self._send_bytes(_ForkingPickler.dumps(obj))
File "C:\Users\BruhK\AppData\Local\Programs\Python\Python310\lib\multiprocessing\connection.py", line 285, in _send_bytes
ov, err = _winapi.WriteFile(self._handle, buf, overlapped=True)
BrokenPipeError: [WinError 232] The pipe is being closed
Note that the data sent from the child function to the parent was a 2d or 3d array. In testing I've been able to send 2d and 3d arrays back and forth between child and parent functions.
An example of the code I used for testing is as follows:
import multiprocessing as mp
import random
import time
def hang(p):
hang_time = random.randint(1, 5)
time.sleep(hang_time)
print(p)
p.send(hang_time)
time.sleep(1)
class Child:
def process():
start = time.time()
p_conn, c_conn = mp.Pipe()
p = mp.Process(target=hang, args=(c_conn,))
p.start()
out = p_conn.recv()
print(f'Waited for {time.time() - start}')
p.join()
print(f'New time: {time.time() - start}')
return out
class Parent:
def run():
# do some stuff
print(f'Hang time: {Child.process()}')
# do some stuff
if __name__ == '__main__':
Parent.run()
How do I fix this issue? Is there any additional information needed?
it looks you have wrong indenting: The data[0].send(False) is inside the for loop, so the it sends the False after processing the first image and your main process exits the while(True)