cv2.cvtColor breaks after hours of running - python-3.x

Question

I am training a pix2pix GAN but two times now my program has randomly broken after hours of running with the same problem.
The runtime error I am getting is :
error: Caught error in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/_utils/worker.py", line 302, in _worker_loop
data = fetcher.fetch both(index)
File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/_utils/fetch.py", line 58, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/_utils/fetch.py", line 58, in <listcomp>
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/content/gdrive/My Drive/All_Deep_Learning/PythonCustomLibraries/pix2pixdatasetlib.py", line 40, in __getitem__
File "/content/gdrive/My Drive/All_Deep_Learning/PythonCustomLibraries/pix2pixdatasetlib.py", line 185, in process_images
File "/content/gdrive/My
Drive/All_Deep_Learning/PythonCustomLibraries/pix2pixdatasetlib.py", line 112, in read_a_image cv2.error: OpenCV(4.6.0) /io/opencv/modules/imgproc/src/color.cpp:182: error: (-215:Assertion failed) !_src.empty() in function 'cvtColor'
This last time it ran for 209 epochs before breaking at 64% of the 210 epoch. So the confusing part is why would it break after running for so long and the only thing I could think of is it most be some kind of memory problem... IDK
Here is my code:
class Pix2PixDataset(Dataset):
def __init__(self, data_points, transforms = None):
self.data_points = data_points
self.transforms = transforms
self.resize = T.Resize((512,512))
def __getitem__(self, index) :
image, y_label = process_images(self.data_points[index].reference_image, self.data_points[index].drawing )
image = self.resize(image)
y_label = self.resize(y_label)
if self.transforms:
image = self.transforms(image)
y_label = self.transforms(y_label)
return(image, y_label)
def __len__(self):
return len(self.data_points)
Here is my read a image function
def read_a_image(a_image_path):
image = cv2.imread(a_image_path)
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
return image
And here is my process image function
def process_images(reference_image_path, drawing_path):
reference_image = read_a_image(reference_image_path)
drawing = read_a_image(drawing_path)
reference_image = Image.fromarray(reference_image)
drawing = Image.fromarray(drawing)
if(apply_random_transformation):
reference_image, drawing = random_transformation(reference_image,drawing)
return reference_image, drawing
And here is my data point class:
class DataPoint:
def __init__(self, reference_image, drawing):
self.reference_image = reference_image
self.drawing = drawing
The error message indicates that the input image _src passed to the cv2.cvtColor function in the read_a_image function is empty. This can happen if the image path provided to the function is incorrect or if the file is missing or corrupted. But again it ran for over 12 hours both times, so why is the image path all of a sudden incorrect or the file is missing or corrupted?
I am using Google Collab and my dataset is in my google drive but I Mounted to my notebook