The CPU usage reaches 100% and the program gets stuck in an infinite loop.

[samyzhh]

After locating the issue through the stack trace, it's found that the following code has fallen into an infinite loop.
Current thread 0x00007fdbd0fe9640 (most recent call first):
File "/home/samy/.local/lib/python3.10/site-packages/facexlib/detection/retinaface_utils.py", line 27 in forward
File "/home/samy/.local/lib/python3.10/site-packages/facexlib/detection/retinaface.py", line 160 in __detect_faces
File "/home/samy/.local/lib/python3.10/site-packages/facexlib/detection/retinaface.py", line 205 in detect_faces
File "/home/samy/.local/lib/python3.10/site-packages/facexlib/utils/face_restoration_helper.py", line 139 in get_face_landmarks_5
File "/home/samy/.local/lib/python3.10/site-packages/gfpgan/utils.py", line 111 in enhance
File "/home/samy/.local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115 in decorate_context
...

code:

 def forward(self):
    anchors = []
    for k, f in enumerate(self.feature_maps):
        min_sizes = self.min_sizes[k]
        for i, j in product(range(f[0]), range(f[1])):
            for min_size in min_sizes:
                s_kx = min_size / self.image_size[1]
                s_ky = min_size / self.image_size[0]
                dense_cx = [x * self.steps[k] / self.image_size[1] for x in [j + 0.5]]  #This line of code is stuck in an infinite loop.
                dense_cy = [y * self.steps[k] / self.image_size[0] for y in [i + 0.5]]
                for cy, cx in product(dense_cy, dense_cx):
                    anchors += [cx, cy, s_kx, s_ky]

    # back to torch land
    output = torch.Tensor(anchors).view(-1, 4)
    if self.clip:
        output.clamp_(max=1, min=0)
    return output

Environment versions:
Name: gfpgan Version: 1.3.8
Name: facexlib Version: 0.3.0
Name: torch Version: 2.0.1+cu118