train error

[zhuliqian]

/home/chase/EAST-master/icdar.py:249: RuntimeWarning: invalid value encountered in float_scalars return np.linalg.norm(np.cross(p2 - p1, p1 - p3)) / np.linalg.norm(p2 - p1) Cross point does not exist Traceback (most recent call last): File "/home/chase/EAST-master/icdar.py", line 659, in generator score_map, geo_map, training_mask = generate_rbox((new_h, new_w), text_polys, text_tags) File "/home/chase/EAST-master/icdar.py", line 521, in generate_rbox if point_dist_to_line(p1, new_p2, p0) > point_dist_to_line(p1, new_p2, p3): File "/home/chase/EAST-master/icdar.py", line 249, in point_dist_to_line return np.linalg.norm(np.cross(p2 - p1, p1 - p3)) / np.linalg.norm(p2 - p1) TypeError: unsupported operand type(s) for -: 'NoneType' and 'float'

[xxlxx1]

@zhuliqian i meet the same error and then another, have you soled the problem?

Traceback (most recent call last): File "/data/xlxia/code/EAST/icdar.py", line 658, in generator score_map, geo_map, training_mask = generate_rbox((new_h, new_w), text_polys, text_tags) File "/data/xlxia/code/EAST/icdar.py", line 520, in generate_rbox if point_dist_to_line(p1, new_p2, p0) > point_dist_to_line(p1, new_p2, p3): File "/data/xlxia/code/EAST/icdar.py", line 248, in point_dist_to_line return np.linalg.norm(np.cross(p2 - p1, p1 - p3)) / np.linalg.norm(p2 - p1

[bit2270943907]

i meet the same error ,i give up multigpu,and try only one gpu,the problem is solved

[ganliqiang]

meet the same error who can help us fix this problem

[1LOVESJohnny]

If ignore this problem, will it influence the training result?

[xxlxx1]

@1LOVESJohnny my result seems right

[1LOVESJohnny]

@1LOVESJohnny my result seems right

Thanks for your reply. Can I ask if you've the problem solved?

[xxlxx1]

@1LOVESJohnny i just ignore this error