Closed Naga-Renu closed 5 years ago
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
I also got this issue and after some hours of investigation 😂 I found out that my xmin, xmax, ymin, ymax were in the wrong order, and the generated entries in the batch were deleted by degenerate_box_handling. Fixed them and now it's all fine, I just wrote in case anyone else gets this error and this might be the problem.
x
can you please tell how did you solve this issue?
I also got this issue and after some hours of investigation 😂 I found out that my xmin, xmax, ymin, ymax were in the wrong order, and the generated entries in the batch were deleted by degenerate_box_handling. Fixed them and now it's all fine, I just wrote in case anyone else gets this error and this might be the problem.
You save my life thanks bro :)
The following error generated while executing fit_generator:
FLIR_ADAS Thermal Data set had been used instead of PASCAL VOC data set
DegenerateBatchError: You produced an empty batch. This might be because the images in the batch vary in their size and/or number of channels. Note that after all transformations (if any were given) have been applied to all images in the batch, all images must be homogenous in size along all axes.
Can anyone have idea when the above error will be thrown?