Different from the question from " the error during training". I found that the training is OK, but when running tracking, the error always occur. The message of error is Value Error: cannot convert float NaN to integer. I think this is not the caused by unconverged training.
Different from the question from " the error during training". I found that the training is OK, but when running tracking, the error always occur. The message of error is Value Error: cannot convert float NaN to integer. I think this is not the caused by unconverged training.