Open JoyeMing opened 2 years ago
When I finished testing the other ten data sets, I tried the Imagenet data set. After the training was completed, an error occurred during the test:
File "/home/dpsh/Dassl.pytorch/dassl/evaluation/evaluator.py", line 69, in evaluate
acc = 100.0 * self. correct / self. total
ZeroDivisionError: float division by zero
Is there any similar situation? How was it resolved?
it means self._ total=0 which is weird
self._ total=0
you need to dive into the dataset and do a debugging to see if there is something wrong
When I finished testing the other ten data sets, I tried the Imagenet data set. After the training was completed, an error occurred during the test:
File "/home/dpsh/Dassl.pytorch/dassl/evaluation/evaluator.py", line 69, in evaluate
acc = 100.0 * self. correct / self. total
ZeroDivisionError: float division by zero
Is there any similar situation? How was it resolved?