QianLingjun

没太搞懂作者的思路，能不能进行一些补充。我这训练还没开始，CPU内存就炸了

utilization of GPU is lower

1

When I increased the training data to 1000 CT cases, the training of 4 12G 1080ti was normal, but the utilization of GPU would intermittently all be 0. The end...

Do you have evaluate results? the MAE loss ,thinks

sklearn.metrics.accuracy_score gt和pred写反的问题

1

官方：sklearn.metrics.accuracy_score(y_true, y_pred, *, normalize=True, sample_weight=None) 本文：acc = metrics.accuracy_score(predicts, gts) 请问这里predicts,和gts，是不是写反了？

heatmap而不是heatmep

请问博主有pytorch的版本吗？谢谢