error

[Huster-Hq]

one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [2, 128, 80, 88]], which is output 0 of ReluBackward0, is at version 3; expected version 0 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).

[voidrank]

Hi @Huster-Hq

Check these following 2 things:

1. Make sure the height and width of your input image are multiple of 16
2. Make sure you are using the correct version of mmcv and mmdet

Best,

Shiyi