尝试过此操作,以将Resnext用作来自here的Unet中的编码器,但始终出现RuntimeError:给定输入大小:(4320x4x4)。计算的输出大小:(4320x-6x-6)。输出大小太小,位于/opt/conda/conda-bld/pytorch_1525796793591/work/torch/lib/THCUNN/generic/SpatialAveragePooling.cu:63
(输入图片128 * 128批处理大小32)
LINE="$(tail -1 "$File")"
UnitID="$(echo "$LINE" | awk '{print $1}')"
UnitIP="$(echo "$LINE" | awk '{print $2}')"