打开微信,使用扫一扫进入页面后,点击右上角菜单,
点击“发送给朋友”或“分享到朋友圈”完成分享
使用的环境:开发平台镜像 public-server/mlu270_ubuntu16.04.pytorch v1.4.0-safe
操作:
cd /opt/cambricon source env_pytorch.sh source $CATCH_HOME/venv/pytorch/bin/activate python pytorch/tools/genoff.py -model resnet18 -mname test -mcore MLU270 -core_number 1 -batch_size 1 -half_input 1
出错信息:ValueError: unknown url type: 'resnet18-5c106cde.pth'
手动下载resnet18-5c106cde.pth并放至相应位置,再次执行
python pytorch/tools/genoff.py -model resnet18 -mname test -mcore MLU270 -core_number 1 -batch_size 1 -half_input 1
出错信息:
RuntimeError: torch_mlu::conv2d() Expected a value of type 'Tensor' for argument '_7' but instead found type 'NoneType'.
Position: 7
Value: None
Declaration: torch_mlu::conv2d(Tensor _0, Tensor _1, Tensor _2, int[] _3, int[] _4, int[] _5, int _6, Tensor _7, Tensor _8) -> (Tensor _0)
这是什么情况???conv2d操作前面7个参数分别对应:input, weight, bias, stride, padding, dilation, groups。后面两个 Tensor _7和Tensor _8 对应什么呢???
热门帖子
精华帖子