在測試tensorflow的時候遇到的問題

1.

InternalError (see above for traceback): Blas xGEMV launch failed : a.shape=[1,3,3], b.shape=[1,3,1], m=3, n=1, k=3
	 [[Node: get_homographies/MatMul_1 = BatchMatMul[T=DT_FLOAT, adj_x=false, adj_y=false, _device="/job:localhost/replica:0/task:0/device:GPU:0"](get_homographies/transpose_1, get_homographies/Squeeze_5)]]
	 [[Node: soft_arg_min/ExpandDims/_3993 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_40572_soft_arg_min/ExpandDims", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]

此時查看了這個blog

https://blog.csdn.net/feixiang7701/article/details/81515447

 

2.多版本cuda

https://www.jianshu.com/p/6a6fbce9073f

參考這個鏈接

3. pip 鏡像

pip install -i https://pypi.tuna.tsinghua.edu.cn/simple some-package