InternalError (see above for traceback): Blas xGEMM launch failed

[wangyueft]

InternalError (see above for traceback): Blas xGEMM launch failed

[WangYueFt]

Hello,thank you for your reply,when I try to run code about sem_seg,I meet this problem,and I have one gpu(8gmemory),can you tell me how to solve this problem?looking forward your reply.
InternalError (see above for traceback): Blas xGEMM launch failed : a.shape=[1,4096,3], b.shape=[1,3,4096], m=4096, n=4096, k=3
[[Node: tower_0/MatMul = BatchMatMul[T=DT_FLOAT, adj_x=false, adj_y=false, _device="/job:localhost/replica:0/task:0/device:GPU:0"](tower_0/ExpandDims_1, tower_0/transpose)]]

Might be caused by tensorflow updates. Can you use an old version?

[longmalongma]

Hello,thank you for your reply,when I try to run code about sem_seg,I meet this problem,and I have one gpu(8gmemory),can you tell me how to solve this problem?looking forward your reply.
InternalError (see above for traceback): Blas xGEMM launch failed : a.shape=[1,4096,3], b.shape=[1,3,4096], m=4096, n=4096, k=3
[[Node: tower_0/MatMul = BatchMatMul[T=DT_FLOAT, adj_x=false, adj_y=false, _device="/job:localhost/replica:0/task:0/device:GPU:0"](tower_0/ExpandDims_1, tower_0/transpose)]]

Might be caused by tensorflow updates. Can you use an old version?

Hi, thanks for your reply.
I have successfully run your code about classification on ModelNet40,but i can not run your code about semantic segmentation on s3dis dataset. the version of tensorflow is tensorflow-gpu==1.9.0.
which version of tensorflow should i insatll?by the way,is the problem have anything to do with memory of my rtx 2080 memory(8g)?

[WangYueFt]

I think we use tensorflow 1.3 when we developed the code. Based on the discussion here tensorflow/tensorflow#25403, it seems the problem is "out of memory".

…

On Fri, Oct 18, 2019 at 9:37 PM longma ***@***.***> wrote: Hello,thank you for your reply,when I try to run code about sem_seg,I meet this problem,and I have one gpu(8gmemory),can you tell me how to solve this problem?looking forward your reply. InternalError (see above for traceback): Blas xGEMM launch failed : a.shape=[1,4096,3], b.shape=[1,3,4096], m=4096, n=4096, k=3 [[Node: tower_0/MatMul = BatchMatMul[T=DT_FLOAT, adj_x=false, adj_y=false, _device="/job:localhost/replica:0/task:0/device:GPU:0"](tower_0/ExpandDims_1, tower_0/transpose)]] Might be caused by tensorflow updates. Can you use an old version? Hi, thanks for your reply. I have successfully run your code about classification on ModelNet40,but i can not run your code about semantic segmentation on s3dis dataset. the version of tensorflow is tensorflow-gpu==1.9.0. which version of tensorflow should i insatll?by the way,is the problem have anything to do with memory of my rtx 2080 memory(8g)? — You are receiving this because you modified the open/close state. Reply to this email directly, view it on GitHub <#38?email_source=notifications&email_token=ACMGCNRY6YGNJ35WTOTHARLQPJQGBA5CNFSM4I2YXUGKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEBWW6XA#issuecomment-544042844>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ACMGCNX55622FWYYG3U5L7TQPJQGBANCNFSM4I2YXUGA> .

[longmalongma]

I think we use tensorflow 1.3 when we developed the code. Based on the discussion here tensorflow/tensorflow#25403, it seems the problem is "out of memory".
…
On Fri, Oct 18, 2019 at 9:37 PM longma @.***> wrote: Hello,thank you for your reply,when I try to run code about sem_seg,I meet this problem,and I have one gpu(8gmemory),can you tell me how to solve this problem?looking forward your reply. InternalError (see above for traceback): Blas xGEMM launch failed : a.shape=[1,4096,3], b.shape=[1,3,4096], m=4096, n=4096, k=3 [[Node: tower_0/MatMul = BatchMatMul[T=DT_FLOAT, adj_x=false, adj_y=false, _device="/job:localhost/replica:0/task:0/device:GPU:0"](tower_0/ExpandDims_1, tower_0/transpose)]] Might be caused by tensorflow updates. Can you use an old version? Hi, thanks for your reply. I have successfully run your code about classification on ModelNet40,but i can not run your code about semantic segmentation on s3dis dataset. the version of tensorflow is tensorflow-gpu==1.9.0. which version of tensorflow should i insatll?by the way,is the problem have anything to do with memory of my rtx 2080 memory(8g)? — You are receiving this because you modified the open/close state. Reply to this email directly, view it on GitHub <#38?email_source=notifications&email_token=ACMGCNRY6YGNJ35WTOTHARLQPJQGBA5CNFSM4I2YXUGKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEBWW6XA#issuecomment-544042844>, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACMGCNX55622FWYYG3U5L7TQPJQGBANCNFSM4I2YXUGA .

I think we use tensorflow 1.3 when we developed the code. Based on the discussion here tensorflow/tensorflow#25403, it seems the problem is "out of memory".
…
On Fri, Oct 18, 2019 at 9:37 PM longma @.***> wrote: Hello,thank you for your reply,when I try to run code about sem_seg,I meet this problem,and I have one gpu(8gmemory),can you tell me how to solve this problem?looking forward your reply. InternalError (see above for traceback): Blas xGEMM launch failed : a.shape=[1,4096,3], b.shape=[1,3,4096], m=4096, n=4096, k=3 [[Node: tower_0/MatMul = BatchMatMul[T=DT_FLOAT, adj_x=false, adj_y=false, _device="/job:localhost/replica:0/task:0/device:GPU:0"](tower_0/ExpandDims_1, tower_0/transpose)]] Might be caused by tensorflow updates. Can you use an old version? Hi, thanks for your reply. I have successfully run your code about classification on ModelNet40,but i can not run your code about semantic segmentation on s3dis dataset. the version of tensorflow is tensorflow-gpu==1.9.0. which version of tensorflow should i insatll?by the way,is the problem have anything to do with memory of my rtx 2080 memory(8g)? — You are receiving this because you modified the open/close state. Reply to this email directly, view it on GitHub <#38?email_source=notifications&email_token=ACMGCNRY6YGNJ35WTOTHARLQPJQGBA5CNFSM4I2YXUGKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEBWW6XA#issuecomment-544042844>, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACMGCNX55622FWYYG3U5L7TQPJQGBANCNFSM4I2YXUGA .

but I can run successfully other paper'codes about semantic segmentation on s3dis,except for your DGCNN.