Skip to content

Instantly share code, notes, and snippets.

@Tagussan

Tagussan/log

Created November 2, 2021 01:56
Show Gist options
  • Save Tagussan/39fb7b3a3cd3316db61d58e84c687b0a to your computer and use it in GitHub Desktop.
Save Tagussan/39fb7b3a3cd3316db61d58e84c687b0a to your computer and use it in GitHub Desktop.
Download ZIP
Raw
log
INFO:Neuron:There are 1 ops of 1 different types in the TorchScript that are not compiled by neuron-cc: aten::adaptive_max_pool2d, (For more information see https://github.com/aws/aws-neuron-sdk/blob/master/release-notes/neuron-cc-ops/neuron-cc-ops-pytorch.md)
INFO:Neuron:Number of arithmetic operators (pre-compilation) before = 306, fused = 295, percent fused = 96.41%
INFO:Neuron:Compiling function _NeuronGraph$868 with neuron-cc
INFO:Neuron:Compiling with command line: '/home/ubuntu/anaconda3/envs/aws_neuron_pytorch_p36/bin/neuron-cc compile /tmp/tmp1qen5wtt/graph_def.pb --framework TENSORFLOW --pipeline compile SaveTemps --output /tmp/tmp1qen5wtt/graph_def.neff --io-config {"inputs": {"0:0": [[1, 5, 3, 384, 384], "float32"]}, "outputs": ["Reshape_2:0"]} --verbose 35'
.[01:48:52] /opt/brazil-pkg-cache/packages/DmlcTvm/DmlcTvm-1.7.2.0/AL2_x86_64/generic-flavor/src/src/relay/pass/do_replication.cc:66: Replication is not applied to group convolution. Kernel and data input channels do not match[3, 3, 4, 128] [5, 98, 98, 128]
[01:48:52] /opt/brazil-pkg-cache/packages/DmlcTvm/DmlcTvm-1.7.2.0/AL2_x86_64/generic-flavor/src/src/relay/pass/do_replication.cc:66: Replication is not applied to group convolution. Kernel and data input channels do not match[3, 3, 4, 128] [5, 98, 98, 128]
[01:48:52] /opt/brazil-pkg-cache/packages/DmlcTvm/DmlcTvm-1.7.2.0/AL2_x86_64/generic-flavor/src/src/relay/pass/do_replication.cc:66: Replication is not applied to group convolution. Kernel and data input channels do not match[3, 3, 4, 128] [5, 98, 98, 128]
[01:48:52] /opt/brazil-pkg-cache/packages/DmlcTvm/DmlcTvm-1.7.2.0/AL2_x86_64/generic-flavor/src/src/relay/pass/do_replication.cc:66: Replication is not applied to group convolution. Kernel and data input channels do not match[3, 3, 8, 256] [5, 98, 98, 256]
[01:48:52] /opt/brazil-pkg-cache/packages/DmlcTvm/DmlcTvm-1.7.2.0/AL2_x86_64/generic-flavor/src/src/relay/pass/do_replication.cc:66: Replication is not applied to group convolution. Kernel and data input channels do not match[3, 3, 8, 256] [5, 50, 50, 256]
[01:48:52] /opt/brazil-pkg-cache/packages/DmlcTvm/DmlcTvm-1.7.2.0/AL2_x86_64/generic-flavor/src/src/relay/pass/do_replication.cc:66: Replication is not applied to group convolution. Kernel and data input channels do not match[3, 3, 8, 256] [5, 50, 50, 256]
[01:48:52] /opt/brazil-pkg-cache/packages/DmlcTvm/DmlcTvm-1.7.2.0/AL2_x86_64/generic-flavor/src/src/relay/pass/do_replication.cc:66: Replication is not applied to group convolution. Kernel and data input channels do not match[3, 3, 8, 256] [5, 50, 50, 256]
[01:48:52] /opt/brazil-pkg-cache/packages/DmlcTvm/DmlcTvm-1.7.2.0/AL2_x86_64/generic-flavor/src/src/relay/pass/do_replication.cc:66: Replication is not applied to group convolution. Kernel and data input channels do not match[3, 3, 16, 512] [5, 50, 50, 512]
[01:48:52] /opt/brazil-pkg-cache/packages/DmlcTvm/DmlcTvm-1.7.2.0/AL2_x86_64/generic-flavor/src/src/relay/pass/do_replication.cc:66: Replication is not applied to group convolution. Kernel and data input channels do not match[3, 3, 16, 512] [5, 26, 26, 512]
[01:48:52] /opt/brazil-pkg-cache/packages/DmlcTvm/DmlcTvm-1.7.2.0/AL2_x86_64/generic-flavor/src/src/relay/pass/do_replication.cc:66: Replication is not applied to group convolution. Kernel and data input channels do not match[3, 3, 16, 512] [5, 26, 26, 512]
[01:48:52] /opt/brazil-pkg-cache/packages/DmlcTvm/DmlcTvm-1.7.2.0/AL2_x86_64/generic-flavor/src/src/relay/pass/do_replication.cc:66: Replication is not applied to group convolution. Kernel and data input channels do not match[3, 3, 16, 512] [5, 26, 26, 512]
[01:48:52] /opt/brazil-pkg-cache/packages/DmlcTvm/DmlcTvm-1.7.2.0/AL2_x86_64/generic-flavor/src/src/relay/pass/do_replication.cc:66: Replication is not applied to group convolution. Kernel and data input channels do not match[3, 3, 16, 512] [5, 26, 26, 512]
[01:48:52] /opt/brazil-pkg-cache/packages/DmlcTvm/DmlcTvm-1.7.2.0/AL2_x86_64/generic-flavor/src/src/relay/pass/do_replication.cc:66: Replication is not applied to group convolution. Kernel and data input channels do not match[3, 3, 16, 512] [5, 26, 26, 512]
[01:48:52] /opt/brazil-pkg-cache/packages/DmlcTvm/DmlcTvm-1.7.2.0/AL2_x86_64/generic-flavor/src/src/relay/pass/do_replication.cc:66: Replication is not applied to group convolution. Kernel and data input channels do not match[3, 3, 32, 1024] [5, 26, 26, 1024]
[01:48:52] /opt/brazil-pkg-cache/packages/DmlcTvm/DmlcTvm-1.7.2.0/AL2_x86_64/generic-flavor/src/src/relay/pass/do_replication.cc:66: Replication is not applied to group convolution. Kernel and data input channels do not match[3, 3, 32, 1024] [5, 14, 14, 1024]
[01:48:52] /opt/brazil-pkg-cache/packages/DmlcTvm/DmlcTvm-1.7.2.0/AL2_x86_64/generic-flavor/src/src/relay/pass/do_replication.cc:66: Replication is not applied to group convolution. Kernel and data input channels do not match[3, 3, 32, 1024] [5, 14, 14, 1024]
...11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: ***************************************************************
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: An Internal Compiler Error has occurred
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: ***************************************************************
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]:
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: Error message: Axis for (c_55_0_7237: range(0, 2, 1)) { # indent=4
for (r_55_0_0_0: range(0, 5, 1)) { # indent=6
for (h_46_0_0_4251_0_h_46_0_0_4251_1_1: range(0, 5, 1)) { # indent=8
for (p_10534: range(0, 2, 1)) { # indent=10
for (c_46_0_0: range(0, 2, 1)) { # indent=12
for (c_46_0_1: range(0, 16, 1)) { # indent=14
float32[2, 5, 5, 5, 2, 64, 384] float32<64 x 384> TongaPSum partitions[5] float32 [2, 5, 5, 5, 2, 64, 384] %9272[c_55_0_7237,n_55_7237_10418_10420,r_55_0_0_0,h_46_0_0_4251_0_h_46_0_0_4251_1_1,p_10534,i0.64,i1.384] = matmul(|V2<4 x 384> TongaSB partitions[4] |V2 [2, 16, 5, 24, 4, 384] %'transpose_17:0'[c_46_0_0,c_46_0_1,n_55_7237_10418_10420,5r_55_0_0_0+h_46_0_0_4251_0_h_46_0_0_4251_1_1,i2.4,i1.384], |V2<4 x 64> TongaSB partitions[2] |V2 [2, 2, 4, 2048] %'t288-4989_local_4997'[c_55_0_7237,c_46_0_0,i2.4,i0.64+64p_10534+128c_46_0_1]), contract={c_46_0_0=[0:2:1],c_46_0_1=[0:16:1]}, lhs_free={n_55_7237_10418_10420=[0:5:1],r_55_0_0_0=[0:5:1],h_46_0_0_4251_0_h_46_0_0_4251_1_1=[0:5:1]}, rhs_free={c_55_0_7237=[0:2:1],p_10534=[0:2:1]}) # id=9348, instances=16000 # dl = Conv2D_3 if -5r_55_0_0_0+-1h_46_0_0_4251_0_h_46_0_0_4251_1_1+23 >= 0
}
}
|V2[5, 2, 5, 5, 128, 384] |V2<64 x 384> TongaSB partitions[4] |V2 [5, 2, 5, 5, 128, 384] %10533[n_55_7237_10418_10420,c_55_0_7237,r_55_0_0_0,h_46_0_0_4251_0_h_46_0_0_4251_1_1,i0.64+64p_10534,i1.384] = tensorscalarptr_subtract(float32<64 x 384> TongaPSum partitions[5] float32 [2, 5, 5, 5, 2, 64, 384] %9272[c_55_0_7237,n_55_7237_10418_10420,r_55_0_0_0,h_46_0_0_4251_0_h_46_0_0_4251_1_1,p_10534,i0.64,i1.384], float32<64 x 1> TongaSB partitions[0] float32 [128, 126] %10468[i0.64+64p_10534,c_55_0_7237+4]) # id=9353, instances=500 # dl = Conv2D_3 if -5r_55_0_0_0+-1h_46_0_0_4251_0_h_46_0_0_4251_1_1+23 >= 0
|V2[2, 5, 5, 128, 5, 384] |V2<64 x 384> TongaSB partitions[3] |V2 [2, 5, 5, 128, 5, 384] %'transpose_21:0'[c_55_0_7237,n_55_7237_10418_10420,r_55_0_0_0,i0.64+64p_10534,h_46_0_0_4251_0_h_46_0_0_4251_1_1,i1.384] = tensorscalarptr_add(multiply(float32<64 x 1> TongaSB partitions[0] float32 [128, 126] %10468[i0.64+64p_10534,c_55_0_7237+2], |V2<64 x 384> TongaSB partitions[4] |V2 [5, 2, 5, 5, 128, 384] %10533[n_55_7237_10418_10420,c_55_0_7237,r_55_0_0_0,h_46_0_0_4251_0_h_46_0_0_4251_1_1,i0.64+64p_10534,i1.384]), float32<64 x 1> TongaSB partitions[0] float32 [128, 126] %10468[i0.64+64p_10534,c_55_0_7237]) # id=9355, instances=500 # dl = Conv2D_3 if -5r_55_0_0_0+-1h_46_0_0_4251_0_h_46_0_0_4251_1_1+23 >= 0
}
}
for (p_10536: range(0, 2, 1)) { # indent=8
|V2[5, 2, 5, 128, 1] |V2<64 x 1> TongaSB partitions[3] |V2 [5, 2, 5, 128, 1] %10535[n_55_7237_10418_10420,c_55_0_7237,r_55_0_0_0,i0.64+64p_10536,0] = tensor_reduce_mean(|V2<64 x 1920> TongaSB partitions[3] |V2 [2, 5, 5, 128, 5, 384] %'transpose_21:0'[c_55_0_7237,n_55_7237_10418_10420,r_55_0_0_0,i0.64+64p_10536,i5.5,i1.2+2i2.48+96i3.2+192i4.2]);reduce_size=1920) # id=9356, instances=100 # dl = AvgPool if -5r_55_0_0_0+-1i5.5+23 >= 0
float32[5, 2, 5, 64, 2, 1] float32<64 x 1> TongaPSum partitions[3] float32 [5, 2, 5, 64, 2, 1] %10360[n_55_7237_10418_10420,c_55_0_7237,r_55_0_0_0,i0.64,p_10536,0] = tensorscalar_multiply(|V2<64 x 1> TongaSB partitions[3] |V2 [5, 2, 5, 128, 1] %10535[n_55_7237_10418_10420,c_55_0_7237,r_55_0_0_0,i0.64+64p_10536,0], 0.2) # id=9357, instances=100 # dl = AvgPool
|V2[2, 128, 5, 1] |V2<64 x 1> TongaSB partitions[1] |V2 [2, 128, 5, 1] %7234[c_55_0_7237,i0.64+64p_10536,n_55_7237_10418_10420,0] = loop_reduce_macro_add(float32<64 x 1> TongaPSum partitions[3] float32 [5, 2, 5, 64, 2, 1] %10360[n_55_7237_10418_10420,c_55_0_7237,r_55_0_0_0,i0.64,p_10536,0]);reduce_axes=r_55_0_0_0=[0:5:1]) # id=9358, instances=100 # dl = AvgPool
}
}
} doesn't appear in params or loopnest
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]:
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: Error class: ValueError
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: Error location: Unknown
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: Command line: /home/ubuntu/anaconda3/envs/aws_neuron_pytorch_p36/bin/neuron-cc compile /tmp/tmp1qen5wtt/graph_def.pb --framework TENSORFLOW --pipeline compile SaveTemps --output /tmp/tmp1qen5wtt/graph_def.neff --io-config '{"inputs": {"0:0": [[1, 5, 3, 384, 384], "float32"]}, "outputs": ["Reshape_2:0"]}' --verbose 35
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]:
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: Internal details:
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/driver/CommandDriver.py", line 223, in neuroncc.driver.CommandDriver.CommandDriver.run
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/driver/commands/CompileCommand.py", line 485, in neuroncc.driver.commands.CompileCommand.CompileCommand.run
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/driver/Job.py", line 289, in neuroncc.driver.Job.SingleInputJob.run
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/driver/Pipeline.py", line 30, in neuroncc.driver.Pipeline.Pipeline.runSingleInput
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/driver/Job.py", line 289, in neuroncc.driver.Job.SingleInputJob.run
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/driver/Pipeline.py", line 30, in neuroncc.driver.Pipeline.Pipeline.runSingleInput
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/driver/Job.py", line 289, in neuroncc.driver.Job.SingleInputJob.run
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/driver/jobs/Frontend.py", line 419, in neuroncc.driver.jobs.Frontend.Frontend.runSingleInput
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/driver/jobs/Frontend.py", line 369, in neuroncc.driver.jobs.Frontend.Frontend.runTVMFrontend
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/driver/jobs/Frontend.py", line 370, in neuroncc.driver.jobs.Frontend.Frontend.runTVMFrontend
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/driver/jobs/Frontend.py", line 380, in neuroncc.driver.jobs.Frontend.Frontend.runTVMFrontend
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/driver/jobs/Frontend.py", line 350, in neuroncc.driver.jobs.Frontend.Frontend.runTVMFrontend.tensorize
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/Frontend.py", line 198, in neuroncc.starfish.penguin.Frontend.tensorizeRelay
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/Frontend.py", line 199, in neuroncc.starfish.penguin.Frontend.tensorizeRelay
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/Frontend.py", line 221, in neuroncc.starfish.penguin.Frontend.tensorizeRelay
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/Frontend.py", line 111, in neuroncc.starfish.penguin.Frontend.compile_cu
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/DotTransform.py", line 378, in neuroncc.starfish.penguin.DotTransform.PassManager.transformFunction
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/DotTransform.py", line 124, in neuroncc.starfish.penguin.DotTransform.DotTransform.runOnFunction
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/DotTransform.py", line 178, in neuroncc.starfish.penguin.DotTransform.DotTransform.run_with_exception_handling
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/DotTransform.py", line 160, in neuroncc.starfish.penguin.DotTransform.DotTransform.run_with_exception_handling
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/DotTransform.py", line 186, in neuroncc.starfish.penguin.DotTransform.DotTransform.timed_run_
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/DotTransform.py", line 188, in neuroncc.starfish.penguin.DotTransform.DotTransform.timed_run_
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/DotTransform.py", line 189, in neuroncc.starfish.penguin.DotTransform.DotTransform.timed_run_
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/DotTransform.py", line 206, in neuroncc.starfish.penguin.DotTransform.DotTransform.run_
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/DotTransform.py", line 207, in neuroncc.starfish.penguin.DotTransform.DotTransform.run_
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/DotTransform.py", line 287, in neuroncc.starfish.penguin.DotTransform.DotTransform.transformFunction
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/DotTransform.py", line 281, in neuroncc.starfish.penguin.DotTransform.DotTransform.runTransforms
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/targets/tonga/passes/TensorInitialization.py", line 141, in neuroncc.starfish.penguin.targets.tonga.passes.TensorInitialization.TensorInitialization.transformStmts
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/DotTransform.py", line 115, in neuroncc.starfish.penguin.DotTransform.DotTransform.transform
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/targets/tonga/passes/TensorInitialization.py", line 284, in neuroncc.starfish.penguin.targets.tonga.passes.TensorInitialization.TensorInitialization.transformTensor
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/targets/tonga/passes/TensorInitialization.py", line 274, in neuroncc.starfish.penguin.targets.tonga.passes.TensorInitialization.TensorInitialization.memsetReduceMacroTensor
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/targets/tonga/passes/TensorInitialization.py", line 254, in neuroncc.starfish.penguin.targets.tonga.passes.TensorInitialization.TensorInitialization.memsetTile
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/targets/tonga/passes/TensorInitialization.py", line 47, in neuroncc.starfish.penguin.targets.tonga.passes.TensorInitialization.TongaMemsetSimplifier.codegenMemset
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/targets/tonga/passes/TensorInitialization.py", line 40, in neuroncc.starfish.penguin.targets.tonga.passes.TensorInitialization.TongaMemsetSimplifier.access_without_predicates
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/targets/tonga/passes/TensorInitialization.py", line 41, in neuroncc.starfish.penguin.targets.tonga.passes.TensorInitialization.TongaMemsetSimplifier.access_without_predicates
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/IntegerSetAnalysis.py", line 473, in neuroncc.starfish.penguin.IntegerSetAnalysis.IntegerSetAnalysis.create_access
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/targets/tonga/passes/TensorInitialization.py", line 28, in neuroncc.starfish.penguin.targets.tonga.passes.TensorInitialization.TongaMemsetSimplifier.create_access_without_domain
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/IntegerSetAnalysis.py", line 410, in neuroncc.starfish.penguin.IntegerSetAnalysis.IntegerSetAnalysis.create_access_map
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/IntegerSetAnalysis.py", line 254, in neuroncc.starfish.penguin.IntegerSetAnalysis.IntegerSetWrapper.create_access_map_impl
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/IntegerSetAnalysis.py", line 228, in neuroncc.starfish.penguin.IntegerSetAnalysis.IntegerSetWrapper.build_aff
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: File "neuroncc/starfish/penguin/IntegerSetAnalysis.py", line 197, in neuroncc.starfish.penguin.IntegerSetAnalysis.IntegerSetWrapper.build_aff.build
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]:
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: Version information:
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: Neuron Compiler version 1.7.3.0+c02f9fde4
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]:
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: HWM version 1.7.0.0-0
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: NEFF version Dynamic
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: TVM version 1.7.2.0+0
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: NumPy version 1.18.5
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: MXNet not available
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: TF not available
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]:
11/02/2021 01:49:59 AM ERROR 3909 [neuron-cc]: Artifacts stored in: /tmp/tmp1qen5wtt
Compiler status ERROR
INFO:Neuron:Compile command returned: 1
WARNING:Neuron:torch.neuron.trace failed on _NeuronGraph$868; falling back to native python function call
ERROR:Neuron:neuron-cc failed with the following command line call:
/home/ubuntu/anaconda3/envs/aws_neuron_pytorch_p36/bin/neuron-cc compile /tmp/tmp1qen5wtt/graph_def.pb --framework TENSORFLOW --pipeline compile SaveTemps --output /tmp/tmp1qen5wtt/graph_def.neff --io-config '{"inputs": {"0:0": [[1, 5, 3, 384, 384], "float32"]}, "outputs": ["Reshape_2:0"]}' --verbose 35
Traceback (most recent call last):
File "/home/ubuntu/anaconda3/envs/aws_neuron_pytorch_p36/lib/python3.6/site-packages/torch_neuron/convert.py", line 391, in op_converter
item, inputs, compiler_workdir=sg_workdir, **kwargs)
File "/home/ubuntu/anaconda3/envs/aws_neuron_pytorch_p36/lib/python3.6/site-packages/torch_neuron/decorators.py", line 194, in trace
'neuron-cc failed with the following command line call:\n{}'.format(command))
subprocess.SubprocessError: neuron-cc failed with the following command line call:
/home/ubuntu/anaconda3/envs/aws_neuron_pytorch_p36/bin/neuron-cc compile /tmp/tmp1qen5wtt/graph_def.pb --framework TENSORFLOW --pipeline compile SaveTemps --output /tmp/tmp1qen5wtt/graph_def.neff --io-config '{"inputs": {"0:0": [[1, 5, 3, 384, 384], "float32"]}, "outputs": ["Reshape_2:0"]}' --verbose 35
INFO:Neuron:Number of arithmetic operators (post-compilation) before = 306, compiled = 0, percent compiled = 0.0%
INFO:Neuron:The neuron partitioner created 1 sub-graphs
INFO:Neuron:Neuron successfully compiled 0 sub-graphs, Total fused subgraphs = 1, Percent of model sub-graphs successfully compiled = 0.0%
INFO:Neuron:Compiled these operators (and operator counts) to Neuron:
INFO:Neuron:Not compiled operators (and operator counts) to Neuron:
INFO:Neuron: => aten::Int: 13 [supported]
INFO:Neuron: => aten::_convolution: 85 [supported]
INFO:Neuron: => aten::adaptive_avg_pool2d: 17 [supported]
INFO:Neuron: => aten::adaptive_max_pool2d: 1 [not supported]
INFO:Neuron: => aten::add: 16 [supported]
INFO:Neuron: => aten::addmm: 2 [supported]
INFO:Neuron: => aten::batch_norm: 53 [supported]
INFO:Neuron: => aten::cat: 1 [supported]
INFO:Neuron: => aten::contiguous: 1 [supported]
INFO:Neuron: => aten::max_pool2d: 1 [supported]
INFO:Neuron: => aten::mul: 18 [supported]
INFO:Neuron: => aten::permute: 1 [supported]
INFO:Neuron: => aten::relu: 66 [supported]
INFO:Neuron: => aten::sigmoid: 16 [supported]
INFO:Neuron: => aten::size: 9 [supported]
INFO:Neuron: => aten::t: 2 [supported]
INFO:Neuron: => aten::view: 4 [supported]
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment