-
-
Save ProGamerGov/9e5b367a90cd4be9cbd1ed023dafbb81 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
[libprotobuf WARNING google/protobuf/io/coded_stream.cc:537] Reading dangerously large protocol message. If the message turns out to be larger than 1073741824 bytes, parsing will be halted for security reasons. To increase the limit (or to disable these warnings), see CodedInputStream::SetTotalBytesLimit() in google/protobuf/io/coded_stream.h. | |
[libprotobuf WARNING google/protobuf/io/coded_stream.cc:78] The total number of bytes read was 538683157 | |
Successfully loaded models/VGG16_SOD_finetune.caffemodel | |
conv1_1: 64 3 3 3 | |
conv1_2: 64 64 3 3 | |
conv2_1: 128 64 3 3 | |
conv2_2: 128 128 3 3 | |
conv3_1: 256 128 3 3 | |
conv3_2: 256 256 3 3 | |
conv3_3: 256 256 3 3 | |
conv4_1: 512 256 3 3 | |
conv4_2: 512 512 3 3 | |
conv4_3: 512 512 3 3 | |
conv5_1: 512 512 3 3 | |
conv5_2: 512 512 3 3 | |
conv5_3: 512 512 3 3 | |
fc6: 1 1 25088 4096 | |
fc7: 1 1 4096 4096 | |
fc8-SOD100: 1 1 4096 100 | |
Setting up style layer 2 : relu1_1 | |
Setting up style layer 7 : relu2_1 | |
Setting up style layer 12 : relu3_1 | |
Setting up style layer 19 : relu4_1 | |
Setting up content layer 21 : relu4_2 | |
Setting up style layer 26 : relu5_1 | |
Capturing content targets | |
nn.Sequential { | |
[input -> (1) -> (2) -> (3) -> (4) -> (5) -> (6) -> (7) -> (8) -> output] | |
(1): nn.GPU(1) @ nn.Sequential { | |
[input -> (1) -> (2) -> (3) -> output] | |
(1): cudnn.SpatialConvolution(3 -> 64, 3x3, 1,1, 1,1) | |
(2): cudnn.ReLU | |
(3): nn.StyleLoss | |
} | |
(2): nn.GPU(2) @ nn.Sequential { | |
[input -> (1) -> (2) -> (3) -> output] | |
(1): cudnn.SpatialConvolution(64 -> 64, 3x3, 1,1, 1,1) | |
(2): cudnn.ReLU | |
(3): cudnn.SpatialMaxPooling(2x2, 2,2) | |
} | |
(3): nn.GPU(3) @ nn.Sequential { | |
[input -> (1) -> (2) -> (3) -> (4) -> (5) -> (6) -> output] | |
(1): cudnn.SpatialConvolution(64 -> 128, 3x3, 1,1, 1,1) | |
(2): cudnn.ReLU | |
(3): nn.StyleLoss | |
(4): cudnn.SpatialConvolution(128 -> 128, 3x3, 1,1, 1,1) | |
(5): cudnn.ReLU | |
(6): cudnn.SpatialMaxPooling(2x2, 2,2) | |
} | |
(4): nn.GPU(4) @ nn.Sequential { | |
[input -> (1) -> (2) -> (3) -> output] | |
(1): cudnn.SpatialConvolution(128 -> 256, 3x3, 1,1, 1,1) | |
(2): cudnn.ReLU | |
(3): nn.StyleLoss | |
} | |
(5): nn.GPU(5) @ nn.Sequential { | |
[input -> (1) -> (2) -> (3) -> (4) -> (5) -> output] | |
(1): cudnn.SpatialConvolution(256 -> 256, 3x3, 1,1, 1,1) | |
(2): cudnn.ReLU | |
(3): cudnn.SpatialConvolution(256 -> 256, 3x3, 1,1, 1,1) | |
(4): cudnn.ReLU | |
(5): cudnn.SpatialMaxPooling(2x2, 2,2) | |
} | |
(6): nn.GPU(6) @ nn.Sequential { | |
[input -> (1) -> (2) -> (3) -> (4) -> (5) -> (6) -> output] | |
(1): cudnn.SpatialConvolution(256 -> 512, 3x3, 1,1, 1,1) | |
(2): cudnn.ReLU | |
(3): nn.StyleLoss | |
(4): cudnn.SpatialConvolution(512 -> 512, 3x3, 1,1, 1,1) | |
(5): cudnn.ReLU | |
(6): nn.ContentLoss | |
} | |
(7): nn.GPU(7) @ nn.Sequential { | |
[input -> (1) -> (2) -> (3) -> (4) -> (5) -> output] | |
(1): cudnn.SpatialConvolution(512 -> 512, 3x3, 1,1, 1,1) | |
(2): cudnn.ReLU | |
(3): cudnn.SpatialMaxPooling(2x2, 2,2) | |
(4): cudnn.SpatialConvolution(512 -> 512, 3x3, 1,1, 1,1) | |
(5): cudnn.ReLU | |
} | |
(8): nn.GPU(8) @ nn.Sequential { | |
[input -> (1) -> output] | |
(1): nn.StyleLoss | |
} | |
} | |
cudnnFindConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 5] Workspace: 0.000103M (current ws size 0.000977M, max: 7207M free: 7587M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,3,3328,3089 -filtA64,3,3,3 1,64,3328,3089 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 4] Workspace: 0.250000M (current ws size 0.000977M, max: 5838M free: 6146M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,64,3328,3089 -filtA64,64,3,3 1,64,3328,3089 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 5] Workspace: 0.500000M (current ws size 0.000977M, max: 8816M free: 9281M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,64,1664,1545 -filtA128,64,3,3 1,128,1664,1545 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 4] Workspace: 1.000000M (current ws size 0.500000M, max: 8816M free: 8006M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,128,1664,1545 -filtA128,128,3,3 1,128,1664,1545 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 5] Workspace: 2.000000M (current ws size 0.000977M, max: 9710M free: 10220M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,128,832,773 -filtA256,128,3,3 1,256,832,773 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 5] Workspace: 4.000000M (current ws size 0.000977M, max: 9405M free: 9897M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,832,773 -filtA256,256,3,3 1,256,832,773 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 5] Workspace: 4.000000M (current ws size 4.000000M, max: 9405M free: 9269M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,832,773 -filtA256,256,3,3 1,256,832,773 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 5] Workspace: 8.000000M (current ws size 0.000977M, max: 10133M free: 10659M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,416,387 -filtA512,256,3,3 1,512,416,387 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 5] Workspace: 16.000000M (current ws size 8.000000M, max: 10133M free: 10317M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,416,387 -filtA512,512,3,3 1,512,416,387 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 5] Workspace: 16.000000M (current ws size 0.000977M, max: 9975M free: 10485M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,416,387 -filtA512,512,3,3 1,512,416,387 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 6] Workspace: 16.000000M (current ws size 16.000000M, max: 9975M free: 10327M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,208,194 -filtA512,512,3,3 1,512,208,194 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
Capturing style target 1 | |
cudnnFindConvolutionForwardAlgorithm: IMPLICIT_GEMM(0)[1 of 5] Workspace: 0.000000M (current ws size 0.000977M, max: 7207M free: 7470M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,3,1011,1664 -filtA64,3,3,3 1,64,1011,1664 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 5] Workspace: 0.250000M (current ws size 0.250000M, max: 5838M free: 5518M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,64,1011,1664 -filtA64,64,3,3 1,64,1011,1664 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 5] Workspace: 0.500000M (current ws size 1.000000M, max: 8816M free: 7692M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,64,506,832 -filtA128,64,3,3 1,128,506,832 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 5] Workspace: 1.000000M (current ws size 1.000000M, max: 8816M free: 7692M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,128,506,832 -filtA128,128,3,3 1,128,506,832 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 6] Workspace: 2.000000M (current ws size 2.000000M, max: 9710M free: 10200M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,128,253,416 -filtA256,128,3,3 1,256,253,416 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 6] Workspace: 4.000000M (current ws size 4.000000M, max: 9405M free: 9111M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,253,416 -filtA256,256,3,3 1,256,253,416 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 6] Workspace: 4.000000M (current ws size 4.000000M, max: 9405M free: 9111M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,253,416 -filtA256,256,3,3 1,256,253,416 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 6] Workspace: 8.000000M (current ws size 16.000000M, max: 10133M free: 10002M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,127,208 -filtA512,256,3,3 1,512,127,208 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 6] Workspace: 16.000000M (current ws size 16.000000M, max: 10133M free: 10001M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,127,208 -filtA512,512,3,3 1,512,127,208 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 6] Workspace: 16.000000M (current ws size 16.000000M, max: 9975M free: 10327M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,127,208 -filtA512,512,3,3 1,512,127,208 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 6] Workspace: 16.000000M (current ws size 16.000000M, max: 9975M free: 10327M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,64,104 -filtA512,512,3,3 1,512,64,104 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 5] Workspace: 0.000103M (current ws size 0.000977M, max: 7207M free: 8303M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,3,3328,3089 -filtA64,3,3,3 1,64,3328,3089 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 4] Workspace: 0.250000M (current ws size 0.250000M, max: 5838M free: 5518M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,64,3328,3089 -filtA64,64,3,3 1,64,3328,3089 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 5] Workspace: 0.500000M (current ws size 1.000000M, max: 8816M free: 7692M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,64,1664,1545 -filtA128,64,3,3 1,128,1664,1545 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 4] Workspace: 1.000000M (current ws size 1.000000M, max: 8816M free: 7692M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,128,1664,1545 -filtA128,128,3,3 1,128,1664,1545 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 5] Workspace: 2.000000M (current ws size 2.000000M, max: 9710M free: 10200M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,128,832,773 -filtA256,128,3,3 1,256,832,773 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 5] Workspace: 4.000000M (current ws size 4.000000M, max: 9405M free: 9111M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,832,773 -filtA256,256,3,3 1,256,832,773 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 5] Workspace: 4.000000M (current ws size 4.000000M, max: 9405M free: 9111M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,832,773 -filtA256,256,3,3 1,256,832,773 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 5] Workspace: 8.000000M (current ws size 16.000000M, max: 10133M free: 10001M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,416,387 -filtA512,256,3,3 1,512,416,387 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 5] Workspace: 16.000000M (current ws size 16.000000M, max: 10133M free: 10001M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,416,387 -filtA512,512,3,3 1,512,416,387 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 5] Workspace: 16.000000M (current ws size 16.000000M, max: 9975M free: 10327M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,416,387 -filtA512,512,3,3 1,512,416,387 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 6] Workspace: 16.000000M (current ws size 16.000000M, max: 9975M free: 10327M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,208,194 -filtA512,512,3,3 1,512,208,194 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
Running optimization with ADAM | |
cudnnFindConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 5] Workspace: 0.000103M (current ws size 0.000977M, max: 7207M free: 8225M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,3,3328,3089 -filtA64,3,3,3 1,64,3328,3089 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 4] Workspace: 0.250000M (current ws size 0.250000M, max: 5838M free: 5518M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,64,3328,3089 -filtA64,64,3,3 1,64,3328,3089 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 5] Workspace: 0.500000M (current ws size 1.000000M, max: 8816M free: 7692M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,64,1664,1545 -filtA128,64,3,3 1,128,1664,1545 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 4] Workspace: 1.000000M (current ws size 1.000000M, max: 8816M free: 7692M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,128,1664,1545 -filtA128,128,3,3 1,128,1664,1545 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 5] Workspace: 2.000000M (current ws size 2.000000M, max: 9710M free: 10200M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,128,832,773 -filtA256,128,3,3 1,256,832,773 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 5] Workspace: 4.000000M (current ws size 4.000000M, max: 9405M free: 9111M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,832,773 -filtA256,256,3,3 1,256,832,773 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 5] Workspace: 4.000000M (current ws size 4.000000M, max: 9405M free: 9111M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,832,773 -filtA256,256,3,3 1,256,832,773 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 5] Workspace: 8.000000M (current ws size 16.000000M, max: 10133M free: 10001M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,416,387 -filtA512,256,3,3 1,512,416,387 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 5] Workspace: 16.000000M (current ws size 16.000000M, max: 10133M free: 10001M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,416,387 -filtA512,512,3,3 1,512,416,387 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 5] Workspace: 16.000000M (current ws size 16.000000M, max: 9975M free: 10327M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,416,387 -filtA512,512,3,3 1,512,416,387 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnFindConvolutionForwardAlgorithm: WINOGRAD(6)[1 of 6] Workspace: 16.000000M (current ws size 16.000000M, max: 9975M free: 10327M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,208,194 -filtA512,512,3,3 1,512,208,194 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnFindConvolutionBackwardDataAlgorithm: WINOGRAD(4)[1 of 5] Workspace: 16.000000M (current ws size 16.000000M, max: 9975M free: 10170M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,208,194 -filtA512,512,3,3 1,512,208,194 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionBackwardDataAlgorithm: WINOGRAD(4)[1 of 4] Workspace: 16.000000M (current ws size 16.000000M, max: 9975M free: 9541M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,416,387 -filtA512,512,3,3 1,512,416,387 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionBackwardDataAlgorithm: WINOGRAD(4)[1 of 4] Workspace: 16.000000M (current ws size 16.000000M, max: 10133M free: 9058M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,416,387 -filtA512,512,3,3 1,512,416,387 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionBackwardDataAlgorithm: WINOGRAD(4)[1 of 4] Workspace: 8.000000M (current ws size 16.000000M, max: 10133M free: 8585M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,416,387 -filtA512,256,3,3 1,512,416,387 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionBackwardDataAlgorithm: WINOGRAD(4)[1 of 4] Workspace: 4.000000M (current ws size 4.000000M, max: 9405M free: 7698M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,832,773 -filtA256,256,3,3 1,256,832,773 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionBackwardDataAlgorithm: WINOGRAD(4)[1 of 4] Workspace: 4.000000M (current ws size 4.000000M, max: 9405M free: 7070M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,832,773 -filtA256,256,3,3 1,256,832,773 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnFindConvolutionBackwardDataAlgorithm: WINOGRAD(4)[1 of 4] Workspace: 2.000000M (current ws size 2.000000M, max: 9710M free: 8629M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,128,832,773 -filtA256,128,3,3 1,256,832,773 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionBackwardDataAlgorithm: WINOGRAD(4)[1 of 4] Workspace: 1.000000M (current ws size 1.000000M, max: 8816M free: 4867M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,128,1664,1545 -filtA128,128,3,3 1,128,1664,1545 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnFindConvolutionBackwardDataAlgorithm: WINOGRAD(4)[1 of 4] Workspace: 0.500000M (current ws size 1.000000M, max: 8816M free: 2983M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,64,1664,1545 -filtA128,64,3,3 1,128,1664,1545 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
THCudaCheck FAIL file=/tmp/luarocks_cutorch-scm-1-6290/cutorch/lib/THC/generic/THCStorage.cu line=66 error=2 : out of memory | |
/home/ubuntu/torch/install/bin/luajit: /home/ubuntu/torch/install/share/lua/5.1/nn/Container.lua:67: | |
In 2 module of nn.Sequential: | |
In 1 module of nn.Sequential: | |
...torch/install/share/lua/5.1/cudnn/SpatialConvolution.lua:203: cuda runtime error (2) : out of memory at /tmp/luarocks_cutorch-scm-1-6290/cutorch/lib/THC/generic/THCStorage.cu:66 | |
stack traceback: | |
[C]: in function 'resizeAs' | |
...torch/install/share/lua/5.1/cudnn/SpatialConvolution.lua:203: in function <...torch/install/share/lua/5.1/cudnn/SpatialConvolution.lua:201> | |
[C]: in function 'xpcall' | |
/home/ubuntu/torch/install/share/lua/5.1/nn/Container.lua:63: in function 'rethrowErrors' | |
/home/ubuntu/torch/install/share/lua/5.1/nn/Sequential.lua:58: in function </home/ubuntu/torch/install/share/lua/5.1/nn/Sequential.lua:50> | |
[C]: in function 'pcall' | |
/home/ubuntu/torch/install/share/lua/5.1/cutorch/init.lua:32: in function 'withDevice' | |
/home/ubuntu/torch/install/share/lua/5.1/nn/GPU.lua:112: in function </home/ubuntu/torch/install/share/lua/5.1/nn/GPU.lua:108> | |
[C]: in function 'xpcall' | |
/home/ubuntu/torch/install/share/lua/5.1/nn/Container.lua:63: in function 'rethrowErrors' | |
/home/ubuntu/torch/install/share/lua/5.1/nn/Sequential.lua:55: in function 'updateGradInput' | |
neural_style.lua:284: in function 'opfunc' | |
/home/ubuntu/torch/install/share/lua/5.1/optim/adam.lua:37: in function 'adam' | |
neural_style.lua:307: in function 'main' | |
neural_style.lua:602: in main chunk | |
[C]: in function 'dofile' | |
...untu/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk | |
[C]: at 0x00405d50 | |
WARNING: If you see a stack trace below, it doesn't point to the place where this error occurred. Please use only the one above. | |
stack traceback: | |
[C]: in function 'error' | |
/home/ubuntu/torch/install/share/lua/5.1/nn/Container.lua:67: in function 'rethrowErrors' | |
/home/ubuntu/torch/install/share/lua/5.1/nn/Sequential.lua:55: in function 'updateGradInput' | |
neural_style.lua:284: in function 'opfunc' | |
/home/ubuntu/torch/install/share/lua/5.1/optim/adam.lua:37: in function 'adam' | |
neural_style.lua:307: in function 'main' | |
neural_style.lua:602: in main chunk | |
[C]: in function 'dofile' | |
...untu/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk | |
[C]: at 0x00405d50 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
[libprotobuf WARNING google/protobuf/io/coded_stream.cc:537] Reading dangerously large protocol message. If the message turns out to be larger than 1073741824 bytes, parsing will be halted for security reasons. To increase the limit (or to disable these warnings), see CodedInputStream::SetTotalBytesLimit() in google/protobuf/io/coded_stream.h. | |
[libprotobuf WARNING google/protobuf/io/coded_stream.cc:78] The total number of bytes read was 538683157 | |
Successfully loaded models/VGG16_SOD_finetune.caffemodel | |
conv1_1: 64 3 3 3 | |
conv1_2: 64 64 3 3 | |
conv2_1: 128 64 3 3 | |
conv2_2: 128 128 3 3 | |
conv3_1: 256 128 3 3 | |
conv3_2: 256 256 3 3 | |
conv3_3: 256 256 3 3 | |
conv4_1: 512 256 3 3 | |
conv4_2: 512 512 3 3 | |
conv4_3: 512 512 3 3 | |
conv5_1: 512 512 3 3 | |
conv5_2: 512 512 3 3 | |
conv5_3: 512 512 3 3 | |
fc6: 1 1 25088 4096 | |
fc7: 1 1 4096 4096 | |
fc8-SOD100: 1 1 4096 100 | |
Setting up style layer 2 : relu1_1 | |
Setting up style layer 7 : relu2_1 | |
Setting up style layer 12 : relu3_1 | |
Setting up style layer 19 : relu4_1 | |
Setting up content layer 21 : relu4_2 | |
Setting up style layer 26 : relu5_1 | |
Capturing content targets | |
nn.Sequential { | |
[input -> (1) -> (2) -> (3) -> (4) -> (5) -> (6) -> (7) -> (8) -> output] | |
(1): nn.GPU(1) @ nn.Sequential { | |
[input -> (1) -> (2) -> (3) -> output] | |
(1): cudnn.SpatialConvolution(3 -> 64, 3x3, 1,1, 1,1) | |
(2): cudnn.ReLU | |
(3): nn.StyleLoss | |
} | |
(2): nn.GPU(2) @ nn.Sequential { | |
[input -> (1) -> (2) -> (3) -> output] | |
(1): cudnn.SpatialConvolution(64 -> 64, 3x3, 1,1, 1,1) | |
(2): cudnn.ReLU | |
(3): cudnn.SpatialMaxPooling(2x2, 2,2) | |
} | |
(3): nn.GPU(3) @ nn.Sequential { | |
[input -> (1) -> (2) -> (3) -> (4) -> (5) -> (6) -> output] | |
(1): cudnn.SpatialConvolution(64 -> 128, 3x3, 1,1, 1,1) | |
(2): cudnn.ReLU | |
(3): nn.StyleLoss | |
(4): cudnn.SpatialConvolution(128 -> 128, 3x3, 1,1, 1,1) | |
(5): cudnn.ReLU | |
(6): cudnn.SpatialMaxPooling(2x2, 2,2) | |
} | |
(4): nn.GPU(4) @ nn.Sequential { | |
[input -> (1) -> (2) -> (3) -> output] | |
(1): cudnn.SpatialConvolution(128 -> 256, 3x3, 1,1, 1,1) | |
(2): cudnn.ReLU | |
(3): nn.StyleLoss | |
} | |
(5): nn.GPU(5) @ nn.Sequential { | |
[input -> (1) -> (2) -> (3) -> (4) -> (5) -> output] | |
(1): cudnn.SpatialConvolution(256 -> 256, 3x3, 1,1, 1,1) | |
(2): cudnn.ReLU | |
(3): cudnn.SpatialConvolution(256 -> 256, 3x3, 1,1, 1,1) | |
(4): cudnn.ReLU | |
(5): cudnn.SpatialMaxPooling(2x2, 2,2) | |
} | |
(6): nn.GPU(6) @ nn.Sequential { | |
[input -> (1) -> (2) -> (3) -> (4) -> (5) -> (6) -> output] | |
(1): cudnn.SpatialConvolution(256 -> 512, 3x3, 1,1, 1,1) | |
(2): cudnn.ReLU | |
(3): nn.StyleLoss | |
(4): cudnn.SpatialConvolution(512 -> 512, 3x3, 1,1, 1,1) | |
(5): cudnn.ReLU | |
(6): nn.ContentLoss | |
} | |
(7): nn.GPU(7) @ nn.Sequential { | |
[input -> (1) -> (2) -> (3) -> (4) -> (5) -> output] | |
(1): cudnn.SpatialConvolution(512 -> 512, 3x3, 1,1, 1,1) | |
(2): cudnn.ReLU | |
(3): cudnn.SpatialMaxPooling(2x2, 2,2) | |
(4): cudnn.SpatialConvolution(512 -> 512, 3x3, 1,1, 1,1) | |
(5): cudnn.ReLU | |
} | |
(8): nn.GPU(8) @ nn.Sequential { | |
[input -> (1) -> output] | |
(1): nn.StyleLoss | |
} | |
} | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_GEMM(0)[1 of 1] Workspace: 0.000000M (current ws size 0.000977M, max: 7207M free: 7587M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,3,3328,3089 -filtA64,3,3,3 1,64,3328,3089 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_GEMM(0)[1 of 1] Workspace: 0.000000M (current ws size 0.000977M, max: 5838M free: 6146M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,64,3328,3089 -filtA64,64,3,3 1,64,3328,3089 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.002197M (current ws size 0.000977M, max: 8816M free: 9281M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,64,1664,1545 -filtA128,64,3,3 1,128,1664,1545 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.004395M (current ws size 0.002197M, max: 8816M free: 8007M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,128,1664,1545 -filtA128,128,3,3 1,128,1664,1545 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.004395M (current ws size 0.000977M, max: 9710M free: 10222M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,128,832,773 -filtA256,128,3,3 1,256,832,773 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.008789M (current ws size 0.000977M, max: 9405M free: 9901M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,832,773 -filtA256,256,3,3 1,256,832,773 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.008789M (current ws size 0.008789M, max: 9405M free: 9273M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,832,773 -filtA256,256,3,3 1,256,832,773 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.008789M (current ws size 0.000977M, max: 10133M free: 10667M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,416,387 -filtA512,256,3,3 1,512,416,387 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.017578M (current ws size 0.008789M, max: 10133M free: 10333M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,416,387 -filtA512,512,3,3 1,512,416,387 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.017578M (current ws size 0.000977M, max: 9975M free: 10501M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,416,387 -filtA512,512,3,3 1,512,416,387 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.017578M (current ws size 0.017578M, max: 9975M free: 10343M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,208,194 -filtA512,512,3,3 1,512,208,194 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
Capturing style target 1 | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_GEMM(0)[1 of 1] Workspace: 0.000000M (current ws size 0.000977M, max: 7207M free: 7470M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,3,1011,1664 -filtA64,3,3,3 1,64,1011,1664 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_GEMM(0)[1 of 1] Workspace: 0.000000M (current ws size 0.000977M, max: 5838M free: 5518M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,64,1011,1664 -filtA64,64,3,3 1,64,1011,1664 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.002197M (current ws size 0.004395M, max: 8816M free: 7693M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,64,506,832 -filtA128,64,3,3 1,128,506,832 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.004395M (current ws size 0.004395M, max: 8816M free: 7693M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,128,506,832 -filtA128,128,3,3 1,128,506,832 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.004395M (current ws size 0.004395M, max: 9710M free: 10202M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,128,253,416 -filtA256,128,3,3 1,256,253,416 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.008789M (current ws size 0.008789M, max: 9405M free: 9115M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,253,416 -filtA256,256,3,3 1,256,253,416 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.008789M (current ws size 0.008789M, max: 9405M free: 9115M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,253,416 -filtA256,256,3,3 1,256,253,416 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.008789M (current ws size 0.017578M, max: 10133M free: 10018M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,127,208 -filtA512,256,3,3 1,512,127,208 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.017578M (current ws size 0.017578M, max: 10133M free: 10017M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,127,208 -filtA512,512,3,3 1,512,127,208 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.017578M (current ws size 0.017578M, max: 9975M free: 10343M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,127,208 -filtA512,512,3,3 1,512,127,208 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.017578M (current ws size 0.017578M, max: 9975M free: 10343M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,64,104 -filtA512,512,3,3 1,512,64,104 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_GEMM(0)[1 of 1] Workspace: 0.000000M (current ws size 0.000977M, max: 7207M free: 8303M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,3,3328,3089 -filtA64,3,3,3 1,64,3328,3089 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_GEMM(0)[1 of 1] Workspace: 0.000000M (current ws size 0.000977M, max: 5838M free: 5518M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,64,3328,3089 -filtA64,64,3,3 1,64,3328,3089 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.002197M (current ws size 0.004395M, max: 8816M free: 7693M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,64,1664,1545 -filtA128,64,3,3 1,128,1664,1545 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.004395M (current ws size 0.004395M, max: 8816M free: 7693M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,128,1664,1545 -filtA128,128,3,3 1,128,1664,1545 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.004395M (current ws size 0.004395M, max: 9710M free: 10202M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,128,832,773 -filtA256,128,3,3 1,256,832,773 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.008789M (current ws size 0.008789M, max: 9405M free: 9115M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,832,773 -filtA256,256,3,3 1,256,832,773 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.008789M (current ws size 0.008789M, max: 9405M free: 9115M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,832,773 -filtA256,256,3,3 1,256,832,773 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.008789M (current ws size 0.017578M, max: 10133M free: 10017M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,416,387 -filtA512,256,3,3 1,512,416,387 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.017578M (current ws size 0.017578M, max: 10133M free: 10017M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,416,387 -filtA512,512,3,3 1,512,416,387 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.017578M (current ws size 0.017578M, max: 9975M free: 10343M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,416,387 -filtA512,512,3,3 1,512,416,387 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.017578M (current ws size 0.017578M, max: 9975M free: 10343M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,208,194 -filtA512,512,3,3 1,512,208,194 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
Running optimization with ADAM | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_GEMM(0)[1 of 1] Workspace: 0.000000M (current ws size 0.000977M, max: 7207M free: 8225M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,3,3328,3089 -filtA64,3,3,3 1,64,3328,3089 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_GEMM(0)[1 of 1] Workspace: 0.000000M (current ws size 0.000977M, max: 5838M free: 5518M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,64,3328,3089 -filtA64,64,3,3 1,64,3328,3089 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.002197M (current ws size 0.004395M, max: 8816M free: 7693M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,64,1664,1545 -filtA128,64,3,3 1,128,1664,1545 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.004395M (current ws size 0.004395M, max: 8816M free: 7693M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,128,1664,1545 -filtA128,128,3,3 1,128,1664,1545 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.004395M (current ws size 0.004395M, max: 9710M free: 10202M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,128,832,773 -filtA256,128,3,3 1,256,832,773 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.008789M (current ws size 0.008789M, max: 9405M free: 9115M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,832,773 -filtA256,256,3,3 1,256,832,773 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.008789M (current ws size 0.008789M, max: 9405M free: 9115M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,832,773 -filtA256,256,3,3 1,256,832,773 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.008789M (current ws size 0.017578M, max: 10133M free: 10017M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,416,387 -filtA512,256,3,3 1,512,416,387 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.017578M (current ws size 0.017578M, max: 10133M free: 10017M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,416,387 -filtA512,512,3,3 1,512,416,387 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.017578M (current ws size 0.017578M, max: 9975M free: 10343M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,416,387 -filtA512,512,3,3 1,512,416,387 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnGetConvolutionForwardAlgorithm: IMPLICIT_PRECOMP_GEMM(1)[1 of 1] Workspace: 0.017578M (current ws size 0.017578M, max: 9975M free: 10343M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,208,194 -filtA512,512,3,3 1,512,208,194 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnGetConvolutionBackwardDataAlgorithm: ALGO_1(1)[1 of 1] Workspace: 0.000000M (current ws size 0.017578M, max: 9975M free: 10186M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,208,194 -filtA512,512,3,3 1,512,208,194 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionBackwardDataAlgorithm: ALGO_1(1)[1 of 1] Workspace: 0.000000M (current ws size 0.017578M, max: 9975M free: 9557M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,416,387 -filtA512,512,3,3 1,512,416,387 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionBackwardDataAlgorithm: ALGO_1(1)[1 of 1] Workspace: 0.000000M (current ws size 0.017578M, max: 10133M free: 9074M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,512,416,387 -filtA512,512,3,3 1,512,416,387 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionBackwardDataAlgorithm: ALGO_1(1)[1 of 1] Workspace: 0.000000M (current ws size 0.017578M, max: 10133M free: 8601M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,416,387 -filtA512,256,3,3 1,512,416,387 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionBackwardDataAlgorithm: ALGO_1(1)[1 of 1] Workspace: 0.000000M (current ws size 0.008789M, max: 9405M free: 7702M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,832,773 -filtA256,256,3,3 1,256,832,773 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionBackwardDataAlgorithm: ALGO_1(1)[1 of 1] Workspace: 0.000000M (current ws size 0.008789M, max: 9405M free: 7074M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,256,832,773 -filtA256,256,3,3 1,256,832,773 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT[found in cache] | |
cudnnGetConvolutionBackwardDataAlgorithm: ALGO_1(1)[1 of 1] Workspace: 0.000000M (current ws size 0.004395M, max: 9710M free: 8631M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,128,832,773 -filtA256,128,3,3 1,256,832,773 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionBackwardDataAlgorithm: ALGO_1(1)[1 of 1] Workspace: 0.000000M (current ws size 0.004395M, max: 8816M free: 4868M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,128,1664,1545 -filtA128,128,3,3 1,128,1664,1545 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
cudnnGetConvolutionBackwardDataAlgorithm: ALGO_1(1)[1 of 1] Workspace: 0.000000M (current ws size 0.004395M, max: 8816M free: 2984M) convDesc=[mode : CUDNN_CROSS_CORRELATION datatype : CUDNN_DATA_FLOAT] hash=-dimA1,64,1664,1545 -filtA128,64,3,3 1,128,1664,1545 -padA1,1 -convStrideA1,1 CUDNN_DATA_FLOAT | |
THCudaCheck FAIL file=/tmp/luarocks_cutorch-scm-1-6290/cutorch/lib/THC/generic/THCStorage.cu line=66 error=2 : out of memory | |
/home/ubuntu/torch/install/bin/luajit: /home/ubuntu/torch/install/share/lua/5.1/nn/Container.lua:67: | |
In 2 module of nn.Sequential: | |
In 1 module of nn.Sequential: | |
...torch/install/share/lua/5.1/cudnn/SpatialConvolution.lua:203: cuda runtime error (2) : out of memory at /tmp/luarocks_cutorch-scm-1-6290/cutorch/lib/THC/generic/THCStorage.cu:66 | |
stack traceback: | |
[C]: in function 'resizeAs' | |
...torch/install/share/lua/5.1/cudnn/SpatialConvolution.lua:203: in function <...torch/install/share/lua/5.1/cudnn/SpatialConvolution.lua:201> | |
[C]: in function 'xpcall' | |
/home/ubuntu/torch/install/share/lua/5.1/nn/Container.lua:63: in function 'rethrowErrors' | |
/home/ubuntu/torch/install/share/lua/5.1/nn/Sequential.lua:58: in function </home/ubuntu/torch/install/share/lua/5.1/nn/Sequential.lua:50> | |
[C]: in function 'pcall' | |
/home/ubuntu/torch/install/share/lua/5.1/cutorch/init.lua:32: in function 'withDevice' | |
/home/ubuntu/torch/install/share/lua/5.1/nn/GPU.lua:112: in function </home/ubuntu/torch/install/share/lua/5.1/nn/GPU.lua:108> | |
[C]: in function 'xpcall' | |
/home/ubuntu/torch/install/share/lua/5.1/nn/Container.lua:63: in function 'rethrowErrors' | |
/home/ubuntu/torch/install/share/lua/5.1/nn/Sequential.lua:55: in function 'updateGradInput' | |
neural_style.lua:284: in function 'opfunc' | |
/home/ubuntu/torch/install/share/lua/5.1/optim/adam.lua:37: in function 'adam' | |
neural_style.lua:307: in function 'main' | |
neural_style.lua:602: in main chunk | |
[C]: in function 'dofile' | |
...untu/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk | |
[C]: at 0x00405d50 | |
WARNING: If you see a stack trace below, it doesn't point to the place where this error occurred. Please use only the one above. | |
stack traceback: | |
[C]: in function 'error' | |
/home/ubuntu/torch/install/share/lua/5.1/nn/Container.lua:67: in function 'rethrowErrors' | |
/home/ubuntu/torch/install/share/lua/5.1/nn/Sequential.lua:55: in function 'updateGradInput' | |
neural_style.lua:284: in function 'opfunc' | |
/home/ubuntu/torch/install/share/lua/5.1/optim/adam.lua:37: in function 'adam' | |
neural_style.lua:307: in function 'main' | |
neural_style.lua:602: in main chunk | |
[C]: in function 'dofile' | |
...untu/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk | |
[C]: at 0x00405d50 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment