I0417 00:16:09.032217 28422 caffe.cpp:212] Use GPU with device ID 0
E0417 00:16:09.239701 28422 upgrade_proto.cpp:618] Attempting to upgrade input file specified using deprecated V1LayerParameter: proto_noGradInput/conv1.prototxt
I0417 00:16:09.239748 28422 upgrade_proto.cpp:626] Successfully upgraded file specified using deprecated V1LayerParameter
I0417 00:16:09.239805 28422 net.cpp:42] Initializing net from parameters: 
name: "ConvLayer_3x96x11x11"
input: "data"
input_dim: 128
input_dim: 3
input_dim: 128
input_dim: 128
state {
  phase: TRAIN
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 96
    kernel_size: 11
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
I0417 00:16:09.239831 28422 net.cpp:340] Input 0 -> data
I0417 00:16:09.239863 28422 layer_factory.hpp:74] Creating layer conv1
I0417 00:16:09.239881 28422 net.cpp:84] Creating Layer conv1
I0417 00:16:09.239886 28422 net.cpp:380] conv1 <- data
I0417 00:16:09.239892 28422 net.cpp:338] conv1 -> conv1
I0417 00:16:09.239902 28422 net.cpp:113] Setting up conv1
I0417 00:16:09.240484 28422 net.cpp:120] Top shape: 128 96 118 118 (171098112)
I0417 00:16:09.240499 28422 net.cpp:169] conv1 does not need backward computation.
I0417 00:16:09.240501 28422 net.cpp:205] This network produces output conv1
I0417 00:16:09.240506 28422 net.cpp:447] Collecting Learning Rate and Weight Decay.
I0417 00:16:09.240511 28422 net.cpp:217] Network initialization done.
I0417 00:16:09.240514 28422 net.cpp:218] Memory required for data: 684392448
I0417 00:16:09.240525 28422 caffe.cpp:224] Performing Forward
I0417 00:16:09.251447 28422 caffe.cpp:229] Initial loss: 0
I0417 00:16:09.251466 28422 caffe.cpp:230] Performing Backward
I0417 00:16:09.251471 28422 caffe.cpp:238] *** Benchmark begins ***
I0417 00:16:09.251473 28422 caffe.cpp:239] Testing for 10 iterations.
I0417 00:16:09.586505 28422 caffe.cpp:270] Iteration: 1 forward-backward time: 229.475 ms.
I0417 00:16:09.793450 28422 caffe.cpp:270] Iteration: 2 forward-backward time: 206.911 ms.
I0417 00:16:10.000334 28422 caffe.cpp:270] Iteration: 3 forward-backward time: 206.854 ms.
I0417 00:16:10.207428 28422 caffe.cpp:270] Iteration: 4 forward-backward time: 207.064 ms.
I0417 00:16:10.416401 28422 caffe.cpp:270] Iteration: 5 forward-backward time: 208.942 ms.
I0417 00:16:10.626866 28422 caffe.cpp:270] Iteration: 6 forward-backward time: 210.436 ms.
I0417 00:16:10.837538 28422 caffe.cpp:270] Iteration: 7 forward-backward time: 210.642 ms.
I0417 00:16:11.048020 28422 caffe.cpp:270] Iteration: 8 forward-backward time: 210.454 ms.
I0417 00:16:11.258597 28422 caffe.cpp:270] Iteration: 9 forward-backward time: 210.547 ms.
I0417 00:16:11.469188 28422 caffe.cpp:270] Iteration: 10 forward-backward time: 210.562 ms.
I0417 00:16:11.469203 28422 caffe.cpp:273] Average time per layer: 
I0417 00:16:11.469208 28422 caffe.cpp:276]      conv1	forward: 95.2224 ms.
I0417 00:16:11.469211 28422 caffe.cpp:279]      conv1	backward: 115.929 ms.
I0417 00:16:11.469223 28422 caffe.cpp:284] Average Forward pass: 95.2344 ms.
I0417 00:16:11.469226 28422 caffe.cpp:286] Average Backward pass: 115.94 ms.
I0417 00:16:11.469231 28422 caffe.cpp:288] Average Forward-Backward: 211.216 ms.
I0417 00:16:11.469235 28422 caffe.cpp:290] Total Time: 2112.16 ms.
I0417 00:16:11.469238 28422 caffe.cpp:291] *** Benchmark ends ***
I0417 00:16:11.584728 28425 caffe.cpp:212] Use GPU with device ID 0
E0417 00:16:11.783291 28425 upgrade_proto.cpp:618] Attempting to upgrade input file specified using deprecated V1LayerParameter: proto_noGradInput/conv2.prototxt
I0417 00:16:11.783339 28425 upgrade_proto.cpp:626] Successfully upgraded file specified using deprecated V1LayerParameter
I0417 00:16:11.783397 28425 net.cpp:42] Initializing net from parameters: 
name: "ConvLayer_64x128x9x9"
input: "data"
input_dim: 128
input_dim: 64
input_dim: 64
input_dim: 64
state {
  phase: TRAIN
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "data"
  top: "conv2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 128
    kernel_size: 9
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
I0417 00:16:11.783434 28425 net.cpp:340] Input 0 -> data
I0417 00:16:11.783462 28425 layer_factory.hpp:74] Creating layer conv2
I0417 00:16:11.783474 28425 net.cpp:84] Creating Layer conv2
I0417 00:16:11.783478 28425 net.cpp:380] conv2 <- data
I0417 00:16:11.783485 28425 net.cpp:338] conv2 -> conv2
I0417 00:16:11.783494 28425 net.cpp:113] Setting up conv2
I0417 00:16:11.787629 28425 net.cpp:120] Top shape: 128 128 56 56 (51380224)
I0417 00:16:11.787645 28425 net.cpp:169] conv2 does not need backward computation.
I0417 00:16:11.787649 28425 net.cpp:205] This network produces output conv2
I0417 00:16:11.787654 28425 net.cpp:447] Collecting Learning Rate and Weight Decay.
I0417 00:16:11.787659 28425 net.cpp:217] Network initialization done.
I0417 00:16:11.787662 28425 net.cpp:218] Memory required for data: 205520896
I0417 00:16:11.787673 28425 caffe.cpp:224] Performing Forward
I0417 00:16:11.797265 28425 caffe.cpp:229] Initial loss: 0
I0417 00:16:11.797283 28425 caffe.cpp:230] Performing Backward
I0417 00:16:11.797287 28425 caffe.cpp:238] *** Benchmark begins ***
I0417 00:16:11.797291 28425 caffe.cpp:239] Testing for 10 iterations.
I0417 00:16:12.323016 28425 caffe.cpp:270] Iteration: 1 forward-backward time: 391.336 ms.
I0417 00:16:12.713781 28425 caffe.cpp:270] Iteration: 2 forward-backward time: 390.724 ms.
I0417 00:16:13.104074 28425 caffe.cpp:270] Iteration: 3 forward-backward time: 390.256 ms.
I0417 00:16:13.493724 28425 caffe.cpp:270] Iteration: 4 forward-backward time: 389.617 ms.
I0417 00:16:13.884798 28425 caffe.cpp:270] Iteration: 5 forward-backward time: 391.038 ms.
I0417 00:16:14.275357 28425 caffe.cpp:270] Iteration: 6 forward-backward time: 390.525 ms.
I0417 00:16:14.665652 28425 caffe.cpp:270] Iteration: 7 forward-backward time: 390.263 ms.
I0417 00:16:15.058218 28425 caffe.cpp:270] Iteration: 8 forward-backward time: 392.532 ms.
I0417 00:16:15.448957 28425 caffe.cpp:270] Iteration: 9 forward-backward time: 390.705 ms.
I0417 00:16:15.841218 28425 caffe.cpp:270] Iteration: 10 forward-backward time: 392.227 ms.
I0417 00:16:15.841234 28425 caffe.cpp:273] Average time per layer: 
I0417 00:16:15.841238 28425 caffe.cpp:276]      conv2	forward: 137.628 ms.
I0417 00:16:15.841243 28425 caffe.cpp:279]      conv2	backward: 253.257 ms.
I0417 00:16:15.841253 28425 caffe.cpp:284] Average Forward pass: 137.639 ms.
I0417 00:16:15.841259 28425 caffe.cpp:286] Average Backward pass: 253.269 ms.
I0417 00:16:15.841262 28425 caffe.cpp:288] Average Forward-Backward: 390.95 ms.
I0417 00:16:15.841267 28425 caffe.cpp:290] Total Time: 3909.5 ms.
I0417 00:16:15.841271 28425 caffe.cpp:291] *** Benchmark ends ***
I0417 00:16:15.957276 28428 caffe.cpp:212] Use GPU with device ID 0
E0417 00:16:16.155486 28428 upgrade_proto.cpp:618] Attempting to upgrade input file specified using deprecated V1LayerParameter: proto_noGradInput/conv3.prototxt
I0417 00:16:16.155534 28428 upgrade_proto.cpp:626] Successfully upgraded file specified using deprecated V1LayerParameter
I0417 00:16:16.155591 28428 net.cpp:42] Initializing net from parameters: 
name: "ConvLayer_128x128x9x9"
input: "data"
input_dim: 128
input_dim: 128
input_dim: 32
input_dim: 32
state {
  phase: TRAIN
}
layer {
  name: "conv3"
  type: "Convolution"
  bottom: "data"
  top: "conv3"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 128
    kernel_size: 9
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
I0417 00:16:16.155622 28428 net.cpp:340] Input 0 -> data
I0417 00:16:16.155648 28428 layer_factory.hpp:74] Creating layer conv3
I0417 00:16:16.155663 28428 net.cpp:84] Creating Layer conv3
I0417 00:16:16.155668 28428 net.cpp:380] conv3 <- data
I0417 00:16:16.155674 28428 net.cpp:338] conv3 -> conv3
I0417 00:16:16.155683 28428 net.cpp:113] Setting up conv3
I0417 00:16:16.163719 28428 net.cpp:120] Top shape: 128 128 24 24 (9437184)
I0417 00:16:16.163739 28428 net.cpp:169] conv3 does not need backward computation.
I0417 00:16:16.163743 28428 net.cpp:205] This network produces output conv3
I0417 00:16:16.163748 28428 net.cpp:447] Collecting Learning Rate and Weight Decay.
I0417 00:16:16.163753 28428 net.cpp:217] Network initialization done.
I0417 00:16:16.163755 28428 net.cpp:218] Memory required for data: 37748736
I0417 00:16:16.163766 28428 caffe.cpp:224] Performing Forward
I0417 00:16:16.171675 28428 caffe.cpp:229] Initial loss: 0
I0417 00:16:16.171695 28428 caffe.cpp:230] Performing Backward
I0417 00:16:16.171700 28428 caffe.cpp:238] *** Benchmark begins ***
I0417 00:16:16.171702 28428 caffe.cpp:239] Testing for 10 iterations.
I0417 00:16:16.494289 28428 caffe.cpp:270] Iteration: 1 forward-backward time: 206.21 ms.
I0417 00:16:16.700170 28428 caffe.cpp:270] Iteration: 2 forward-backward time: 205.846 ms.
I0417 00:16:16.905923 28428 caffe.cpp:270] Iteration: 3 forward-backward time: 205.726 ms.
I0417 00:16:17.111634 28428 caffe.cpp:270] Iteration: 4 forward-backward time: 205.683 ms.
I0417 00:16:17.317338 28428 caffe.cpp:270] Iteration: 5 forward-backward time: 205.677 ms.
I0417 00:16:17.523074 28428 caffe.cpp:270] Iteration: 6 forward-backward time: 205.708 ms.
I0417 00:16:17.728760 28428 caffe.cpp:270] Iteration: 7 forward-backward time: 205.656 ms.
I0417 00:16:17.934566 28428 caffe.cpp:270] Iteration: 8 forward-backward time: 205.779 ms.
I0417 00:16:18.140295 28428 caffe.cpp:270] Iteration: 9 forward-backward time: 205.702 ms.
I0417 00:16:18.346161 28428 caffe.cpp:270] Iteration: 10 forward-backward time: 205.824 ms.
I0417 00:16:18.346177 28428 caffe.cpp:273] Average time per layer: 
I0417 00:16:18.346180 28428 caffe.cpp:276]      conv3	forward: 118.811 ms.
I0417 00:16:18.346184 28428 caffe.cpp:279]      conv3	backward: 86.9291 ms.
I0417 00:16:18.346195 28428 caffe.cpp:284] Average Forward pass: 118.822 ms.
I0417 00:16:18.346200 28428 caffe.cpp:286] Average Backward pass: 86.9393 ms.
I0417 00:16:18.346205 28428 caffe.cpp:288] Average Forward-Backward: 205.808 ms.
I0417 00:16:18.346210 28428 caffe.cpp:290] Total Time: 2058.08 ms.
I0417 00:16:18.346213 28428 caffe.cpp:291] *** Benchmark ends ***
I0417 00:16:18.462502 28431 caffe.cpp:212] Use GPU with device ID 0
E0417 00:16:18.660501 28431 upgrade_proto.cpp:618] Attempting to upgrade input file specified using deprecated V1LayerParameter: proto_noGradInput/conv4.prototxt
I0417 00:16:18.660543 28431 upgrade_proto.cpp:626] Successfully upgraded file specified using deprecated V1LayerParameter
I0417 00:16:18.660604 28431 net.cpp:42] Initializing net from parameters: 
name: "ConvLayer_128x128x7x7"
input: "data"
input_dim: 128
input_dim: 128
input_dim: 16
input_dim: 16
state {
  phase: TRAIN
}
layer {
  name: "conv4"
  type: "Convolution"
  bottom: "data"
  top: "conv4"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 128
    kernel_size: 7
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
I0417 00:16:18.660634 28431 net.cpp:340] Input 0 -> data
I0417 00:16:18.660660 28431 layer_factory.hpp:74] Creating layer conv4
I0417 00:16:18.660676 28431 net.cpp:84] Creating Layer conv4
I0417 00:16:18.660681 28431 net.cpp:380] conv4 <- data
I0417 00:16:18.660687 28431 net.cpp:338] conv4 -> conv4
I0417 00:16:18.660696 28431 net.cpp:113] Setting up conv4
I0417 00:16:18.665567 28431 net.cpp:120] Top shape: 128 128 10 10 (1638400)
I0417 00:16:18.665585 28431 net.cpp:169] conv4 does not need backward computation.
I0417 00:16:18.665588 28431 net.cpp:205] This network produces output conv4
I0417 00:16:18.665593 28431 net.cpp:447] Collecting Learning Rate and Weight Decay.
I0417 00:16:18.665597 28431 net.cpp:217] Network initialization done.
I0417 00:16:18.665601 28431 net.cpp:218] Memory required for data: 6553600
I0417 00:16:18.665611 28431 caffe.cpp:224] Performing Forward
I0417 00:16:18.672343 28431 caffe.cpp:229] Initial loss: 0
I0417 00:16:18.672368 28431 caffe.cpp:230] Performing Backward
I0417 00:16:18.672372 28431 caffe.cpp:238] *** Benchmark begins ***
I0417 00:16:18.672374 28431 caffe.cpp:239] Testing for 10 iterations.
I0417 00:16:18.733033 28431 caffe.cpp:270] Iteration: 1 forward-backward time: 37.4661 ms.
I0417 00:16:18.770238 28431 caffe.cpp:270] Iteration: 2 forward-backward time: 37.1763 ms.
I0417 00:16:18.807390 28431 caffe.cpp:270] Iteration: 3 forward-backward time: 37.1292 ms.
I0417 00:16:18.844597 28431 caffe.cpp:270] Iteration: 4 forward-backward time: 37.1866 ms.
I0417 00:16:18.881824 28431 caffe.cpp:270] Iteration: 5 forward-backward time: 37.207 ms.
I0417 00:16:18.918928 28431 caffe.cpp:270] Iteration: 6 forward-backward time: 37.0812 ms.
I0417 00:16:18.956117 28431 caffe.cpp:270] Iteration: 7 forward-backward time: 37.1661 ms.
I0417 00:16:18.993290 28431 caffe.cpp:270] Iteration: 8 forward-backward time: 37.1497 ms.
I0417 00:16:19.030442 28431 caffe.cpp:270] Iteration: 9 forward-backward time: 37.1302 ms.
I0417 00:16:19.067639 28431 caffe.cpp:270] Iteration: 10 forward-backward time: 37.1743 ms.
I0417 00:16:19.067652 28431 caffe.cpp:273] Average time per layer: 
I0417 00:16:19.067656 28431 caffe.cpp:276]      conv4	forward: 24.9653 ms.
I0417 00:16:19.067659 28431 caffe.cpp:279]      conv4	backward: 12.1875 ms.
I0417 00:16:19.067669 28431 caffe.cpp:284] Average Forward pass: 24.9748 ms.
I0417 00:16:19.067674 28431 caffe.cpp:286] Average Backward pass: 12.1979 ms.
I0417 00:16:19.067678 28431 caffe.cpp:288] Average Forward-Backward: 37.2101 ms.
I0417 00:16:19.067682 28431 caffe.cpp:290] Total Time: 372.101 ms.
I0417 00:16:19.067687 28431 caffe.cpp:291] *** Benchmark ends ***
I0417 00:16:19.182812 28434 caffe.cpp:212] Use GPU with device ID 0
E0417 00:16:19.381808 28434 upgrade_proto.cpp:618] Attempting to upgrade input file specified using deprecated V1LayerParameter: proto_noGradInput/conv5.prototxt
I0417 00:16:19.381850 28434 upgrade_proto.cpp:626] Successfully upgraded file specified using deprecated V1LayerParameter
I0417 00:16:19.381907 28434 net.cpp:42] Initializing net from parameters: 
name: "ConvLayer_384x384x3x3"
input: "data"
input_dim: 128
input_dim: 384
input_dim: 13
input_dim: 13
state {
  phase: TRAIN
}
layer {
  name: "conv5"
  type: "Convolution"
  bottom: "data"
  top: "conv5"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 384
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
I0417 00:16:19.381934 28434 net.cpp:340] Input 0 -> data
I0417 00:16:19.381965 28434 layer_factory.hpp:74] Creating layer conv5
I0417 00:16:19.381981 28434 net.cpp:84] Creating Layer conv5
I0417 00:16:19.381986 28434 net.cpp:380] conv5 <- data
I0417 00:16:19.381994 28434 net.cpp:338] conv5 -> conv5
I0417 00:16:19.382002 28434 net.cpp:113] Setting up conv5
I0417 00:16:19.389842 28434 net.cpp:120] Top shape: 128 384 11 11 (5947392)
I0417 00:16:19.389859 28434 net.cpp:169] conv5 does not need backward computation.
I0417 00:16:19.389863 28434 net.cpp:205] This network produces output conv5
I0417 00:16:19.389868 28434 net.cpp:447] Collecting Learning Rate and Weight Decay.
I0417 00:16:19.389873 28434 net.cpp:217] Network initialization done.
I0417 00:16:19.389875 28434 net.cpp:218] Memory required for data: 23789568
I0417 00:16:19.389886 28434 caffe.cpp:224] Performing Forward
I0417 00:16:19.396874 28434 caffe.cpp:229] Initial loss: 0
I0417 00:16:19.396894 28434 caffe.cpp:230] Performing Backward
I0417 00:16:19.396899 28434 caffe.cpp:238] *** Benchmark begins ***
I0417 00:16:19.396901 28434 caffe.cpp:239] Testing for 10 iterations.
I0417 00:16:19.465308 28434 caffe.cpp:270] Iteration: 1 forward-backward time: 42.5421 ms.
I0417 00:16:19.507385 28434 caffe.cpp:270] Iteration: 2 forward-backward time: 42.0465 ms.
I0417 00:16:19.549574 28434 caffe.cpp:270] Iteration: 3 forward-backward time: 42.1663 ms.
I0417 00:16:19.591656 28434 caffe.cpp:270] Iteration: 4 forward-backward time: 42.0607 ms.
I0417 00:16:19.633795 28434 caffe.cpp:270] Iteration: 5 forward-backward time: 42.11 ms.
I0417 00:16:19.675912 28434 caffe.cpp:270] Iteration: 6 forward-backward time: 42.0966 ms.
I0417 00:16:19.717980 28434 caffe.cpp:270] Iteration: 7 forward-backward time: 42.0465 ms.
I0417 00:16:19.760063 28434 caffe.cpp:270] Iteration: 8 forward-backward time: 42.0618 ms.
I0417 00:16:19.802140 28434 caffe.cpp:270] Iteration: 9 forward-backward time: 42.0547 ms.
I0417 00:16:19.844267 28434 caffe.cpp:270] Iteration: 10 forward-backward time: 42.1059 ms.
I0417 00:16:19.844281 28434 caffe.cpp:273] Average time per layer: 
I0417 00:16:19.844285 28434 caffe.cpp:276]      conv5	forward: 27.6744 ms.
I0417 00:16:19.844288 28434 caffe.cpp:279]      conv5	backward: 14.4205 ms.
I0417 00:16:19.844300 28434 caffe.cpp:284] Average Forward pass: 27.6845 ms.
I0417 00:16:19.844303 28434 caffe.cpp:286] Average Backward pass: 14.4304 ms.
I0417 00:16:19.844308 28434 caffe.cpp:288] Average Forward-Backward: 42.1531 ms.
I0417 00:16:19.844312 28434 caffe.cpp:290] Total Time: 421.531 ms.
I0417 00:16:19.844316 28434 caffe.cpp:291] *** Benchmark ends ***