log

--------------------------------	
inputs	 1000
    1
    5
    1
   16
   16
   16
[torch.LongStorage of size 7]

targets	 1000
[torch.LongStorage of size 1]

min target	1	
max target	8	
--------------------------------	
 1000
    1
    5
    1
   16
   16
   16
[torch.LongStorage of size 7]

 1000
[torch.LongStorage of size 1]

--------------------------------	
inputs	 1000
    1
    5
    1
   16
   16
   16
[torch.LongStorage of size 7]

targets	 1000
[torch.LongStorage of size 1]

min target	1	
max target	8	
--------------------------------	
 1000
    1
    5
    1
   16
   16
   16
[torch.LongStorage of size 7]

 1000
[torch.LongStorage of size 1]

creating fresh new model!	
loader seed: 	1	
nn.Sequential {
  [input -> (1) -> (2) -> (3) -> (4) -> (5) -> (6) -> (7) -> (8) -> output]
  (1): nn.Parallel {
    input
       `-> (1): nn.Sequential {
             [input -> (1) -> (2) -> output]
             (1): nn.Parallel {
               input
                 |`-> (1): nn.Sequential {
                 |      [input -> (1) -> (2) -> (3) -> (4) -> (5) -> (6) -> (7) -> (8) -> (9) -> (10) -> output]
                 |      (1): cudnn.VolumetricConvolution(1 -> 16, 3x3x3, 1,1,1, 1,1,1)
                 |      (2): cudnn.ReLU
                 |      (3): cudnn.VolumetricMaxPooling
                 |      (4): cudnn.VolumetricConvolution(16 -> 32, 3x3x3, 1,1,1, 1,1,1)
                 |      (5): cudnn.ReLU
                 |      (6): cudnn.VolumetricMaxPooling
                 |      (7): cudnn.VolumetricConvolution(32 -> 64, 3x3x3, 1,1,1, 1,1,1)
                 |      (8): cudnn.ReLU
                 |      (9): cudnn.VolumetricMaxPooling
                 |      (10): nn.Reshape(512)
                 |    }
                 |`-> (2): nn.Sequential {
                 |      [input -> (1) -> (2) -> (3) -> (4) -> (5) -> (6) -> (7) -> (8) -> (9) -> (10) -> output]
                 |      (1): cudnn.VolumetricConvolution(1 -> 16, 3x3x3, 1,1,1, 1,1,1)
                 |      (2): cudnn.ReLU
                 |      (3): cudnn.VolumetricMaxPooling
                 |      (4): cudnn.VolumetricConvolution(16 -> 32, 3x3x3, 1,1,1, 1,1,1)
                 |      (5): cudnn.ReLU
                 |      (6): cudnn.VolumetricMaxPooling
                 |      (7): cudnn.VolumetricConvolution(32 -> 64, 3x3x3, 1,1,1, 1,1,1)
                 |      (8): cudnn.ReLU
                 |      (9): cudnn.VolumetricMaxPooling
                 |      (10): nn.Reshape(512)
                 |    }
                 |`-> (3): nn.Sequential {
                 |      [input -> (1) -> (2) -> (3) -> (4) -> (5) -> (6) -> (7) -> (8) -> (9) -> (10) -> output]
                 |      (1): cudnn.VolumetricConvolution(1 -> 16, 3x3x3, 1,1,1, 1,1,1)
                 |      (2): cudnn.ReLU
                 |      (3): cudnn.VolumetricMaxPooling
                 |      (4): cudnn.VolumetricConvolution(16 -> 32, 3x3x3, 1,1,1, 1,1,1)
                 |      (5): cudnn.ReLU
                 |      (6): cudnn.VolumetricMaxPooling
                 |      (7): cudnn.VolumetricConvolution(32 -> 64, 3x3x3, 1,1,1, 1,1,1)
                 |      (8): cudnn.ReLU
                 |      (9): cudnn.VolumetricMaxPooling
                 |      (10): nn.Reshape(512)
                 |    }
                 |`-> (4): nn.Sequential {
                 |      [input -> (1) -> (2) -> (3) -> (4) -> (5) -> (6) -> (7) -> (8) -> (9) -> (10) -> output]
                 |      (1): cudnn.VolumetricConvolution(1 -> 16, 3x3x3, 1,1,1, 1,1,1)
                 |      (2): cudnn.ReLU
                 |      (3): cudnn.VolumetricMaxPooling
                 |      (4): cudnn.VolumetricConvolution(16 -> 32, 3x3x3, 1,1,1, 1,1,1)
                 |      (5): cudnn.ReLU
                 |      (6): cudnn.VolumetricMaxPooling
                 |      (7): cudnn.VolumetricConvolution(32 -> 64, 3x3x3, 1,1,1, 1,1,1)
                 |      (8): cudnn.ReLU
                 |      (9): cudnn.VolumetricMaxPooling
                 |      (10): nn.Reshape(512)
                 |    }
                  `-> (5): nn.Sequential {
                        [input -> (1) -> (2) -> (3) -> (4) -> (5) -> (6) -> (7) -> (8) -> (9) -> (10) -> output]
                        (1): cudnn.VolumetricConvolution(1 -> 16, 3x3x3, 1,1,1, 1,1,1)
                        (2): cudnn.ReLU
                        (3): cudnn.VolumetricMaxPooling
                        (4): cudnn.VolumetricConvolution(16 -> 32, 3x3x3, 1,1,1, 1,1,1)
                        (5): cudnn.ReLU
                        (6): cudnn.VolumetricMaxPooling
                        (7): cudnn.VolumetricConvolution(32 -> 64, 3x3x3, 1,1,1, 1,1,1)
                        (8): cudnn.ReLU
                        (9): cudnn.VolumetricMaxPooling
                        (10): nn.Reshape(512)
                      }
                  ... -> output
             }
             (2): nn.Reshape(1x2560)
           }
       ... -> output
  }
  (2): cudnn.SpatialMaxPooling(1x1, 1,1)
  (3): nn.Reshape(2560)
  (4): nn.Linear(2560 -> 2048)
  (5): cudnn.ReLU
  (6): nn.Dropout(0.500000)
  (7): nn.Linear(2048 -> 8)
  (8): cudnn.LogSoftMax
}
/root/torch/install/bin/luajit: /root/torch/install/share/lua/5.1/cudnn/convert.lua:64: attempt to call method 'replace' (a nil value)
stack traceback:
	/root/torch/install/share/lua/5.1/cudnn/convert.lua:64: in function 'convert'
	train_point_cloud.lua:43: in main chunk
	[C]: in function 'dofile'
	/root/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
	[C]: at 0x00406670