Modified DetectNet without Bounding Box Learning

[krishneel]

I have managed to train DetectNet on my custom data to detect truck from aerial images. I used 600 for training and 200 for Val. The images were of 1280 x 720 resolution. The detection results gives bounding boxes as required.

Now, I want to do something little different that is, I want to predict the probabilities of an image region containing an object and then use some segmentation method like min-max cuts to segment the actual object.

If I understand well than DetectNet overlays an image with specified grid and than each grid predicts whether an object or part of an object is present on that particular grid. I am not interested in getting object bounding boxes but just a heatmap or probability map of each region specified by the grid. I think #L2484 should give this heatmap. I have removed all bounding box layers from the DetectNet Prototxt and my sample prototxt file is attached below.

Note that I did not use the Nvidia Data Argumentation Layer but I wrote my own slightly different argumentation and I divided the image into grids and then label each grid either as an object, part of an object (IOU > 0.7) or background. Labels are either 0 for background or 1 for foreground. I wrote the labels to HDF-5 which I read and use the layer reshape to change to 2D blobs. For e.g. for an image of 610 x 610 with grid size of 16 x 16 I will get 38 x 38 regions which is read from HDF5 as 1 x 1444 dimension vector. Finally just like the DetectNet I use EuclideanLoss to compute the loss.

Unfortunately the aforementioned network seems not to converge at all. I am using 600 training image where objects are covering almost 30-60% of each image. I have spent alot of time trying to debug what is wrong and I realized that after the first iteration the output from the Sigmoid Layer #L2399 outputs only zero. I tried to run it for over 200 epoch but its same. Only in the first iteration the output is some probabilities but thereafter its all zero.

My question is:

1. What could be the reason that the network is not learning anything? Why the output is zero?
2. Is DetectNet learning dependent on the bounding box? I feel that removing the bounding box learning should not affect the learning of cvg/classifier.
3. Besides I am beginner in this area so maybe my representation is incorrect and I will grateful if I can get come expert input weather I am on the right track or not.

Thanks

`# Data/Input layers
name: "DetectNet"
layer {
  ntruck_datasetsame: "train_data"
  type: "Data"
  top: "data"
  data_param {
    backend: LMDB
    source: "jobs/20161115-230826-c442/train_db/features"   
    batch_size: 3
  }
  include: { 
    phase: TRAIN 
  }
}
layer {
  name: "train_label"
  type: "HDF5Data"
  top: "label"
  hdf5_data_param {
    source: "jobs/train/region_labels.txt"
    batch_size: 3
  }
  include: { phase: TRAIN }
}
layer {
  name: "val_data"
  type: "Data"
  top: "data"
  data_param {
    backend: LMDB
    source: "jobs/20161115-230826-c442/val_db/features"
    batch_size: 2
  }
  include: { phase: TEST}
}
layer {
  name: "val_label"
  type: "HDF5Data"
  top: "label"
  hdf5_data_param {
    source: "jobs/val/region_labels.txt"
    batch_size: 2
  }
  include: { phase: TEST}
}

######################################################################
# Start of convolutional network
######################################################################

layer {
  name: "conv1/7x7_s2"
  type: "Convolution"
  bottom: "data"
  top: "conv1/7x7_s2"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 64
    pad: 3
    kernel_size: 7
    stride: 2
    weight_filler {
      type: "xavier"
      std: 0.1
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}

layer {
  name: "conv1/relu_7x7"
  type: "ReLU"
  bottom: "conv1/7x7_s2"
  top: "conv1/7x7_s2"
}

layer {
  name: "pool1/3x3_s2"
  type: "Pooling"
  bottom: "conv1/7x7_s2"
  top: "pool1/3x3_s2"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}

layer {
  name: "pool1/norm1"
  type: "LRN"
  bottom: "pool1/3x3_s2"
  top: "pool1/norm1"
  lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
  }
}

layer {
  name: "conv2/3x3_reduce"
  type: "Convolution"
  bottom: "pool1/norm1"
  top: "conv2/3x3_reduce"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 64
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.1
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}

layer {
  name: "conv2/relu_3x3_reduce"
  type: "ReLU"
  bottom: "conv2/3x3_reduce"
  top: "conv2/3x3_reduce"
}

layer {
  name: "conv2/3x3"
  type: "Convolution"
  bottom: "conv2/3x3_reduce"
  top: "conv2/3x3"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 192
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
      std: 0.03
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}

layer {
  name: "conv2/relu_3x3"
  type: "ReLU"
  bottom: "conv2/3x3"
  top: "conv2/3x3"
}

layer {
  name: "conv2/norm2"
  type: "LRN"
  bottom: "conv2/3x3"
  top: "conv2/norm2"
  lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
  }
}

layer {
  name: "pool2/3x3_s2"
  type: "Pooling"
  bottom: "conv2/norm2"
  top: "pool2/3x3_s2"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}

layer {
  name: "inception_3a/1x1"
  type: "Convolution"
  bottom: "pool2/3x3_s2"
  top: "inception_3a/1x1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 64
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.03
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}

layer {
  name: "inception_3a/relu_1x1"
  type: "ReLU"
  bottom: "inception_3a/1x1"
  top: "inception_3a/1x1"
}

layer {
  name: "inception_3a/3x3_reduce"
  type: "Convolution"
  bottom: "pool2/3x3_s2"
  top: "inception_3a/3x3_reduce"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 96
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.09
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}

layer {
  name: "inception_3a/relu_3x3_reduce"
  type: "ReLU"
  bottom: "inception_3a/3x3_reduce"
  top: "inception_3a/3x3_reduce"
}

layer {
  name: "inception_3a/3x3"
  type: "Convolution"
  bottom: "inception_3a/3x3_reduce"
  top: "inception_3a/3x3"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
      std: 0.03
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}

layer {
  name: "inception_3a/relu_3x3"
  type: "ReLU"
  bottom: "inception_3a/3x3"
  top: "inception_3a/3x3"
}

layer {
  name: "inception_3a/5x5_reduce"
  type: "Convolution"
  bottom: "pool2/3x3_s2"
  top: "inception_3a/5x5_reduce"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 16
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.2
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_3a/relu_5x5_reduce"
  type: "ReLU"
  bottom: "inception_3a/5x5_reduce"
  top: "inception_3a/5x5_reduce"
}
layer {
  name: "inception_3a/5x5"
  type: "Convolution"
  bottom: "inception_3a/5x5_reduce"
  top: "inception_3a/5x5"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 32
    pad: 2
    kernel_size: 5
    weight_filler {
      type: "xavier"
      std: 0.03
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_3a/relu_5x5"
  type: "ReLU"
  bottom: "inception_3a/5x5"
  top: "inception_3a/5x5"
}

layer {
  name: "inception_3a/pool"
  type: "Pooling"
  bottom: "pool2/3x3_s2"
  top: "inception_3a/pool"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 1
    pad: 1
  }
}

layer {
  name: "inception_3a/pool_proj"
  type: "Convolution"
  bottom: "inception_3a/pool"
  top: "inception_3a/pool_proj"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 32
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.1
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_3a/relu_pool_proj"
  type: "ReLU"
  bottom: "inception_3a/pool_proj"
  top: "inception_3a/pool_proj"
}

layer {
  name: "inception_3a/output"
  type: "Concat"
  bottom: "inception_3a/1x1"
  bottom: "inception_3a/3x3"
  bottom: "inception_3a/5x5"
  bottom: "inception_3a/pool_proj"
  top: "inception_3a/output"
}

layer {
  name: "inception_3b/1x1"
  type: "Convolution"
  bottom: "inception_3a/output"
  top: "inception_3b/1x1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.03
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}

layer {
  name: "inception_3b/relu_1x1"
  type: "ReLU"
  bottom: "inception_3b/1x1"
  top: "inception_3b/1x1"
}

layer {
  name: "inception_3b/3x3_reduce"
  type: "Convolution"
  bottom: "inception_3a/output"
  top: "inception_3b/3x3_reduce"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.09
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_3b/relu_3x3_reduce"
  type: "ReLU"
  bottom: "inception_3b/3x3_reduce"
  top: "inception_3b/3x3_reduce"
}
layer {
  name: "inception_3b/3x3"
  type: "Convolution"
  bottom: "inception_3b/3x3_reduce"
  top: "inception_3b/3x3"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 192
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
      std: 0.03
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_3b/relu_3x3"
  type: "ReLU"
  bottom: "inception_3b/3x3"
  top: "inception_3b/3x3"
}

layer {
  name: "inception_3b/5x5_reduce"
  type: "Convolution"
  bottom: "inception_3a/output"
  top: "inception_3b/5x5_reduce"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 32
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.2
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_3b/relu_5x5_reduce"
  type: "ReLU"
  bottom: "inception_3b/5x5_reduce"
  top: "inception_3b/5x5_reduce"
}
layer {
  name: "inception_3b/5x5"
  type: "Convolution"
  bottom: "inception_3b/5x5_reduce"
  top: "inception_3b/5x5"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 96
    pad: 2
    kernel_size: 5
    weight_filler {
      type: "xavier"
      std: 0.03
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_3b/relu_5x5"
  type: "ReLU"
  bottom: "inception_3b/5x5"
  top: "inception_3b/5x5"
}

layer {
  name: "inception_3b/pool"
  type: "Pooling"
  bottom: "inception_3a/output"
  top: "inception_3b/pool"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 1
    pad: 1
  }
}
layer {
  name: "inception_3b/pool_proj"
  type: "Convolution"
  bottom: "inception_3b/pool"
  top: "inception_3b/pool_proj"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 64
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.1
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_3b/relu_pool_proj"
  type: "ReLU"
  bottom: "inception_3b/pool_proj"
  top: "inception_3b/pool_proj"
}
layer {
  name: "inception_3b/output"
  type: "Concat"
  bottom: "inception_3b/1x1"
  bottom: "inception_3b/3x3"
  bottom: "inception_3b/5x5"
  bottom: "inception_3b/pool_proj"
  top: "inception_3b/output"
}

layer {
  name: "pool3/3x3_s2"
  type: "Pooling"
  bottom: "inception_3b/output"
  top: "pool3/3x3_s2"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}

layer {
  name: "inception_4a/1x1"
  type: "Convolution"
  bottom: "pool3/3x3_s2"
  top: "inception_4a/1x1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 192
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.03
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}

layer {
  name: "inception_4a/relu_1x1"
  type: "ReLU"
  bottom: "inception_4a/1x1"
  top: "inception_4a/1x1"
}

layer {
  name: "inception_4a/3x3_reduce"
  type: "Convolution"
  bottom: "pool3/3x3_s2"
  top: "inception_4a/3x3_reduce"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 96
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.09
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}

layer {
  name: "inception_4a/relu_3x3_reduce"
  type: "ReLU"
  bottom: "inception_4a/3x3_reduce"
  top: "inception_4a/3x3_reduce"
}

layer {
  name: "inception_4a/3x3"
  type: "Convolution"
  bottom: "inception_4a/3x3_reduce"
  top: "inception_4a/3x3"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 208
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
      std: 0.03
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}

layer {
  name: "inception_4a/relu_3x3"
  type: "ReLU"
  bottom: "inception_4a/3x3"
  top: "inception_4a/3x3"
}

layer {
  name: "inception_4a/5x5_reduce"
  type: "Convolution"
  bottom: "pool3/3x3_s2"
  top: "inception_4a/5x5_reduce"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 16
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.2
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_4a/relu_5x5_reduce"
  type: "ReLU"
  bottom: "inception_4a/5x5_reduce"
  top: "inception_4a/5x5_reduce"
}
layer {
  name: "inception_4a/5x5"
  type: "Convolution"
  bottom: "inception_4a/5x5_reduce"
  top: "inception_4a/5x5"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 48
    pad: 2
    kernel_size: 5
    weight_filler {
      type: "xavier"
      std: 0.03
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_4a/relu_5x5"
  type: "ReLU"
  bottom: "inception_4a/5x5"
  top: "inception_4a/5x5"
}
layer {
  name: "inception_4a/pool"
  type: "Pooling"
  bottom: "pool3/3x3_s2"
  top: "inception_4a/pool"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 1
    pad: 1
  }
}
layer {
  name: "inception_4a/pool_proj"
  type: "Convolution"
  bottom: "inception_4a/pool"
  top: "inception_4a/pool_proj"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 64
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.1
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_4a/relu_pool_proj"
  type: "ReLU"
  bottom: "inception_4a/pool_proj"
  top: "inception_4a/pool_proj"
}
layer {
  name: "inception_4a/output"
  type: "Concat"
  bottom: "inception_4a/1x1"
  bottom: "inception_4a/3x3"
  bottom: "inception_4a/5x5"
  bottom: "inception_4a/pool_proj"
  top: "inception_4a/output"
}

layer {
  name: "inception_4b/1x1"
  type: "Convolution"
  bottom: "inception_4a/output"
  top: "inception_4b/1x1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 160
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.03
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}

layer {
  name: "inception_4b/relu_1x1"
  type: "ReLU"
  bottom: "inception_4b/1x1"
  top: "inception_4b/1x1"
}
layer {
  name: "inception_4b/3x3_reduce"
  type: "Convolution"
  bottom: "inception_4a/output"
  top: "inception_4b/3x3_reduce"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 112
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.09
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_4b/relu_3x3_reduce"
  type: "ReLU"
  bottom: "inception_4b/3x3_reduce"
  top: "inception_4b/3x3_reduce"
}
layer {
  name: "inception_4b/3x3"
  type: "Convolution"
  bottom: "inception_4b/3x3_reduce"
  top: "inception_4b/3x3"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 224
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
      std: 0.03
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_4b/relu_3x3"
  type: "ReLU"
  bottom: "inception_4b/3x3"
  top: "inception_4b/3x3"
}
layer {
  name: "inception_4b/5x5_reduce"
  type: "Convolution"
  bottom: "inception_4a/output"
  top: "inception_4b/5x5_reduce"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 24
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.2
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_4b/relu_5x5_reduce"
  type: "ReLU"
  bottom: "inception_4b/5x5_reduce"
  top: "inception_4b/5x5_reduce"
}
layer {
  name: "inception_4b/5x5"
  type: "Convolution"
  bottom: "inception_4b/5x5_reduce"
  top: "inception_4b/5x5"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 64
    pad: 2
    kernel_size: 5
    weight_filler {
      type: "xavier"
      std: 0.03
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_4b/relu_5x5"
  type: "ReLU"
  bottom: "inception_4b/5x5"
  top: "inception_4b/5x5"
}
layer {
  name: "inception_4b/pool"
  type: "Pooling"
  bottom: "inception_4a/output"
  top: "inception_4b/pool"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 1
    pad: 1
  }
}
layer {
  name: "inception_4b/pool_proj"
  type: "Convolution"
  bottom: "inception_4b/pool"
  top: "inception_4b/pool_proj"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 64
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.1
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_4b/relu_pool_proj"
  type: "ReLU"
  bottom: "inception_4b/pool_proj"
  top: "inception_4b/pool_proj"
}
layer {
  name: "inception_4b/output"
  type: "Concat"
  bottom: "inception_4b/1x1"
  bottom: "inception_4b/3x3"
  bottom: "inception_4b/5x5"
  bottom: "inception_4b/pool_proj"
  top: "inception_4b/output"
}

layer {
  name: "inception_4c/1x1"
  type: "Convolution"
  bottom: "inception_4b/output"
  top: "inception_4c/1x1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.03
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}

layer {
  name: "inception_4c/relu_1x1"
  type: "ReLU"
  bottom: "inception_4c/1x1"
  top: "inception_4c/1x1"
}

layer {
  name: "inception_4c/3x3_reduce"
  type: "Convolution"
  bottom: "inception_4b/output"
  top: "inception_4c/3x3_reduce"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.09
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}

layer {
  name: "inception_4c/relu_3x3_reduce"
  type: "ReLU"
  bottom: "inception_4c/3x3_reduce"
  top: "inception_4c/3x3_reduce"
}
layer {
  name: "inception_4c/3x3"
  type: "Convolution"
  bottom: "inception_4c/3x3_reduce"
  top: "inception_4c/3x3"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
      std: 0.03
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_4c/relu_3x3"
  type: "ReLU"
  bottom: "inception_4c/3x3"
  top: "inception_4c/3x3"
}
layer {
  name: "inception_4c/5x5_reduce"
  type: "Convolution"
  bottom: "inception_4b/output"
  top: "inception_4c/5x5_reduce"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 24
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.2
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_4c/relu_5x5_reduce"
  type: "ReLU"
  bottom: "inception_4c/5x5_reduce"
  top: "inception_4c/5x5_reduce"
}
layer {
  name: "inception_4c/5x5"
  type: "Convolution"
  bottom: "inception_4c/5x5_reduce"
  top: "inception_4c/5x5"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 64
    pad: 2
    kernel_size: 5
    weight_filler {
      type: "xavier"
      std: 0.03
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_4c/relu_5x5"
  type: "ReLU"
  bottom: "inception_4c/5x5"
  top: "inception_4c/5x5"
}
layer {
  name: "inception_4c/pool"
  type: "Pooling"
  bottom: "inception_4b/output"
  top: "inception_4c/pool"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 1
    pad: 1
  }
}
layer {
  name: "inception_4c/pool_proj"
  type: "Convolution"
  bottom: "inception_4c/pool"
  top: "inception_4c/pool_proj"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 64
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.1
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_4c/relu_pool_proj"
  type: "ReLU"
  bottom: "inception_4c/pool_proj"
  top: "inception_4c/pool_proj"
}
layer {
  name: "inception_4c/output"
  type: "Concat"
  bottom: "inception_4c/1x1"
  bottom: "inception_4c/3x3"
  bottom: "inception_4c/5x5"
  bottom: "inception_4c/pool_proj"
  top: "inception_4c/output"
}

layer {
  name: "inception_4d/1x1"
  type: "Convolution"
  bottom: "inception_4c/output"
  top: "inception_4d/1x1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 112
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.1
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_4d/relu_1x1"
  type: "ReLU"
  bottom: "inception_4d/1x1"
  top: "inception_4d/1x1"
}
layer {
  name: "inception_4d/3x3_reduce"
  type: "Convolution"
  bottom: "inception_4c/output"
  top: "inception_4d/3x3_reduce"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 144
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.1
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_4d/relu_3x3_reduce"
  type: "ReLU"
  bottom: "inception_4d/3x3_reduce"
  top: "inception_4d/3x3_reduce"
}
layer {
  name: "inception_4d/3x3"
  type: "Convolution"
  bottom: "inception_4d/3x3_reduce"
  top: "inception_4d/3x3"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 288
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
      std: 0.1
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_4d/relu_3x3"
  type: "ReLU"
  bottom: "inception_4d/3x3"
  top: "inception_4d/3x3"
}
layer {
  name: "inception_4d/5x5_reduce"
  type: "Convolution"
  bottom: "inception_4c/output"
  top: "inception_4d/5x5_reduce"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 32
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.1
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_4d/relu_5x5_reduce"
  type: "ReLU"
  bottom: "inception_4d/5x5_reduce"
  top: "inception_4d/5x5_reduce"
}
layer {
  name: "inception_4d/5x5"
  type: "Convolution"
  bottom: "inception_4d/5x5_reduce"
  top: "inception_4d/5x5"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 64
    pad: 2
    kernel_size: 5
    weight_filler {
      type: "xavier"
      std: 0.1
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_4d/relu_5x5"
  type: "ReLU"
  bottom: "inception_4d/5x5"
  top: "inception_4d/5x5"
}
layer {
  name: "inception_4d/pool"
  type: "Pooling"
  bottom: "inception_4c/output"
  top: "inception_4d/pool"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 1
    pad: 1
  }
}
layer {
  name: "inception_4d/pool_proj"
  type: "Convolution"
  bottom: "inception_4d/pool"
  top: "inception_4d/pool_proj"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 64
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.1
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_4d/relu_pool_proj"
  type: "ReLU"
  bottom: "inception_4d/pool_proj"
  top: "inception_4d/pool_proj"
}
layer {
  name: "inception_4d/output"
  type: "Concat"
  bottom: "inception_4d/1x1"
  bottom: "inception_4d/3x3"
  bottom: "inception_4d/5x5"
  bottom: "inception_4d/pool_proj"
  top: "inception_4d/output"
}

layer {
  name: "inception_4e/1x1"
  type: "Convolution"
  bottom: "inception_4d/output"
  top: "inception_4e/1x1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.03
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_4e/relu_1x1"
  type: "ReLU"
  bottom: "inception_4e/1x1"
  top: "inception_4e/1x1"
}
layer {
  name: "inception_4e/3x3_reduce"
  type: "Convolution"
  bottom: "inception_4d/output"
  top: "inception_4e/3x3_reduce"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 160
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.09
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_4e/relu_3x3_reduce"
  type: "ReLU"
  bottom: "inception_4e/3x3_reduce"
  top: "inception_4e/3x3_reduce"
}
layer {
  name: "inception_4e/3x3"
  type: "Convolution"
  bottom: "inception_4e/3x3_reduce"
  top: "inception_4e/3x3"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 320
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
      std: 0.03
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_4e/relu_3x3"
  type: "ReLU"
  bottom: "inception_4e/3x3"
  top: "inception_4e/3x3"
}
layer {
  name: "inception_4e/5x5_reduce"
  type: "Convolution"
  bottom: "inception_4d/output"
  top: "inception_4e/5x5_reduce"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 32
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.2
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_4e/relu_5x5_reduce"
  type: "ReLU"
  bottom: "inception_4e/5x5_reduce"
  top: "inception_4e/5x5_reduce"
}
layer {
  name: "inception_4e/5x5"
  type: "Convolution"
  bottom: "inception_4e/5x5_reduce"
  top: "inception_4e/5x5"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    pad: 2
    kernel_size: 5
    weight_filler {
      type: "xavier"
      std: 0.03
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_4e/relu_5x5"
  type: "ReLU"
  bottom: "inception_4e/5x5"
  top: "inception_4e/5x5"
}
layer {
  name: "inception_4e/pool"
  type: "Pooling"
  bottom: "inception_4d/output"
  top: "inception_4e/pool"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 1
    pad: 1
  }
}
layer {
  name: "inception_4e/pool_proj"
  type: "Convolution"
  bottom: "inception_4e/pool"
  top: "inception_4e/pool_proj"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.1
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_4e/relu_pool_proj"
  type: "ReLU"
  bottom: "inception_4e/pool_proj"
  top: "inception_4e/pool_proj"
}
layer {
  name: "inception_4e/output"
  type: "Concat"
  bottom: "inception_4e/1x1"
  bottom: "inception_4e/3x3"
  bottom: "inception_4e/5x5"
  bottom: "inception_4e/pool_proj"
  top: "inception_4e/output"
}

layer {
  name: "inception_5a/1x1"
  type: "Convolution"
  bottom: "inception_4e/output"
  top: "inception_5a/1x1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.03
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_5a/relu_1x1"
  type: "ReLU"
  bottom: "inception_5a/1x1"
  top: "inception_5a/1x1"
}

layer {
  name: "inception_5a/3x3_reduce"
  type: "Convolution"
  bottom: "inception_4e/output"
  top: "inception_5a/3x3_reduce"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 160
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.09
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_5a/relu_3x3_reduce"
  type: "ReLU"
  bottom: "inception_5a/3x3_reduce"
  top: "inception_5a/3x3_reduce"
}

layer {
  name: "inception_5a/3x3"
  type: "Convolution"
  bottom: "inception_5a/3x3_reduce"
  top: "inception_5a/3x3"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 320
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
      std: 0.03
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_5a/relu_3x3"
  type: "ReLU"
  bottom: "inception_5a/3x3"
  top: "inception_5a/3x3"
}
layer {
  name: "inception_5a/5x5_reduce"
  type: "Convolution"
  bottom: "inception_4e/output"
  top: "inception_5a/5x5_reduce"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 32
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.2
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_5a/relu_5x5_reduce"
  type: "ReLU"
  bottom: "inception_5a/5x5_reduce"
  top: "inception_5a/5x5_reduce"
}
layer {
  name: "inception_5a/5x5"
  type: "Convolution"
  bottom: "inception_5a/5x5_reduce"
  top: "inception_5a/5x5"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    pad: 2
    kernel_size: 5
    weight_filler {
      type: "xavier"
      std: 0.03
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_5a/relu_5x5"
  type: "ReLU"
  bottom: "inception_5a/5x5"
  top: "inception_5a/5x5"
}
layer {
  name: "inception_5a/pool"
  type: "Pooling"
  bottom: "inception_4e/output"
  top: "inception_5a/pool"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 1
    pad: 1
  }
}
layer {
  name: "inception_5a/pool_proj"
  type: "Convolution"
  bottom: "inception_5a/pool"
  top: "inception_5a/pool_proj"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.1
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_5a/relu_pool_proj"
  type: "ReLU"
  bottom: "inception_5a/pool_proj"
  top: "inception_5a/pool_proj"
}
layer {
  name: "inception_5a/output"
  type: "Concat"
  bottom: "inception_5a/1x1"
  bottom: "inception_5a/3x3"
  bottom: "inception_5a/5x5"
  bottom: "inception_5a/pool_proj"
  top: "inception_5a/output"
}

layer {
  name: "inception_5b/1x1"
  type: "Convolution"
  bottom: "inception_5a/output"
  top: "inception_5b/1x1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 384
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.1
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_5b/relu_1x1"
  type: "ReLU"
  bottom: "inception_5b/1x1"
  top: "inception_5b/1x1"
}
layer {
  name: "inception_5b/3x3_reduce"
  type: "Convolution"
  bottom: "inception_5a/output"
  top: "inception_5b/3x3_reduce"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  convolution_param {
    num_output: 192
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.1
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_5b/relu_3x3_reduce"
  type: "ReLU"
  bottom: "inception_5b/3x3_reduce"
  top: "inception_5b/3x3_reduce"
}
layer {
  name: "inception_5b/3x3"
  type: "Convolution"
  bottom: "inception_5b/3x3_reduce"
  top: "inception_5b/3x3"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 384
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
      std: 0.1
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_5b/relu_3x3"
  type: "ReLU"
  bottom: "inception_5b/3x3"
  top: "inception_5b/3x3"
}
layer {
  name: "inception_5b/5x5_reduce"
  type: "Convolution"
  bottom: "inception_5a/output"
  top: "inception_5b/5x5_reduce"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 48
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.1
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_5b/relu_5x5_reduce"
  type: "ReLU"
  bottom: "inception_5b/5x5_reduce"
  top: "inception_5b/5x5_reduce"
}
layer {
  name: "inception_5b/5x5"
  type: "Convolution"
  bottom: "inception_5b/5x5_reduce"
  top: "inception_5b/5x5"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    pad: 2
    kernel_size: 5
    weight_filler {
      type: "xavier"
      std: 0.1
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_5b/relu_5x5"
  type: "ReLU"
  bottom: "inception_5b/5x5"
  top: "inception_5b/5x5"
}
layer {
  name: "inception_5b/pool"
  type: "Pooling"
  bottom: "inception_5a/output"
  top: "inception_5b/pool"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 1
    pad: 1
  }
}
layer {
  name: "inception_5b/pool_proj"
  type: "Convolution"
  bottom: "inception_5b/pool"
  top: "inception_5b/pool_proj"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.1
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "inception_5b/relu_pool_proj"
  type: "ReLU"
  bottom: "inception_5b/pool_proj"
  top: "inception_5b/pool_proj"
}
layer {
  name: "inception_5b/output"
  type: "Concat"
  bottom: "inception_5b/1x1"
  bottom: "inception_5b/3x3"
  bottom: "inception_5b/5x5"
  bottom: "inception_5b/pool_proj"
  top: "inception_5b/output"
}
layer {
  name: "pool5/drop_s1"
  type: "Dropout"
  bottom: "inception_5b/output"
  top: "pool5/drop_s1"
  dropout_param {
    dropout_ratio: 0.4
  }
}
layer {
  name: "cvg/classifier"
  type: "Convolution"
  bottom: "pool5/drop_s1"
  top: "cvg/classifier"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 1
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.03
    }
    bias_filler {
      type: "constant"
      value: 0.
    }
  }
}
layer {
  name: "coverage/sig"
  type: "Sigmoid"
  bottom: "cvg/classifier"
  top: "coverage"
}

######################################################################
# End of convolutional network
######################################################################

layer {
  name: "reshape"
  type: "Reshape"
  bottom: "label"
  top: "label_reshape"
  reshape_param {shape: { dim: 0 dim: 1 dim:38 dim:38 } }
}

layer {
  name: "coverage_loss"
  type: "EuclideanLoss"
  bottom: "coverage"
  bottom: "label_reshape"
  top: "loss_coverage"
  include { phase: TRAIN }
  include { phase: TEST}
}`

[gheinrich]

Hello, sorry for the late response. Are you able to sanity check your labels and check whether those are correct? I would also expect your network to learn well, in principle. That being said, it does sound like image segmentation would be more appropriate for your task, right?

Have a look at this example: https://github.com/NVIDIA/DIGITS/tree/digits-5.0/examples/semantic-segmentation

This article might also be helpful: https://devblogs.nvidia.com/parallelforall/image-segmentation-using-digits-5/

Finally, it doesn't sound like you're using DIGITS, correct?