Input Layer type: ImageData in windows caffe cpp giving Blank Output

Question

I am working on Image Segmentation problem using caffe in windows using cpp. I am using the "Imagedata" input type to train the network but I am getting the Blank output while testing. Can anyone help me to analyse the issue.

**********  solver.prototxt  ***************

test_initialization: false
base_lr: 0.01
display: 51
max_iter: 50000
lr_policy: "step"
gamma: 0.1
momentum: 0.9
weight_decay: 0.0001
stepsize: 4069
snapshot: 10000
snapshot_prefix: "snapshot"
solver_mode: GPU
net: "train.prototxt"
solver_type: SGD

File_Triangle.txt and File_label_triangle.txt has the absolute path of the image location and a dummy label. e.g D:\00000032.png 0

****************  train.prototxt   ********************

layer {
  name: "data"
  type: "ImageData"
  top: "data"
  top: "xx"
  include {
    phase: TRAIN
  }
  image_data_param {
    source: "File_triangle.txt"
     batch_size: 1
     new_height: 32
     new_width: 32
     is_color: False
}

}

layer {
  name: "label"
  type: "ImageData"
  top: "label"
  top: "yy"
  image_data_param {
    source: "File_label_triangle.txt"
     batch_size: 1
     new_height: 32
     new_width: 32
     is_color: False
}
  include {
    phase: TRAIN
  }
}


layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  param {
    lr_mult: 1.0
  }
  param {
    lr_mult: 0.10000000149
  }
  convolution_param {
    num_output: 32
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "gaussian"
      std: 0.0010000000475
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "conv1"
  top: "conv1"
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "conv1"
  top: "conv2"
  param {
    lr_mult: 1.0
  }
  param {
    lr_mult: 0.10000000149
  }
  convolution_param {
    num_output: 1024
    pad: 0
    kernel_size: 16
    stride: 16
    weight_filler {
      type: "gaussian"
      std: 0.0010000000475
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu2"
  type: "ReLU"
  bottom: "conv2"
  top: "conv2"
}
layer {
  name: "upsample"
  type: "Deconvolution"
  bottom: "conv2"
  top: "upsample"
  param {
    lr_mult: 1.0
  }
  convolution_param {
    num_output: 1
    pad: 0
    kernel_size: 16
    stride: 16
    bias_filler {
      type: "constant"
      value: 128.0
    }
  }
}
layer {
  name: "lossL1"
  type: "SmoothL1Loss"
  bottom: "upsample"
  bottom: "label"
  top: "lossL1"
  loss_weight: 1.0
}

Code snippet for training in cpp

shared_ptr<Net<float> > net_;
net_.reset(new Net<float>("train.prototxt", caffe::Phase::TRAIN));
Caffe::set_mode(Caffe::GPU);
caffe::SolverParameter solver_param;
caffe::ReadSolverParamsFromTextFileOrDie("solver.prototxt", &solver_param);
boost::shared_ptr<caffe::Solver<float> > solver(caffe::SolverRegistry<float>::CreateSolver(solver_param));
solver->Solve();

After Training I am using .caffemodel to test the network.

********************  test.prototxt  **********************

layer {
  name: "data"
  type: "Input"
  top: "data"
  input_param { shape: { dim: 1 dim: 1 dim: 32 dim: 32 } }
}

layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  param {
    lr_mult: 1.0
  }
  param {
    lr_mult: 0.10000000149
  }
  convolution_param {
    num_output: 32
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "gaussian"
      std: 0.0010000000475
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "conv1"
  top: "conv1"
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "conv1"
  top: "conv2"
  param {
    lr_mult: 1.0
  }
  param {
    lr_mult: 0.10000000149
  }
  convolution_param {
    num_output: 1024
    pad: 0
    kernel_size: 16
    stride: 16
    weight_filler {
      type: "gaussian"
      std: 0.0010000000475
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu2"
  type: "ReLU"
  bottom: "conv2"
  top: "conv2"
}
layer {
  name: "upsample"
  type: "Deconvolution"
  bottom: "conv2"
  top: "upsample"
  param {
    lr_mult: 1.0
  }
  convolution_param {
    num_output: 1
    pad: 0
    kernel_size: 16
    stride: 16
    bias_filler {
      type: "constant"
      value: 128.0
    }
  }
}

The Code Snippet used for testing.

Caffe::set_mode(Caffe::GPU);

boost::shared_ptr<caffe::Net<float> > net_;
net_.reset(new Net<float>("test.prototxt", caffe::TEST));

net_->CopyTrainedLayersFrom("snapshot_iter_50000.caffemodel");

cv::Mat matInput = cv::imread("input image path");

matInput.convertTo(matInput, CV_32F);
int height = matInput.rows;
int width = matInput.cols;

Blob<float>* input_layer = net_->input_blobs()[0];
float* input_data = input_layer->mutable_cpu_data();
int layer_index = height * width;
for (size_t i = 0; i < height; i++)
{
    for (size_t j = 0; j < width; j++)
    {
        input_data[i*width + j] = matInput.at<float>(i, j);
    }

}

net_->Forward();

const shared_ptr<Blob<float> >& concat_blob = net_->blob_by_name("upsample");
const float* concat_out = concat_blob->cpu_data();

cv::Mat matout(height, width, CV_8UC1);
for (size_t i = 0; i < height*width; i++)
{
    matout.data[i] = concat_out[i];
}

cv::imwrite(output_str, matout);

AnkitSahu AnkitSahu · Accepted Answer · 2017-03-27T06:41:49

I got the issue. The network is giving proper output but the mistake is with dumping it. The Network is giving output in float (i.e at upsample layer) and it is not in a normalize form. Below modifications is giving proper output.

const shared_ptr<Blob<float> >& concat_blob = net_->blob_by_name("upsample");
const float* concat_out = concat_blob->cpu_data();

cv::Mat matout(height, width, CV_32FC1);
for (int i = 0; i < height; i++)
{
    for (int j = 0; j < width; j++)
    {
         matout.at<float>(i, j) = (float)(concat_out[i*width + j]);
    }
}
cv::normalize(matout, matout, 0, 255, CV_MINMAX);
cv::imwrite("output image path", matout);

Input Layer type: ImageData in windows caffe cpp giving Blank Output

1 Answers