Caffe 损失层、均值和准确度

Question

我有一个完全卷积的深度估计网络，如下所示：（为了简单起见，只有上层和下层）：

# input: image and depth_image
layer {
  name: "train-data"
  type: "Data"
  top: "data"
  top: "silence_1"
  include {
    phase: TRAIN
  }
  transform_param {
    #mean_file: "mean_train.binaryproto"
    scale: 0.00390625
  }
  data_param {
        source: "/train_lmdb"
    batch_size: 4
    backend: LMDB
  }
}
layer {
  name: "train-depth"
  type: "Data"
  top: "depth"
  top: "silence_2"
  include {
    phase: TRAIN
  }
  transform_param {
    scale: 0.00390625
  }
  data_param {
    source: "train_depth_lmdb"
    batch_size: 4
    backend: LMDB
  }
}
layer {
  name: "val-data"
  type: "Data"
  top: "data"
  top: "silence_1"
  include {
    phase: TEST
  }
  transform_param {
    #mean_file: "mean_val.binaryproto"
    scale: 0.00390625
  }
  data_param {
    source: "val_lmdb"
    batch_size: 4
    backend: LMDB
  }
}
layer {
  name: "val-depth"
  type: "Data"
  top: "depth"
  top: "silence_2"
  include {
    phase: TEST
  }
  transform_param {
    scale: 0.00390625
  }
  data_param {
    source: "val_depth_lmdb"
    batch_size: 4
    backend: LMDB
  }
}
################## Silence unused labels ##################
layer {
    name: "silence_layer_1"
    type: "Silence"
    bottom: "silence_1"
}

layer {
    name: "silence_layer_2"
    type: "Silence"
    bottom: "silence_2"
}
....
layer {
    name: "conv"
    type: "Convolution"
    bottom: "concat"
    top: "conv"
    convolution_param {
        num_output: 1
        kernel_size: 5
        pad: 2
        stride: 1
        engine: CUDNN
        weight_filler {
            type: "gaussian"
            std: 0.01
        }
        bias_filler {
            type: "constant"
            value: 0
        }
    }
}

layer {
    name: "relu"
    type: "ReLU"
    bottom: "conv"
    top: "result"
    relu_param{
    negative_slope: 0.01
        engine: CUDNN
    }
}

# Error
layer {
  name: "accuracy"
  type: "Accuracy"
  bottom: "result"
  bottom: "depth"
  top: "accuracy"
  include {
    phase: TEST
  }
}
layer {
  name: "loss"
  type: "EuclideanLoss"
  bottom: "result"
  bottom: "depth"
  top: "loss"
}

现在我有3个问题：

当我训练网络时，精度层总是 1。我不明白为什么？

EuclideanLayer 是用于此目的的正确层吗？

在这种情况下需要均值还是我可以忽略均值？

#Define image transformers
transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})
transformer.set_mean('data', mean_array)
transformer.set_transpose('data', (2,0,1))

image = "test.png"

img = caffe.io.load_image(image, False)

img = caffe.io.resize_image( img, (IMAGE_WIDTH, IMAGE_HEIGHT))

net.blobs['data'].data[...] = transformer.preprocess('data', img)

pred = net.forward()

output_blob = pred['result']

Answer 1

准确度始终为 1 - 请参阅。
"EuclideanLoss" 层非常适合回归。
减去均值应该有助于网络更好地收敛。继续使用它。您可以阅读更多关于数据规范化的重要性以及在这方面可以做些什么 here.

Caffe 损失层、均值和准确度

Caffe loss layer, mean and accuracy

machine-learning

neural-network

deep-learning

caffe

conv-neural-network