我有一个用于深度估计的全卷积网络，简化为只展示上层和下层:

# input: image and depth_imagelayer {  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    }}# Errorlayer {  name: "accuracy"  type: "Accuracy"  bottom: "result"  bottom: "depth"  top: "accuracy"  include {    phase: TEST  }}layer {  name: "loss"  type: "EuclideanLoss"  bottom: "result"  bottom: "depth"  top: "loss"}

现在我有三个问题:

当我在训练网络时，准确度层总是显示为1。我不明白这是为什么？

EuclideanLayer是否是这种情况的正确层？

在这种情况下是否需要使用均值，或者我可以忽略均值？

#Define image transformerstransformer = 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']

回答：

1. 准确度总是1 – 请参考这个回答。
2. "EuclideanLoss"层适合用于回归任务。
3. 减去均值可以帮助网络更好地收敛。继续使用它。你可以在这里阅读更多关于数据归一化的重要性及其相关做法。