我在caffe和深度学习方面还是个新手。我正在尝试实现深度学习架构。
这是我尝试实现的架构。该架构和Parse27k数据集由亚琛工业大学视觉计算研究所的计算机视觉小组创建和构建。
下面你可以看到我需要改进的模型：
Train_val.prototxt
name: "Parse27"layer { name: "data" type: "HDF5Data" top: "crops" top: "labels" include { phase: TRAIN } hdf5_data_param { source: "/home/nail/caffe/caffe/examples/hdf5_classification/data/train.txt" batch_size: 256 }}layer { name: "data" type: "HDF5Data" top: "crops" top: "labels" include { phase: TEST } hdf5_data_param { source: "/home/nail/caffe/caffe/examples/hdf5_classification/data/test.txt" batch_size: 256 }}layer { name: "conv1" type: "Convolution" bottom: "crops" top: "conv1" param { lr_mult: 1 decay_mult: 1 } param { lr_mult: 2 decay_mult: 0 } convolution_param { num_output: 96 kernel_size: 11 stride: 4 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0 } }}layer { name: "relu1" type: "ReLU" bottom: "conv1" top: "conv1"}layer { name: "pool1" type: "Pooling" bottom: "conv1" top: "pool1" pooling_param { pool: MAX kernel_size: 3 stride: 2 }}layer { name: "norm1" type: "LRN" bottom: "pool1" top: "norm1" lrn_param { local_size: 5 alpha: 0.0001 beta: 0.75 }}layer { name: "conv2" type: "Convolution" bottom: "norm1" top: "conv2" param { lr_mult: 1 decay_mult: 1 } param { lr_mult: 2 decay_mult: 0 } convolution_param { num_output: 256 pad: 2 kernel_size: 5 group: 2 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 1 } }}layer { name: "relu2" type: "ReLU" bottom: "conv2" top: "conv2"}layer { name: "pool2" type: "Pooling" bottom: "conv2" top: "pool2" pooling_param { pool: MAX kernel_size: 3 stride: 2 }}layer { name: "norm2" type: "LRN" bottom: "pool2" top: "norm2" lrn_param { local_size: 5 alpha: 0.0001 beta: 0.75 }}layer { name: "conv3" type: "Convolution" bottom: "norm2" top: "conv3" 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: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0 } }}layer { name: "relu3" type: "ReLU" bottom: "conv3" top: "conv3"}layer { name: "conv4" type: "Convolution" bottom: "conv3" top: "conv4" param { lr_mult: 1 decay_mult: 1 } param { lr_mult: 2 decay_mult: 0 } convolution_param { num_output: 384 pad: 1 kernel_size: 3 group: 2 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 1 } }}layer { name: "relu4" type: "ReLU" bottom: "conv4" top: "conv4"}layer { name: "conv5" type: "Convolution" bottom: "conv4" top: "conv5" param { lr_mult: 1 decay_mult: 1 } param { lr_mult: 2 decay_mult: 0 } convolution_param { num_output: 256 pad: 1 kernel_size: 3 group: 2 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 1 } }}layer { name: "relu5" type: "ReLU" bottom: "conv5" top: "conv5"}layer { name: "pool5" type: "Pooling" bottom: "conv5" top: "pool5" pooling_param { pool: MAX kernel_size: 3 stride: 2 }}layer { name: "fc6" type: "InnerProduct" bottom: "pool5" top: "fc6" param { lr_mult: 1 decay_mult: 1 } param { lr_mult: 2 decay_mult: 0 } inner_product_param { num_output: 4096 weight_filler { type: "gaussian" std: 0.005 } bias_filler { type: "constant" value: 1 } }}layer { name: "relu6" type: "ReLU" bottom: "fc6" top: "fc6"}layer { name: "drop6" type: "Dropout" bottom: "fc6" top: "fc6" dropout_param { dropout_ratio: 0.5 }}layer { name: "fc7" type: "InnerProduct" bottom: "fc6" top: "fc7" param { lr_mult: 1 decay_mult: 1 } param { lr_mult: 2 decay_mult: 0 } inner_product_param { num_output: 4096 weight_filler { type: "gaussian" std: 0.005 } bias_filler { type: "constant" value: 1 } }}layer { name: "relu7" type: "ReLU" bottom: "fc7" top: "fc7"}layer { name: "drop7" type: "Dropout" bottom: "fc7" top: "fc7" dropout_param { dropout_ratio: 0.5 }}layer { name: "fc8" type: "InnerProduct" bottom: "fc7" top: "fc8" param { lr_mult: 1 decay_mult: 1 } param { lr_mult: 2 decay_mult: 0 } inner_product_param { num_output: 1000 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0 } }}layer { name: "accuracy" type: "Accuracy" bottom: "fc8" bottom: "labels" top: "accuracy" include { phase: TEST }}layer { name: "loss" type: "SoftmaxWithLoss" bottom: "fc8" bottom: "labels" top: "loss"}Solver.prototxt
net: "models/Parse27/train_val.prototxt"test_iter: 1000test_interval: 1000base_lr: 0.01lr_policy: "step"gamma: 0.1stepsize: 100000display: 20max_iter: 450000momentum: 0.9weight_decay: 0.0005snapshot: 10000snapshot_prefix: "models/Parse27/Parse27_train"solver_mode: GPU我在实现这个架构时遇到了两个主要困难。
-
如上所述，我的模型不包括自定义损失层。我的模型几乎是caffeNet架构。但我应该用自定义损失层（绿色框）替换最后一个层（红色框内）。
-
我的训练数据集具有以下结构。
crops Dataset {27482, 3, 128, 192}labels Dataset {27482, 12}mean Dataset {3, 128, 192}pids Dataset {27482}
如上所示，crops和labels中的行数（示例）相同，为27482。然而，我的标签数据集有12列。而我的模型在只有一个标签时可以工作。我如何让它训练所有标签？
我的Train_val.prototxt中的模型目前看起来像这样：
任何帮助或建议将不胜感激。
回答：
