理解 Torch 并在 tensorflow 上实现答案

【问题标题】：Understanding torch and implement on tensorflow理解 Torch 并在 tensorflow 上实现
【发布时间】：2019-02-22 00:30:36
【问题描述】：

我正在实现 LBCNN 的 TensorFlow 版本，代码如下：https://github.com/juefeix/lbcnn.torch。这里的问题是，当我尝试在 tensorflow 中重写时，成本函数保持高位且波动。即使我调试了所有东西，我也陷入了两周的困境，我仍然不知道我错在哪里。

手电筒代码：

-- resnet.lua

local function createModel(opt)
   local function basicblock(nChIn,nChOut,sz)
     local s = nn.Sequential()
     local shareConv = Convolution(nChIn,nChOut,sz,sz,1,
                       1,(sz-1)/2,(sz-1)/2)
     s:add(SBatchNorm(nChIn))      
     s:add(shareConv)
     s:add(ReLU())
     s:add(Convolution(nChOut,nChIn,1,1))
     local identity = nn.Identity()
     local output= nn.Sequential(): add(nn.ConcatTable() 
         :add(s):add(identity)):add(nn.CAddTable(true))
     return output
   end

   local sz = opt.convSize
   local nInputPlane = opt.nInputPlane
   local nChIn = opt.numChannels
   local nChOut = opt.numWeights

   -- define model to train
   model = nn.Sequential()
   model:add(Convolution(nInputPlane,nChIn,sz,sz,1,1,1,1))
   model:add(SBatchNorm(nChIn))
   model:add(ReLU(true))

   for stages = 1,opt.depth do
      model:add(basicblock(nChIn,nChOut,sz))
    end
   model:add(Avg(5,5,5,5))

   -- stage 3 : standard 2-layer neural network
   model:add(nn.Reshape(nChIn*opt.view))
   model:add(nn.Dropout(0.5))
   model:add(nn.Linear(nChIn*opt.view, 
   math.max(opt.nClasses,opt.full)))
   model:add(cudnn.ReLU())
   model:add(nn.Dropout(0.5))

   model: add(nn.Linear (math.max(opt.full,opt.nClasses), opt.nClasses))
   model:cuda()

   return model
end

return createModel

张量流代码：

def cnn(prev_input, lbc_size, lbc_channels, output_channels):

   shortcut = tf.identity(prev_input)
   B = tf.contrib.layers.batch_norm(prev_input)

   Z = tf.contrib.layers.conv2d(inputs = B, num_outputs = lbc_channels,
   kernel_size = 3, stride = 1, padding = "SAME", activation_fn = None)

   A1 = tf.nn.relu(Z)

   A2 = tf.contrib.layers.conv2d(inputs = A1, 
        num_outputs=output_channels, 
        kernel_size = 1, stride = 1, 
        padding = "SAME", activation_fn = None)

   A3 = tf.add(A2, shortcut)

   return A3

def model(X, Keep_probability):

  with tf.name_scope("Pre-Conv"):
    X1 = tf.contrib.layers.conv2d(inputs = X, num_outputs = 
          output_channels,kernel_size = lbc_size, stride = 1, 
          padding = "SAME", activation_fn = None)
    X2 = tf.contrib.layers.batch_norm(X1)
    X3 = tf.nn.relu(X2)

  X_in = X3

  for i in range(conv_layers):
    with tf.name_scope("conv"):
       X_out,BB,ZZ,AA,AAA = cnn(X_in, lbc_size, lbc_channels, 
         out_channels)
       X_in = X_out

  with tf.name_scope("AvgPool"):
    Z = tf.nn.avg_pool(value = X_in, ksize = [1, 5, 5, 1], 
       strides = [1, 5, 5, 1], padding = "VALID")

  with tf.name_scope("Flatter"):
    P = tf.contrib.layers.flatten(Z)

  with tf.name_scope("Dropout"):
    F1 = tf.nn.dropout(x = P, keep_prob = 0.5)

  with tf.name_scope("Fully"):
    F2 = tf.contrib.layers.fully_connected(inputs = F1, 
       num_outputs = fc_hidden_units, activation_fn = tf.nn.relu)

  with tf.name_scope("Dropout"):
    F3 = tf.nn.dropout(x = F2, keep_prob = 0.5)

  with tf.name_scope("Fully"):
    F4 = tf.contrib.layers.fully_connected(inputs = F3, 
      num_outputs = output_classes, activation_fn = None)

  return F4

假设所有参数，我都正确传递。我只想问2架构是否相同？还有一件事是他们的代码在我使用 AdamOptimizer 时使用带有动量和 weight_decay 的 SGD，这会有所不同吗？非常感谢。

【问题讨论】：

标签： tensorflow torch

【解决方案1】：

我没有查看您的整个代码来检查它是否确实相同，但是当您将优化器从动量更改为亚当时，收敛的示例通常会有所不同。您还应该需要重新调整超参数以获得良好的性能。

【讨论】：