Convolution and Deconvolution Image with Filter2019 Community Moderator ElectionHow do subsequent convolution layers work?Stuck on deconvolution in Theano and TensorFlowImage Classification, Convolution Network and Gamma Correction for imagesHow are weights represented in a convolution neural network?Relation between convolution in math and CNNWhat is the difference between Dilated Convolution and Deconvolution?Deconvolution vs Sub-pixel ConvolutionAdding bias in deconvolution (transposed convolution) layerunderstanding the filter function in convolution neural networkWhat is the motivation for row-wise convolution and folding in Kalchbrenner et al. (2014)?

Can a virus destroy the BIOS of a modern computer?

How to blend text to background so it looks burned in paint.net?

Why "Having chlorophyll without photosynthesis is actually very dangerous" and "like living with a bomb"?

How would I stat a creature to be immune to everything but the Magic Missile spell? (just for fun)

Why do bosons tend to occupy the same state?

Why is this clock signal connected to a capacitor to gnd?

table going outside the page

How badly should I try to prevent a user from XSSing themselves?

Where does SFDX store details about scratch orgs?

Why is the ratio of two extensive quantities always intensive?

I would say: "You are another teacher", but she is a woman and I am a man

Why is consensus so controversial in Britain?

What exploit are these user agents trying to use?

Forgetting the musical notes while performing in concert

Blender 2.8 I can't see vertices, edges or faces in edit mode

Aircraft with solar-panels?

If human space travel is limited by the G force vulnerability, is there a way to counter G forces?

A category-like structure without composition?

Why can't we play rap on piano?

How can saying a song's name be a copyright violation?

numexpr behavior in math mode and/or TikZ

How do I deal with an unproductive colleague in a small company?

Why is it a bad idea to hire a hitman to eliminate most corrupt politicians?

Saudi Arabia Transit Visa



Convolution and Deconvolution Image with Filter



2019 Community Moderator ElectionHow do subsequent convolution layers work?Stuck on deconvolution in Theano and TensorFlowImage Classification, Convolution Network and Gamma Correction for imagesHow are weights represented in a convolution neural network?Relation between convolution in math and CNNWhat is the difference between Dilated Convolution and Deconvolution?Deconvolution vs Sub-pixel ConvolutionAdding bias in deconvolution (transposed convolution) layerunderstanding the filter function in convolution neural networkWhat is the motivation for row-wise convolution and folding in Kalchbrenner et al. (2014)?










0












$begingroup$


I tried deconvolving the result of the convolution of an image 100x100x3 (hight, width, number of channels) with filter 3x3x3x5 (filter hight, filter width, number of channels, number of filters) then add a bias 1x1x1x5. The convolution works very well but the deconvolution doesn't work.
Can anyone help explain more about deconvolution with numpy.



Here is my code:



def conv(img, W, b, s, p): 
"""
calculate the convolving betwen image and filter und save the result in array (feature_map)

Argument:
img-- input Image, list of array with shape (h, w, number_of_channels)
W-- Filter, array of shape (f, f, number_of_channels, c)
b-- Bias, a vector of the shape (1, 1, 1, c)
s-- Stride
p-- Padding

Returns:
feature_map -- the result of convolving betwenn image and filter, an array of the shape (m, new_h, new_w, c)

"""
#Image dimensions
(h, w, number_of_channels) = img.shape

#Filter dimensions
(f, f, number_of_channels, c) = W.shape

# Compute the dimensions of the CONV output volume using the formula given above. Hint: use int() to floor. (≈2 lines)
n_h = int((h - f + 2 * p) / s) + 1
n_w = int((w - f + 2 * p) / s) + 1

#create initial feature map
feature_map = np.zeros((n_h, n_w, c))

#add Padding to the input
img_pad = np.pad(img, ((p,p),(p,p), (0,0)) , 'constant', constant_values = 0)

#loop over the vertical of the output
for h_i in range (n_h):

#loop over the horizontal of the output
for w_i in range (n_w):

#loop over the Filter layers (output channels)
for c_i in range(c):

#defin the image region, that will convoliving with the filter
img_region = img_pad[h_i*s:h_i*s + f,w_i*s:w_i*s + f, :]
# convolve the image_region with the filter W and bias b to get the feature map
feature_map[h_i, w_i, c_i] = conv_opertation(img_region, W[...,c_i], b[...,c_i])

#activation function Relu
#return the original value in the feature map if it is larger than 0
feature_map[h_i, w_i, c_i] = np.max([feature_map[h_i, w_i, c_i], 0])

assert(feature_map.shape == (n_h, n_w, c))

return feature_map

def deConv (feature_map, W, b, s, p):
'''
calculate the decovolution between the feature map and the filter

Arguements:
feature_map-- the result of convolving the image and the filter W, array of the shape (new_h, new_w, c)
W-- filter, an array of the shape (f, f, number_of_channels, c)
b-- Bias, a vector of the shape (1, 1, 1, c)
s-- Stird
p-- Padding

Returns:
new_img-- reconstruktion image, an array of the shape (h, w, number of channels)

'''
#dimensions of the filter
(f, f, number_of_channels, c) = W.shape

#add Padding to the filter
feature_map_pad = np.pad(feature_map, ((p,p),(p,p), (0,0)) , 'constant', constant_values = 0)

#dimensions of the feature map
(n_h, n_w, c) = feature_map_pad.shape

#dimenstions of the new image
new_h= int((n_h - f + 2 * p)/s)-1
new_w= int((n_w - f + 2 * p)/s)-1

#create initial new image
image = np.zeros((new_h, new_w, number_of_channels))

#loop over the vertical axis of the filter
for h_i in range(new_h):
#loop over the vertical axis of the filter
for w_i in range(new_w):
#loop over the filter channels
for c_i in range(c):

#defin the feature map region, that will convoliving with the filter
feature_map_region = feature_map_pad[h_i*s:h_i*s+f, w_i*s:w_i*s+f,c_i]

#loop over the feature map layer
for i in range(number_of_channels):
# convolve the the feature map region with the filter W and bias b to get image
image[h_i, w_i, i] = conv_opertation(feature_map_region, W[:,:,i,c_i], b[:,:,0,c_i])

#activation function Relu
#return the original value in the feature map if it is larger than 0
image[h_i, w_i, c_i] = np.max([image[h_i,w_i,c_i], 0])

assert(image.shape == (new_h,new_w, number_of_channels))

return image









share|improve this question











$endgroup$
















    0












    $begingroup$


    I tried deconvolving the result of the convolution of an image 100x100x3 (hight, width, number of channels) with filter 3x3x3x5 (filter hight, filter width, number of channels, number of filters) then add a bias 1x1x1x5. The convolution works very well but the deconvolution doesn't work.
    Can anyone help explain more about deconvolution with numpy.



    Here is my code:



    def conv(img, W, b, s, p): 
    """
    calculate the convolving betwen image and filter und save the result in array (feature_map)

    Argument:
    img-- input Image, list of array with shape (h, w, number_of_channels)
    W-- Filter, array of shape (f, f, number_of_channels, c)
    b-- Bias, a vector of the shape (1, 1, 1, c)
    s-- Stride
    p-- Padding

    Returns:
    feature_map -- the result of convolving betwenn image and filter, an array of the shape (m, new_h, new_w, c)

    """
    #Image dimensions
    (h, w, number_of_channels) = img.shape

    #Filter dimensions
    (f, f, number_of_channels, c) = W.shape

    # Compute the dimensions of the CONV output volume using the formula given above. Hint: use int() to floor. (≈2 lines)
    n_h = int((h - f + 2 * p) / s) + 1
    n_w = int((w - f + 2 * p) / s) + 1

    #create initial feature map
    feature_map = np.zeros((n_h, n_w, c))

    #add Padding to the input
    img_pad = np.pad(img, ((p,p),(p,p), (0,0)) , 'constant', constant_values = 0)

    #loop over the vertical of the output
    for h_i in range (n_h):

    #loop over the horizontal of the output
    for w_i in range (n_w):

    #loop over the Filter layers (output channels)
    for c_i in range(c):

    #defin the image region, that will convoliving with the filter
    img_region = img_pad[h_i*s:h_i*s + f,w_i*s:w_i*s + f, :]
    # convolve the image_region with the filter W and bias b to get the feature map
    feature_map[h_i, w_i, c_i] = conv_opertation(img_region, W[...,c_i], b[...,c_i])

    #activation function Relu
    #return the original value in the feature map if it is larger than 0
    feature_map[h_i, w_i, c_i] = np.max([feature_map[h_i, w_i, c_i], 0])

    assert(feature_map.shape == (n_h, n_w, c))

    return feature_map

    def deConv (feature_map, W, b, s, p):
    '''
    calculate the decovolution between the feature map and the filter

    Arguements:
    feature_map-- the result of convolving the image and the filter W, array of the shape (new_h, new_w, c)
    W-- filter, an array of the shape (f, f, number_of_channels, c)
    b-- Bias, a vector of the shape (1, 1, 1, c)
    s-- Stird
    p-- Padding

    Returns:
    new_img-- reconstruktion image, an array of the shape (h, w, number of channels)

    '''
    #dimensions of the filter
    (f, f, number_of_channels, c) = W.shape

    #add Padding to the filter
    feature_map_pad = np.pad(feature_map, ((p,p),(p,p), (0,0)) , 'constant', constant_values = 0)

    #dimensions of the feature map
    (n_h, n_w, c) = feature_map_pad.shape

    #dimenstions of the new image
    new_h= int((n_h - f + 2 * p)/s)-1
    new_w= int((n_w - f + 2 * p)/s)-1

    #create initial new image
    image = np.zeros((new_h, new_w, number_of_channels))

    #loop over the vertical axis of the filter
    for h_i in range(new_h):
    #loop over the vertical axis of the filter
    for w_i in range(new_w):
    #loop over the filter channels
    for c_i in range(c):

    #defin the feature map region, that will convoliving with the filter
    feature_map_region = feature_map_pad[h_i*s:h_i*s+f, w_i*s:w_i*s+f,c_i]

    #loop over the feature map layer
    for i in range(number_of_channels):
    # convolve the the feature map region with the filter W and bias b to get image
    image[h_i, w_i, i] = conv_opertation(feature_map_region, W[:,:,i,c_i], b[:,:,0,c_i])

    #activation function Relu
    #return the original value in the feature map if it is larger than 0
    image[h_i, w_i, c_i] = np.max([image[h_i,w_i,c_i], 0])

    assert(image.shape == (new_h,new_w, number_of_channels))

    return image









    share|improve this question











    $endgroup$














      0












      0








      0





      $begingroup$


      I tried deconvolving the result of the convolution of an image 100x100x3 (hight, width, number of channels) with filter 3x3x3x5 (filter hight, filter width, number of channels, number of filters) then add a bias 1x1x1x5. The convolution works very well but the deconvolution doesn't work.
      Can anyone help explain more about deconvolution with numpy.



      Here is my code:



      def conv(img, W, b, s, p): 
      """
      calculate the convolving betwen image and filter und save the result in array (feature_map)

      Argument:
      img-- input Image, list of array with shape (h, w, number_of_channels)
      W-- Filter, array of shape (f, f, number_of_channels, c)
      b-- Bias, a vector of the shape (1, 1, 1, c)
      s-- Stride
      p-- Padding

      Returns:
      feature_map -- the result of convolving betwenn image and filter, an array of the shape (m, new_h, new_w, c)

      """
      #Image dimensions
      (h, w, number_of_channels) = img.shape

      #Filter dimensions
      (f, f, number_of_channels, c) = W.shape

      # Compute the dimensions of the CONV output volume using the formula given above. Hint: use int() to floor. (≈2 lines)
      n_h = int((h - f + 2 * p) / s) + 1
      n_w = int((w - f + 2 * p) / s) + 1

      #create initial feature map
      feature_map = np.zeros((n_h, n_w, c))

      #add Padding to the input
      img_pad = np.pad(img, ((p,p),(p,p), (0,0)) , 'constant', constant_values = 0)

      #loop over the vertical of the output
      for h_i in range (n_h):

      #loop over the horizontal of the output
      for w_i in range (n_w):

      #loop over the Filter layers (output channels)
      for c_i in range(c):

      #defin the image region, that will convoliving with the filter
      img_region = img_pad[h_i*s:h_i*s + f,w_i*s:w_i*s + f, :]
      # convolve the image_region with the filter W and bias b to get the feature map
      feature_map[h_i, w_i, c_i] = conv_opertation(img_region, W[...,c_i], b[...,c_i])

      #activation function Relu
      #return the original value in the feature map if it is larger than 0
      feature_map[h_i, w_i, c_i] = np.max([feature_map[h_i, w_i, c_i], 0])

      assert(feature_map.shape == (n_h, n_w, c))

      return feature_map

      def deConv (feature_map, W, b, s, p):
      '''
      calculate the decovolution between the feature map and the filter

      Arguements:
      feature_map-- the result of convolving the image and the filter W, array of the shape (new_h, new_w, c)
      W-- filter, an array of the shape (f, f, number_of_channels, c)
      b-- Bias, a vector of the shape (1, 1, 1, c)
      s-- Stird
      p-- Padding

      Returns:
      new_img-- reconstruktion image, an array of the shape (h, w, number of channels)

      '''
      #dimensions of the filter
      (f, f, number_of_channels, c) = W.shape

      #add Padding to the filter
      feature_map_pad = np.pad(feature_map, ((p,p),(p,p), (0,0)) , 'constant', constant_values = 0)

      #dimensions of the feature map
      (n_h, n_w, c) = feature_map_pad.shape

      #dimenstions of the new image
      new_h= int((n_h - f + 2 * p)/s)-1
      new_w= int((n_w - f + 2 * p)/s)-1

      #create initial new image
      image = np.zeros((new_h, new_w, number_of_channels))

      #loop over the vertical axis of the filter
      for h_i in range(new_h):
      #loop over the vertical axis of the filter
      for w_i in range(new_w):
      #loop over the filter channels
      for c_i in range(c):

      #defin the feature map region, that will convoliving with the filter
      feature_map_region = feature_map_pad[h_i*s:h_i*s+f, w_i*s:w_i*s+f,c_i]

      #loop over the feature map layer
      for i in range(number_of_channels):
      # convolve the the feature map region with the filter W and bias b to get image
      image[h_i, w_i, i] = conv_opertation(feature_map_region, W[:,:,i,c_i], b[:,:,0,c_i])

      #activation function Relu
      #return the original value in the feature map if it is larger than 0
      image[h_i, w_i, c_i] = np.max([image[h_i,w_i,c_i], 0])

      assert(image.shape == (new_h,new_w, number_of_channels))

      return image









      share|improve this question











      $endgroup$




      I tried deconvolving the result of the convolution of an image 100x100x3 (hight, width, number of channels) with filter 3x3x3x5 (filter hight, filter width, number of channels, number of filters) then add a bias 1x1x1x5. The convolution works very well but the deconvolution doesn't work.
      Can anyone help explain more about deconvolution with numpy.



      Here is my code:



      def conv(img, W, b, s, p): 
      """
      calculate the convolving betwen image and filter und save the result in array (feature_map)

      Argument:
      img-- input Image, list of array with shape (h, w, number_of_channels)
      W-- Filter, array of shape (f, f, number_of_channels, c)
      b-- Bias, a vector of the shape (1, 1, 1, c)
      s-- Stride
      p-- Padding

      Returns:
      feature_map -- the result of convolving betwenn image and filter, an array of the shape (m, new_h, new_w, c)

      """
      #Image dimensions
      (h, w, number_of_channels) = img.shape

      #Filter dimensions
      (f, f, number_of_channels, c) = W.shape

      # Compute the dimensions of the CONV output volume using the formula given above. Hint: use int() to floor. (≈2 lines)
      n_h = int((h - f + 2 * p) / s) + 1
      n_w = int((w - f + 2 * p) / s) + 1

      #create initial feature map
      feature_map = np.zeros((n_h, n_w, c))

      #add Padding to the input
      img_pad = np.pad(img, ((p,p),(p,p), (0,0)) , 'constant', constant_values = 0)

      #loop over the vertical of the output
      for h_i in range (n_h):

      #loop over the horizontal of the output
      for w_i in range (n_w):

      #loop over the Filter layers (output channels)
      for c_i in range(c):

      #defin the image region, that will convoliving with the filter
      img_region = img_pad[h_i*s:h_i*s + f,w_i*s:w_i*s + f, :]
      # convolve the image_region with the filter W and bias b to get the feature map
      feature_map[h_i, w_i, c_i] = conv_opertation(img_region, W[...,c_i], b[...,c_i])

      #activation function Relu
      #return the original value in the feature map if it is larger than 0
      feature_map[h_i, w_i, c_i] = np.max([feature_map[h_i, w_i, c_i], 0])

      assert(feature_map.shape == (n_h, n_w, c))

      return feature_map

      def deConv (feature_map, W, b, s, p):
      '''
      calculate the decovolution between the feature map and the filter

      Arguements:
      feature_map-- the result of convolving the image and the filter W, array of the shape (new_h, new_w, c)
      W-- filter, an array of the shape (f, f, number_of_channels, c)
      b-- Bias, a vector of the shape (1, 1, 1, c)
      s-- Stird
      p-- Padding

      Returns:
      new_img-- reconstruktion image, an array of the shape (h, w, number of channels)

      '''
      #dimensions of the filter
      (f, f, number_of_channels, c) = W.shape

      #add Padding to the filter
      feature_map_pad = np.pad(feature_map, ((p,p),(p,p), (0,0)) , 'constant', constant_values = 0)

      #dimensions of the feature map
      (n_h, n_w, c) = feature_map_pad.shape

      #dimenstions of the new image
      new_h= int((n_h - f + 2 * p)/s)-1
      new_w= int((n_w - f + 2 * p)/s)-1

      #create initial new image
      image = np.zeros((new_h, new_w, number_of_channels))

      #loop over the vertical axis of the filter
      for h_i in range(new_h):
      #loop over the vertical axis of the filter
      for w_i in range(new_w):
      #loop over the filter channels
      for c_i in range(c):

      #defin the feature map region, that will convoliving with the filter
      feature_map_region = feature_map_pad[h_i*s:h_i*s+f, w_i*s:w_i*s+f,c_i]

      #loop over the feature map layer
      for i in range(number_of_channels):
      # convolve the the feature map region with the filter W and bias b to get image
      image[h_i, w_i, i] = conv_opertation(feature_map_region, W[:,:,i,c_i], b[:,:,0,c_i])

      #activation function Relu
      #return the original value in the feature map if it is larger than 0
      image[h_i, w_i, c_i] = np.max([image[h_i,w_i,c_i], 0])

      assert(image.shape == (new_h,new_w, number_of_channels))

      return image






      python neural-network convolution autoencoder numpy






      share|improve this question















      share|improve this question













      share|improve this question




      share|improve this question








      edited Mar 27 at 3:24









      Shamit Verma

      1,3191214




      1,3191214










      asked Mar 26 at 14:10









      Edward AlhanounEdward Alhanoun

      12




      12




















          0






          active

          oldest

          votes












          Your Answer





          StackExchange.ifUsing("editor", function ()
          return StackExchange.using("mathjaxEditing", function ()
          StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix)
          StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
          );
          );
          , "mathjax-editing");

          StackExchange.ready(function()
          var channelOptions =
          tags: "".split(" "),
          id: "557"
          ;
          initTagRenderer("".split(" "), "".split(" "), channelOptions);

          StackExchange.using("externalEditor", function()
          // Have to fire editor after snippets, if snippets enabled
          if (StackExchange.settings.snippets.snippetsEnabled)
          StackExchange.using("snippets", function()
          createEditor();
          );

          else
          createEditor();

          );

          function createEditor()
          StackExchange.prepareEditor(
          heartbeatType: 'answer',
          autoActivateHeartbeat: false,
          convertImagesToLinks: false,
          noModals: true,
          showLowRepImageUploadWarning: true,
          reputationToPostImages: null,
          bindNavPrevention: true,
          postfix: "",
          imageUploader:
          brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
          contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
          allowUrls: true
          ,
          onDemand: true,
          discardSelector: ".discard-answer"
          ,immediatelyShowMarkdownHelp:true
          );



          );













          draft saved

          draft discarded


















          StackExchange.ready(
          function ()
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f48028%2fconvolution-and-deconvolution-image-with-filter%23new-answer', 'question_page');

          );

          Post as a guest















          Required, but never shown

























          0






          active

          oldest

          votes








          0






          active

          oldest

          votes









          active

          oldest

          votes






          active

          oldest

          votes















          draft saved

          draft discarded
















































          Thanks for contributing an answer to Data Science Stack Exchange!


          • Please be sure to answer the question. Provide details and share your research!

          But avoid


          • Asking for help, clarification, or responding to other answers.

          • Making statements based on opinion; back them up with references or personal experience.

          Use MathJax to format equations. MathJax reference.


          To learn more, see our tips on writing great answers.




          draft saved


          draft discarded














          StackExchange.ready(
          function ()
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f48028%2fconvolution-and-deconvolution-image-with-filter%23new-answer', 'question_page');

          );

          Post as a guest















          Required, but never shown





















































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown

































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown







          Popular posts from this blog

          Adding axes to figuresAdding axes labels to LaTeX figuresLaTeX equivalent of ConTeXt buffersRotate a node but not its content: the case of the ellipse decorationHow to define the default vertical distance between nodes?TikZ scaling graphic and adjust node position and keep font sizeNumerical conditional within tikz keys?adding axes to shapesAlign axes across subfiguresAdding figures with a certain orderLine up nested tikz enviroments or how to get rid of themAdding axes labels to LaTeX figures

          Tähtien Talli Jäsenet | Lähteet | NavigointivalikkoSuomen Hippos – Tähtien Talli

          Do these cracks on my tires look bad? The Next CEO of Stack OverflowDry rot tire should I replace?Having to replace tiresFishtailed so easily? Bad tires? ABS?Filling the tires with something other than air, to avoid puncture hassles?Used Michelin tires safe to install?Do these tyre cracks necessitate replacement?Rumbling noise: tires or mechanicalIs it possible to fix noisy feathered tires?Are bad winter tires still better than summer tires in winter?Torque converter failure - Related to replacing only 2 tires?Why use snow tires on all 4 wheels on 2-wheel-drive cars?