Model summary in pytorch

Question

Is there any way  I can print the summary of a model in PyTorch like model summary   method does in Keras as follows   Model Summary                                                                                                       Layer  type                      Output Shape          Param       Connected to                                                                                                                           input 1  InputLayer               None  1  15  27      0                                                                                                                                                  convolution2d 1  Convolution2D    None  8  15  27      872         input 1 0  0                                                                                                                           maxpooling2d 1  MaxPooling2D      None  8  7  27       0           convolution2d 1 0  0                                                                                                                   flatten 1  Flatten                None  1512           0           maxpooling2d 1 0  0                                                                                                                    dense 1  Dense                    None  1              1513        flatten 1 0  0                                                                                                                         Total params  2 385 Trainable params  2 385 Non-trainable params  0

User · Answer

Simplest to remember  not as pretty as Keras    print model    This also work   repr model    If you just want the number of parameters   sum  param nelement   for param in model parameters       From  Is there similar pytorch function as model summary   as keras   forum PyTorch org

User · Answer

Simply print the model after defining an object for the model class  class RNN nn Module       def   init   self  input dim  embedding dim  hidden dim  output dim           super     init              self embedding   nn Embedding input dim  embedding dim          self rnn   nn RNN embedding dim  hidden dim          self fc   nn Linear hidden dim  output dim      def forward                 model   RNN input dim  embedding dim  hidden dim  output dim  print model

User · Answer

You can just use x shape  in order to measure tensor s x dimensions

User · Answer

While you will not get as detailed information about the model as in Keras  model summary  simply printing the model will give you some idea about the different layers involved and their specifications   For instance   from torchvision import models model   models vgg16   print model    The output in this case would be something as follows   VGG      features   Sequential        0   Conv2d 3  64  kernel size  3  3   stride  1  1   padding  1  1        1   ReLU  inplace       2   Conv2d 64  64  kernel size  3  3   stride  1  1   padding  1  1        3   ReLU  inplace       4   MaxPool2d  size  2  2   stride  2  2   dilation  1  1        5   Conv2d 64  128  kernel size  3  3   stride  1  1   padding  1  1        6   ReLU  inplace       7   Conv2d 128  128  kernel size  3  3   stride  1  1   padding  1  1        8   ReLU  inplace       9   MaxPool2d  size  2  2   stride  2  2   dilation  1  1        10   Conv2d 128  256  kernel size  3  3   stride  1  1   padding  1  1        11   ReLU  inplace       12   Conv2d 256  256  kernel size  3  3   stride  1  1   padding  1  1        13   ReLU  inplace       14   Conv2d 256  256  kernel size  3  3   stride  1  1   padding  1  1        15   ReLU  inplace       16   MaxPool2d  size  2  2   stride  2  2   dilation  1  1        17   Conv2d 256  512  kernel size  3  3   stride  1  1   padding  1  1        18   ReLU  inplace       19   Conv2d 512  512  kernel size  3  3   stride  1  1   padding  1  1        20   ReLU  inplace       21   Conv2d 512  512  kernel size  3  3   stride  1  1   padding  1  1        22   ReLU  inplace       23   MaxPool2d  size  2  2   stride  2  2   dilation  1  1        24   Conv2d 512  512  kernel size  3  3   stride  1  1   padding  1  1        25   ReLU  inplace       26   Conv2d 512  512  kernel size  3  3   stride  1  1   padding  1  1        27   ReLU  inplace       28   Conv2d 512  512  kernel size  3  3   stride  1  1   padding  1  1        29   ReLU  inplace       30   MaxPool2d  size  2  2   stride  2  2   dilation  1  1          classifier   Sequential        0   Dropout  p   0 5       1   Linear  25088 - gt  4096       2   ReLU  inplace       3   Dropout  p   0 5       4   Linear  4096 - gt  4096       5   ReLU  inplace       6   Linear  4096 - gt  1000          Now you could  as mentioned by Kashyap  use the state dict method to get the weights of the different layers  But using this listing of the layers would perhaps provide more direction is creating a helper function to get that Keras like model summary  Hope this helps

User · Answer

Keras like model summary using torchsummary  from torchsummary import summary summary model  input size  3  224  224

User · Answer

AFAK there is no model summary   like equivalent in pytorch  Meanwhile you can refer script by szagoruyko  which gives a nice visualizaton like in resnet18-example  Cheers

User · Answer

Yes  you can get exact Keras representation  using pytorch-summary package   Example for VGG16  from torchvision import models from torchsummary import summary  vgg   models vgg16   summary vgg   3  224  224    ----------------------------------------------------------------         Layer  type                Output Shape         Param                                                                                Conv2d-1          -1  64  224  224            1 792               ReLU-2          -1  64  224  224                0             Conv2d-3          -1  64  224  224           36 928               ReLU-4          -1  64  224  224                0          MaxPool2d-5          -1  64  112  112                0             Conv2d-6         -1  128  112  112           73 856               ReLU-7         -1  128  112  112                0             Conv2d-8         -1  128  112  112          147 584               ReLU-9         -1  128  112  112                0         MaxPool2d-10           -1  128  56  56                0            Conv2d-11           -1  256  56  56          295 168              ReLU-12           -1  256  56  56                0            Conv2d-13           -1  256  56  56          590 080              ReLU-14           -1  256  56  56                0            Conv2d-15           -1  256  56  56          590 080              ReLU-16           -1  256  56  56                0         MaxPool2d-17           -1  256  28  28                0            Conv2d-18           -1  512  28  28        1 180 160              ReLU-19           -1  512  28  28                0            Conv2d-20           -1  512  28  28        2 359 808              ReLU-21           -1  512  28  28                0            Conv2d-22           -1  512  28  28        2 359 808              ReLU-23           -1  512  28  28                0         MaxPool2d-24           -1  512  14  14                0            Conv2d-25           -1  512  14  14        2 359 808              ReLU-26           -1  512  14  14                0            Conv2d-27           -1  512  14  14        2 359 808              ReLU-28           -1  512  14  14                0            Conv2d-29           -1  512  14  14        2 359 808              ReLU-30           -1  512  14  14                0         MaxPool2d-31             -1  512  7  7                0            Linear-32                  -1  4096      102 764 544              ReLU-33                  -1  4096                0           Dropout-34                  -1  4096                0            Linear-35                  -1  4096       16 781 312              ReLU-36                  -1  4096                0           Dropout-37                  -1  4096                0            Linear-38                  -1  1000        4 097 000                                                                  Total params  138 357 544 Trainable params  138 357 544 Non-trainable params  0 ---------------------------------------------------------------- Input size  MB   0 57 Forward backward pass size  MB   218 59 Params size  MB   527 79 Estimated Total Size  MB   746 96 ----------------------------------------------------------------

User · Answer

You can use   from torchsummary import summary   You can specify device  device   torch device  cuda  if torch cuda is available   else  cpu     You can create a Network  and if you are using MNIST datasets  then following commands will work and show you summary  model   Network   to device  summary model  1 28 28

User · Answer

For visualization and summary of PyTorch models  tensorboardX can also can be utilized

User · Answer

This will show a model s weights and parameters  but not output shape    from torch nn modules module import  addindent import torch import numpy as np def torch summarize model  show weights True  show parameters True          Summarizes torch model by showing trainable parameters and weights         tmpstr   model   class     name         n      for key  module in model  modules items              if it contains layers let call it recursively to get params and weights         if type module  in               torch nn modules container Container              torch nn modules container Sequential                        modstr   torch summarize module          else              modstr   module   repr             modstr    addindent modstr  2           params   sum  np prod p size    for p in module parameters             weights   tuple  tuple p size    for p in module parameters              tmpstr            key           modstr          if show weights              tmpstr       weights     format weights          if show parameters              tmpstr        parameters     format params          tmpstr      n          tmpstr   tmpstr           return tmpstr    Test import torchvision models as models model   models alexnet   print torch summarize model        Output   AlexNet        features   Sequential          0   Conv2d 3  64  kernel size  11  11   stride  4  4   padding  2  2    weights   64  3  11  11    64     parameters 23296        1   ReLU  inplace   weights     parameters 0        2   MaxPool2d  size  3  3   stride  2  2   dilation  1  1    weights     parameters 0        3   Conv2d 64  192  kernel size  5  5   stride  1  1   padding  2  2    weights   192  64  5  5    192     parameters 307392        4   ReLU  inplace   weights     parameters 0        5   MaxPool2d  size  3  3   stride  2  2   dilation  1  1    weights     parameters 0        6   Conv2d 192  384  kernel size  3  3   stride  1  1   padding  1  1    weights   384  192  3  3    384     parameters 663936        7   ReLU  inplace   weights     parameters 0        8   Conv2d 384  256  kernel size  3  3   stride  1  1   padding  1  1    weights   256  384  3  3    256     parameters 884992        9   ReLU  inplace   weights     parameters 0        10   Conv2d 256  256  kernel size  3  3   stride  1  1   padding  1  1    weights   256  256  3  3    256     parameters 590080        11   ReLU  inplace   weights     parameters 0        12   MaxPool2d  size  3  3   stride  2  2   dilation  1  1    weights     parameters 0        weights   64  3  11  11    64     192  64  5  5    192     384  192  3  3    384     256  384  3  3    256     256  256  3  3    256     parameters 2469696      classifier   Sequential          0   Dropout  p   0 5   weights     parameters 0        1   Linear  9216 - gt  4096   weights   4096  9216    4096     parameters 37752832        2   ReLU  inplace   weights     parameters 0        3   Dropout  p   0 5   weights     parameters 0        4   Linear  4096 - gt  4096   weights   4096  4096    4096     parameters 16781312        5   ReLU  inplace   weights     parameters 0        6   Linear  4096 - gt  1000   weights   1000  4096    1000     parameters 4097000        weights   4096  9216    4096     4096  4096    4096     1000  4096    1000     parameters 58631144       Edit  isaykatsman has a pytorch PR to add a model summary   that is exactly like keras https   github com pytorch pytorch pull 3043 files

User · Answer

In order to use torchsummary type   from torchsummary import summary   Install it first if you don t have it   pip install torchsummary    And then you can try it  but note from some reason it is not working unless I set model to cuda alexnet cuda   from torchsummary import summary help summary  import torchvision models as models alexnet   models alexnet pretrained False  alexnet cuda   summary alexnet   3  224  224   print alexnet    The summary must take the input size and batch size is set to -1 meaning any batch size we provide   If we set summary alexnet   3  224  224   32  this means use the bs 32   summary model  input size  batch size -1  device  cuda       Out   Help on function summary in module torchsummary torchsummary   summary model  input size  batch size -1  device  cuda    ----------------------------------------------------------------         Layer  type                Output Shape         Param                                                                                Conv2d-1            32  64  55  55           23 296               ReLU-2            32  64  55  55                0          MaxPool2d-3            32  64  27  27                0             Conv2d-4           32  192  27  27          307 392               ReLU-5           32  192  27  27                0          MaxPool2d-6           32  192  13  13                0             Conv2d-7           32  384  13  13          663 936               ReLU-8           32  384  13  13                0             Conv2d-9           32  256  13  13          884 992              ReLU-10           32  256  13  13                0            Conv2d-11           32  256  13  13          590 080              ReLU-12           32  256  13  13                0         MaxPool2d-13             32  256  6  6                0 AdaptiveAvgPool2d-14             32  256  6  6                0           Dropout-15                  32  9216                0            Linear-16                  32  4096       37 752 832              ReLU-17                  32  4096                0           Dropout-18                  32  4096                0            Linear-19                  32  4096       16 781 312              ReLU-20                  32  4096                0            Linear-21                  32  1000        4 097 000                                                                  Total params  61 100 840 Trainable params  61 100 840 Non-trainable params  0 ---------------------------------------------------------------- Input size  MB   18 38 Forward backward pass size  MB   268 12 Params size  MB   233 08 Estimated Total Size  MB   519 58 ---------------------------------------------------------------- AlexNet     features   Sequential       0   Conv2d 3  64  kernel size  11  11   stride  4  4   padding  2  2        1   ReLU inplace       2   MaxPool2d kernel size 3  stride 2  padding 0  dilation 1  ceil mode False       3   Conv2d 64  192  kernel size  5  5   stride  1  1   padding  2  2        4   ReLU inplace       5   MaxPool2d kernel size 3  stride 2  padding 0  dilation 1  ceil mode False       6   Conv2d 192  384  kernel size  3  3   stride  1  1   padding  1  1        7   ReLU inplace       8   Conv2d 384  256  kernel size  3  3   stride  1  1   padding  1  1        9   ReLU inplace       10   Conv2d 256  256  kernel size  3  3   stride  1  1   padding  1  1        11   ReLU inplace       12   MaxPool2d kernel size 3  stride 2  padding 0  dilation 1  ceil mode False         avgpool   AdaptiveAvgPool2d output size  6  6      classifier   Sequential       0   Dropout p 0 5       1   Linear in features 9216  out features 4096  bias True       2   ReLU inplace       3   Dropout p 0 5       4   Linear in features 4096  out features 4096  bias True       5   ReLU inplace       6   Linear in features 4096  out features 1000  bias True

[python] Model summary in pytorch

Examples related to python

Examples related to pytorch