Back ArrowExplore all kits

How to load pretrained model using pytorch

share link

by shivanisanju03 dot icon Updated: Feb 3, 2023

technology logo
technology logo

Solution Kit Solution Kit  

In this kit we are going to see how to load pretrained model using pytorch. A pre-trained model is a model created by some one else to solve a similar problem. Instead of building a model from scratch to solve a similar problem, you use the model trained on other problem as a starting point. To load a pretrained model for example torch.nn: Loads a model’s parameter dictionary.


Please check the below code to know how to load pretrained model using pytorch,


Fig: Preview of the output that you will get on running this code from your IDE

Code

In this solution we're using pytorch library

loading pretrained model in pytorch

Lines of Code : 46dotLicense : Strong Copyleft (CC BY-SA 4.0)

Dependent Libraries : 
import torch
import torch.nn as nn


class Model(nn.Module):

    def __init__(self):
        super(Model, self).__init__()

        vocab_size = 10000
        embed_size = 100
        # word embedding layer
        self._word_embedding = nn.Embedding(vocab_size, embed_size)
        # linear transformation layers (no bias)
        self._projection = nn.ModuleList([nn.Linear(100, 50, bias=False)
                                          for i in range(2)])
        # linear transformation layers (no bias)
        self._classification = nn.ModuleList([nn.Linear(50, 50, bias=False)
                                              for i in range(4)])

    def forward(self):
        return


model = Model()
checkpoint = {
    'model': model.state_dict()  # OrderedDict
}

# _word_embedding.weight --> torch.Size([10000, 100])
# _projection.0.weight --> torch.Size([50, 100])
# _projection.1.weight --> torch.Size([50, 100])
# _classification.0.weight --> torch.Size([50, 50])
# _classification.1.weight --> torch.Size([50, 50])
# _classification.2.weight --> torch.Size([50, 50])
# _classification.3.weight --> torch.Size([50, 50])

for name, param in checkpoint['model'].items():
    print(name, '-->', param.size()) # see above

# similarly, we can print as follows
print(checkpoint["model"]["_word_embedding.weight"].size(0)) # 10000
print(checkpoint["model"]["_word_embedding.weight"].size(1)) # 100
print(checkpoint["model"]["_projection.0.weight"].size(0)) # 50
print(checkpoint["model"]["_classification.0.weight"].size(0)) # 50

Instructions

Follow the steps carefully to get the output easily.

  1. Install pytorch on your IDE(Any of your favorite IDE).
  2. Copy the snippet using the 'copy' and paste it in your IDE.
  3. Run the file to generate the output.


I hope you found this useful. I have added the link to dependent library, version information in the following sections.


I found this code snippet by searching for ' loading pretrained model using pytorch' in kandi. You can try any such use case!

Environment tested

I tested this solution in the following versions. Be mindful of changes when working with other versions.

  1. The solution is created in Jupyter notebook 6.5.2.
  2. The solution is tested on Python 3.8.10.
  3. Pytorch version 1.0.2.


Using this solution, we are able to understand how to load pretrained model using pytorch with simple steps. This process also facilities an easy way to use, hassle-free method to create a hands-on working version of code which would help us how to load pretrained model using pytorch

Dependent Library

torch-lightby ne7ermore

Python doticonstar image 458 doticonVersion:Currentdoticon
License: Permissive (MIT)

Deep-learning by using Pytorch. Basic nns like Logistic, CNN, RNN, LSTM and some examples are implemented by complex model.

Support
    Quality
      Security
        License
          Reuse

            torch-lightby ne7ermore

            Python doticon star image 458 doticonVersion:Currentdoticon License: Permissive (MIT)

            Deep-learning by using Pytorch. Basic nns like Logistic, CNN, RNN, LSTM and some examples are implemented by complex model.
            Support
              Quality
                Security
                  License
                    Reuse

                      pytorch-tutorialby yunjey

                      Python doticonstar image 26754 doticonVersion:Currentdoticon
                      License: Permissive (MIT)

                      PyTorch Tutorial for Deep Learning Researchers

                      Support
                        Quality
                          Security
                            License
                              Reuse

                                pytorch-tutorialby yunjey

                                Python doticon star image 26754 doticonVersion:Currentdoticon License: Permissive (MIT)

                                PyTorch Tutorial for Deep Learning Researchers
                                Support
                                  Quality
                                    Security
                                      License
                                        Reuse

                                          You can also search for any dependent libraries on kandi like 'pytorch' and 'torch.nn'

                                          Support

                                          1. For any support on kandi solution kits, please use the chat
                                          2. For further learning resources, visit the Open Weaver Community learning page.


                                          See similar Kits and Libraries

                                          Open Weaver – Develop Applications Faster with Open Source

                                          kandi

                                          Community and Support

                                          Company

                                          Follow

                                          • © 2023 Open Weaver Inc.