Recipe: How to save and reload a deep learning model in Pytorch?
MACHINE LEARNING RECIPES PYTORCH PYTORCH MODEL

How to save and reload a deep learning model in Pytorch?

This Pytorch recipe provides you a solution for saving and loading Pytorch models - entire models or just the parameters.

This recipe provides options to save and reload an entire model or just the parameters of the model. While reloading this recipe copies the parameter from 1 net to another net. There are 3 main functions involved in saving and loading a model in pytorch.

1. torch.save: This saves a serialized object to disk. It uses python's pickle utility for serialization. Models, tensors and dictionaries can be saved using this function.
2. torch.load: torch.load: Uses pickle's unpickling facilities to deserialize pickled object files to memory. This function also facilitates the device to load the data into.
3. torch.nn.Module.load_state_dict: Loads a model's parameter dictionary using a deserialized state_dict. The learnable parameters (i.e. weights and biases) of an torch.nn.Module model are contained in the model's parameters (accessed with model.parameters()). A state_dict is simply a Python dictionary object that maps each layer to its parameter tensor.

What is PyTorch ?
Pytorch is a Python-based scientific computing package that uses the power of graphics processing units and can replace the numpy library. It is also a very popular deep learning research platform built for flexibility and speed. You can use other Python packages such as NumPy, SciPy to extend PyTorch functionalities.

What is Deep Learning Model ?
Deep learning is a subset of machine learning. Deep learning uses neural networks to make predictions. A neural network takes inputs, which are then processed using hidden layers using weights that are adjusted during training. The model then outputs a prediction.

In [72]:
import torch
from torch.autograd import Variable
import matplotlib.pyplot as plt
%matplotlib inline

torch.manual_seed(1)    # reproducible
Out[72]:
<torch._C.Generator at 0x12214f310>
In [73]:
#sample data
x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim=1)  # x data (tensor), shape=(100, 1)
y = x.pow(2) + 0.2*torch.rand(x.size())  # noisy y data (tensor), shape=(100, 1)
x, y = Variable(x, requires_grad=False), Variable(y, requires_grad=False)
In [74]:
def save():
    # save net1
    net1 = torch.nn.Sequential(
        torch.nn.Linear(1, 10),
        torch.nn.ReLU(),
        torch.nn.Linear(10, 1)
    )
    optimizer = torch.optim.SGD(net1.parameters(), lr=0.5)
    loss_func = torch.nn.MSELoss()

    for t in range(100):
        prediction = net1(x)
        loss = loss_func(prediction, y)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

    # plot result
    plt.figure(1, figsize=(10, 3))
    plt.subplot(131)
    plt.title('Net1')
    plt.scatter(x.data.numpy(), y.data.numpy())
    plt.plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw=5)

    # 2 ways to save the net
    torch.save(net1, 'net.pkl')  # save entire net
    torch.save(net1.state_dict(), 'net_params.pkl')   # save only the parameters
In [75]:
def restore_net():
    # restore entire net1 to net2
    net2 = torch.load('net.pkl')
    prediction = net2(x)

    # plot result
    plt.subplot(132)
    plt.title('Net2')
    plt.scatter(x.data.numpy(), y.data.numpy())
    plt.plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw=5)
In [76]:
def restore_params():
    # restore only the parameters in net1 to net3
    net3 = torch.nn.Sequential(
        torch.nn.Linear(1, 10),
        torch.nn.ReLU(),
        torch.nn.Linear(10, 1)
    )

    # copy net1's parameters into net3
    net3.load_state_dict(torch.load('net_params.pkl'))
    prediction = net3(x)

    # plot result
    plt.subplot(133)
    plt.title('Net3')
    plt.scatter(x.data.numpy(), y.data.numpy())
    plt.plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw=5)
    plt.show()
In [77]:
# save net1
save()
# restore entire net (may slow)
restore_net()
# restore only the net parameters
restore_params()


Stuck at work?
Can't find the recipe you are looking for. Let us know and we will find an expert to create the recipe for you. Click here
Companies using this Recipe
1 developer from eClerx
1 developer from New Delhi DataPoint
1 developer from Altimetrik
1 developer from Greet Labs
1 developer from Tata Communications
1 developer from ANAC
1 developer from KPMG
1 developer from Vodafone
1 developer from BNY Mellon
1 developer from ManageSmart