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.
import torch
from torch.autograd import Variable
import matplotlib.pyplot as plt
%matplotlib inline
torch.manual_seed(1) # reproducible
#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)
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
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)
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()
# save net1
save()
# restore entire net (may slow)
restore_net()
# restore only the net parameters
restore_params()