load and restore.py

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Wed Nov  8 12:12:16 2017

@author: zengliang
"""
import torch
import torchvision
import torch.utils.data as data
import torchvision.transforms as transforms
import torchvision.datasets as dsets
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable
import torch.optim as optim

# Download and construct dataset.
train_dataset = dsets.CIFAR10(root='../data/',
                               train=True, 
                               transform=transforms.ToTensor(),
                               download=True)

# Select one data pair (read data from disk).
image, label = train_dataset[0]
print (image.size())
print (label)

# Data Loader (this provides queue and thread in a very simple way).
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                                           batch_size=100, 
                                           shuffle=True,
                                           num_workers=2)

# When iteration starts, queue and thread start to load dataset from files.
data_iter = iter(train_loader)

# Mini-batch images and labels.
images, labels = data_iter.next()

# Actual usage of data loader is as below.
for images, labels in train_loader:
    # Your training code will be written here
    pass

#---------------------------------------------
#for your own dataset
class CustomDataset(data.Dataset):
    def __init__(self):
        # TODO
        # 1. Initialize file path or list of file names. 
        pass
    def __getitem__(self, index):
        # TODO
        # 1. Read one data from file (e.g. using numpy.fromfile, PIL.Image.open).
        # 2. Preprocess the data (e.g. torchvision.Transform).
        # 3. Return a data pair (e.g. image and label).
        pass
    def __len__(self):
        # You should change 0 to the total size of your dataset.
        return 0 

# Then, you can just use prebuilt torch's data loader. 
custom_dataset = CustomDataset()
train_loader = torch.utils.data.DataLoader(dataset=custom_dataset,
                                           batch_size=100, 
                                           shuffle=True,
                                           num_workers=2)

#--------------------------------------
#use pretrained network
# Download and load pretrained resnet.
resnet = torchvision.models.resnet18(pretrained=True)

# If you want to finetune only top layer of the model.
for param in resnet.parameters():
    param.requires_grad = False
    
# Replace top layer for finetuning.
resnet.fc = nn.Linear(resnet.fc.in_features, 100)  # 100 is for example.

# For test.
images = Variable(torch.randn(10, 3, 256, 256))
outputs = resnet(images)
print (outputs.size())   # (10, 100)

#------------------------
# Save and load the entire model.
torch.save(resnet, 'model.pkl')
model = torch.load('model.pkl')

# Save and load only the model parameters(recommended).
torch.save(resnet.state_dict(), 'params.pkl')
resnet.load_state_dict(torch.load('params.pkl'))