In [1]:
from __future__ import print_function, division
import torch
import torch.nn as nn
import torch.optim as optim
from torch.autograd import Variable
import numpy as np
import torchvision
from torchvision import datasets, models, transforms
import matplotlib.pyplot as plt
import time
import copy
import os
import torch.utils.data as Data
plt.ion()

In [3]:
torch.manual_seed(1)    # reproducible

# Hyper Parameters
EPOCH = 4               # train the training data n times, to save time, we just train 1 epoch
BATCH_SIZE = 10
LR = 0.001

In [4]:
data_transforms = {
    'train': transforms.Compose([
        transforms.RandomSizedCrop(224),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
    'val': transforms.Compose([
        transforms.Scale(224),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
}

data_dir = 'D:/DATA/hymenoptera_data'
dsets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x])
         for x in ['train', 'val']}
dset_loaders = {x: torch.utils.data.DataLoader(dsets[x], batch_size=BATCH_SIZE,
                                               shuffle=True, num_workers=4)
                for x in ['train', 'val']}
dset_sizes = {x: len(dsets[x]) for x in ['train', 'val']}
dset_classes = dsets['train'].classes

test_x,test_y = next(iter(dset_loaders['val']))
test_x = Variable(test_x)

use_gpu = torch.cuda.is_available()

In [5]:
print(len(dsets['train']))
print(len(dsets['val']))


244
153

In [6]:
def imshow(inp, title=None):
    """Imshow for Tensor."""
    inp = inp.numpy().transpose((1, 2, 0))
    mean = np.array([0.485, 0.456, 0.406])
    std = np.array([0.229, 0.224, 0.225])
    inp = std * inp + mean
    plt.imshow(inp)
    if title is not None:
        plt.title(title)
    plt.pause(0.001)  # pause a bit so that plots are updated


# Get a batch of training data
inputs, classes = next(iter(dset_loaders['train']))

# Make a grid from batch
out = torchvision.utils.make_grid(inputs)

imshow(out, title=[dset_classes[x] for x in classes])



In [12]:
class AlexNet(nn.Module):

    def __init__(self, num_classes=2):
        super(AlexNet, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=11, stride=4, padding=2),#input channel = 3
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.Conv2d(64, 192, kernel_size=5, padding=2),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.Conv2d(192, 384, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(384, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(256, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
        )
        self.classifier = nn.Sequential(
            nn.Dropout(),
            nn.Linear(256 * 6 * 6, 4096),
            nn.ReLU(inplace=True),
            nn.Dropout(),
            nn.Linear(4096, 4096),
            nn.ReLU(inplace=True),
            nn.Linear(4096, num_classes),
        )

    def forward(self, x):
        x = self.features(x)
        x = x.view(x.size(0), 256 * 6 * 6)
        x = self.classifier(x)
        return x

In [13]:
def train():
    
    Alex_net = AlexNet()
    print(Alex_net)  # net architecture

    optimizer = torch.optim.Adam(Alex_net.parameters(), lr=LR)   # optimize all cnn parameters
    loss_func = nn.CrossEntropyLoss()                       # the target label is not one-hotted

    # following function (plot_with_labels) is for visualization, can be ignored if not interested

    # training and testing
    for epoch in range(EPOCH):
        for step, (x, y) in enumerate(dset_loaders['train']):   # gives batch data, normalize x when iterate train_loader
            b_x = Variable(x)   # batch x
            b_y = Variable(y)   # batch y

            output = Alex_net(b_x)              # cnn output
            loss = loss_func(output, b_y)   # cross entropy loss
            optimizer.zero_grad()           # clear gradients for this training step
            loss.backward()                 # backpropagation, compute gradients
            optimizer.step()                # apply gradients

            if step % 50 == 0:
                test_output = Alex_net(test_x)
                pred_y = torch.max(test_output, 1)[1].data.squeeze()
                accuracy = sum(pred_y == test_y) / float(test_y.size(0))
                print('Epoch: ', epoch, '/', step, '| train loss: %.4f' % loss.data[0], '| test accuracy: %.2f' % accuracy)


    # print 10 predictions from test data
    test_output = Alex_net(test_x[:20])
    pred_y = torch.max(test_output, 1)[1].data.numpy().squeeze()
    print(pred_y, 'prediction number')
    print(test_y[:20].numpy(), 'real number')

In [14]:
train()


AlexNet (
  (features): Sequential (
    (0): Conv2d(3, 64, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2))
    (1): ReLU (inplace)
    (2): MaxPool2d (size=(3, 3), stride=(2, 2), dilation=(1, 1))
    (3): Conv2d(64, 192, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
    (4): ReLU (inplace)
    (5): MaxPool2d (size=(3, 3), stride=(2, 2), dilation=(1, 1))
    (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 (size=(3, 3), stride=(2, 2), dilation=(1, 1))
  )
  (classifier): Sequential (
    (0): Dropout (p = 0.5)
    (1): Linear (9216 -> 4096)
    (2): ReLU (inplace)
    (3): Dropout (p = 0.5)
    (4): Linear (4096 -> 4096)
    (5): ReLU (inplace)
    (6): Linear (4096 -> 2)
  )
)
Epoch:  0 / 0 | train loss: 0.6931 | test accuracy: 0.60
Epoch:  1 / 0 | train loss: 0.6827 | test accuracy: 0.80
Epoch:  2 / 0 | train loss: 0.6877 | test accuracy: 0.30
Epoch:  3 / 0 | train loss: 0.6932 | test accuracy: 0.30
[0 0 0 0 0 0 0 0 0 0] prediction number
[1 1 1 1 0 1 0 1 1 0] real number

In [ ]: