train/test acc for Transfer Learning

%matplotlib inline
from graphviz import Digraph
import torch
from torch.autograd import Variable


# make_dot was moved to https://github.com/szagoruyko/pytorchviz
from torchviz import make_dot
# -*- coding: utf-8 -*-
"""
Transfer Learning Tutorial
==========================
**Author**: `Sasank Chilamkurthy <https://chsasank.github.io>`_

In this tutorial, you will learn how to train your network using
transfer learning. You can read more about the transfer learning at `cs231n
notes <http://cs231n.github.io/transfer-learning/>`__

Quoting these notes,

    In practice, very few people train an entire Convolutional Network
    from scratch (with random initialization), because it is relatively
    rare to have a dataset of sufficient size. Instead, it is common to
    pretrain a ConvNet on a very large dataset (e.g. ImageNet, which
    contains 1.2 million images with 1000 categories), and then use the
    ConvNet either as an initialization or a fixed feature extractor for
    the task of interest.

These two major transfer learning scenarios look as follows:

-  **Finetuning the convnet**: Instead of random initializaion, we
   initialize the network with a pretrained network, like the one that is
   trained on imagenet 1000 dataset. Rest of the training looks as
   usual.
-  **ConvNet as fixed feature extractor**: Here, we will freeze the weights
   for all of the network except that of the final fully connected
   layer. This last fully connected layer is replaced with a new one
   with random weights and only this layer is trained.

"""
# License: BSD
# Author: Sasank Chilamkurthy

from __future__ import print_function, division

import torch
import torch.nn as nn
import torch.optim as optim
from torch.optim import lr_scheduler
import numpy as np
import torchvision
from torchvision import datasets, models, transforms
import matplotlib.pyplot as plt
import time
import os
import copy

plt.ion()   # interactive mode


######################################################################
# Load Data
# ---------
#
# We will use torchvision and torch.utils.data packages for loading the
# data.
#
# The problem we're going to solve today is to train a model to classify
# **ants** and **bees**. We have about 120 training images each for ants and bees.
# There are 75 validation images for each class. Usually, this is a very
# small dataset to generalize upon, if trained from scratch. Since we
# are using transfer learning, we should be able to generalize reasonably
# well.
#
# This dataset is a very small subset of imagenet.
#
# .. Note ::
#    Download the data from
#    `here <https://download.pytorch.org/tutorial/hymenoptera_data.zip>`_
#    and extract it to the current directory.

# Data augmentation and normalization for training
# Just normalization for validation
data_transforms = {
    'train': transforms.Compose([
        transforms.RandomResizedCrop(224),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
#    'val': transforms.Compose([
#        transforms.Resize(256),
#        transforms.CenterCrop(224),
#        transforms.ToTensor(),
#        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
#    ]),

        'test': transforms.Compose([
        transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
}

#data_dir = 'hymenoptera_data'
#data_dir = "mona_data"
#data_dir = "shooting_data_2class"
#data_dir = "shooting_data_3cat"
data_dir = "images"
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x),
                                          data_transforms[x])
                  for x in ['train', 'test']}
dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=4,
                                             shuffle=True, num_workers=4)
              for x in ['train', 'test']}
dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'test']}
class_names = image_datasets['train'].classes

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")


######################################################################
# Visualize a few images
# ^^^^^^^^^^^^^^^^^^^^^^
# Let's visualize a few training images so as to understand the data
# augmentations.

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
    inp = np.clip(inp, 0, 1)
    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(dataloaders['train']))

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

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


######################################################################
# Training the model
# ------------------
#
# Now, let's write a general function to train a model. Here, we will
# illustrate:
#
# -  Scheduling the learning rate
# -  Saving the best model
#
# In the following, parameter ``scheduler`` is an LR scheduler object from
# ``torch.optim.lr_scheduler``.


def train_model(model, criterion, optimizer, scheduler, num_epochs=25):
    since = time.time()

    best_model_wts = copy.deepcopy(model.state_dict())
    best_acc = 0.0

    for epoch in range(num_epochs):
        print('Epoch {}/{}'.format(epoch, num_epochs - 1))
        print('-' * 10)

        # Each epoch has a training and validation phase
        for phase in ['train', 'test']:
            if phase == 'train':
                scheduler.step()
                model.train()  # Set model to training mode
##            else:
##                model.eval()   # Set model to evaluate mode

            running_loss = 0.0
            running_corrects = 0

            # Iterate over data.
            for inputs, labels in dataloaders[phase]:
                inputs = inputs.to(device)
                labels = labels.to(device)

                # zero the parameter gradients
                optimizer.zero_grad()

                # forward
                # track history if only in train
                with torch.set_grad_enabled(phase == 'train'):
                    outputs = model(inputs)
                    _, preds = torch.max(outputs, 1)
                    loss = criterion(outputs, labels)

                    # backward + optimize only if in training phase
                    if phase == 'train':
                        loss.backward()
                        optimizer.step()

                # statistics
                running_loss += loss.item() * inputs.size(0)
                running_corrects += torch.sum(preds == labels.data)

            epoch_loss = running_loss / dataset_sizes[phase]
            epoch_acc = running_corrects.double() / dataset_sizes[phase]

            print('{} Loss: {:.4f} Acc: {:.4f}'.format(
                phase, epoch_loss, epoch_acc))

            # deep copy the model
 #           if phase == 'val' and epoch_acc > best_acc:
 #               best_acc = epoch_acc
 #               best_model_wts = copy.deepcopy(model.state_dict())

        print()

    time_elapsed = time.time() - since
    print('Training complete in {:.0f}m {:.0f}s'.format(
        time_elapsed // 60, time_elapsed % 60))
#    print('Best val Acc: {:4f}'.format(best_acc))

    # load best model weights
#    model.load_state_dict(best_model_wts)
    return model


######################################################################
# Visualizing the model predictions
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
#
# Generic function to display predictions for a few images
#

def visualize_model(model, num_images=6):
    was_training = model.training
    model.eval()
    images_so_far = 0
    fig = plt.figure()

    with torch.no_grad():
        for i, (inputs, labels) in enumerate(dataloaders['test']):
            inputs = inputs.to(device)
            labels = labels.to(device)

            outputs = model(inputs)
            _, preds = torch.max(outputs, 1)

            for j in range(inputs.size()[0]):
                images_so_far += 1
                ax = plt.subplot(num_images//2, 2, images_so_far)
                ax.axis('off')
                ax.set_title('predicted: {}'.format(class_names[preds[j]]))
                imshow(inputs.cpu().data[j])

                if images_so_far == num_images:
                    model.train(mode=was_training)
                    return
        model.train(mode=was_training)

######################################################################
# Finetuning the convnet
# ----------------------
#
# Load a pretrained model and reset final fully connected layer.
#

#model_ft = models.resnet18(pretrained=True)
model_ft = models.resnet50(pretrained=True)

num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs, 9)

model_ft = model_ft.to(device)

criterion = nn.CrossEntropyLoss()

# Observe that all parameters are being optimized
optimizer_ft = optim.SGD(model_ft.parameters(), lr=0.001, momentum=0.9)

# Decay LR by a factor of 0.1 every 7 epochs
exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)


######################################################################
# Train and evaluate
# ^^^^^^^^^^^^^^^^^^
#
# It should take around 15-25 min on CPU. On GPU though, it takes less than a
# minute.
#

model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler,
                       num_epochs=25)

######################################################################
#

visualize_model(model_ft)


---------------------------------------------------------------------
Epoch 0/24
----------
train Loss: 2.0849 Acc: 0.3047
test Loss: 1.9907 Acc: 0.3643

Epoch 1/24
----------
train Loss: 1.9912 Acc: 0.3262
test Loss: 1.9723 Acc: 0.3143

Epoch 2/24
----------
train Loss: 1.8772 Acc: 0.3451
test Loss: 1.9634 Acc: 0.3429

Epoch 3/24
----------
train Loss: 1.8997 Acc: 0.3477
test Loss: 2.2405 Acc: 0.2857

Epoch 4/24
----------
train Loss: 1.8376 Acc: 0.3869
test Loss: 2.0975 Acc: 0.2857

Epoch 5/24
----------
train Loss: 1.7459 Acc: 0.4121
test Loss: 2.0324 Acc: 0.3143

Epoch 6/24
----------
train Loss: 1.7635 Acc: 0.4046
test Loss: 2.0811 Acc: 0.4071

Epoch 7/24
----------
train Loss: 1.4989 Acc: 0.4829
test Loss: 1.9167 Acc: 0.4214

Epoch 8/24
----------
train Loss: 1.3821 Acc: 0.5145
test Loss: 1.9868 Acc: 0.3929

Epoch 9/24
----------
train Loss: 1.3185 Acc: 0.5575
test Loss: 1.9225 Acc: 0.4143

Epoch 10/24
----------
train Loss: 1.3083 Acc: 0.5436
test Loss: 1.9001 Acc: 0.4357

Epoch 11/24
----------
train Loss: 1.2618 Acc: 0.5638
test Loss: 1.9409 Acc: 0.4000

Epoch 12/24
----------
train Loss: 1.2696 Acc: 0.5765
test Loss: 1.9952 Acc: 0.3857

Epoch 13/24
----------
train Loss: 1.2782 Acc: 0.5638
test Loss: 1.8705 Acc: 0.4143

Epoch 14/24
----------
train Loss: 1.1628 Acc: 0.6233
test Loss: 1.9135 Acc: 0.4071

Epoch 15/24
----------
train Loss: 1.2363 Acc: 0.5904
test Loss: 1.9826 Acc: 0.4071

Epoch 16/24
----------
train Loss: 1.2247 Acc: 0.5879
test Loss: 1.9062 Acc: 0.4357

Epoch 17/24
----------
train Loss: 1.1758 Acc: 0.6157
test Loss: 1.9463 Acc: 0.4500

Epoch 18/24
----------
train Loss: 1.2133 Acc: 0.5942
test Loss: 1.9168 Acc: 0.4143

Epoch 19/24
----------
train Loss: 1.1976 Acc: 0.5828
test Loss: 1.9197 Acc: 0.4000

Epoch 20/24
----------
train Loss: 1.1934 Acc: 0.6119
test Loss: 1.8853 Acc: 0.4071

Epoch 21/24
----------
train Loss: 1.1578 Acc: 0.6068
test Loss: 1.9011 Acc: 0.3929

Epoch 22/24
----------
train Loss: 1.1713 Acc: 0.5967
test Loss: 1.8918 Acc: 0.4143

Epoch 23/24
----------
train Loss: 1.1726 Acc: 0.6068
test Loss: 1.9312 Acc: 0.4643

Epoch 24/24
----------
train Loss: 1.1744 Acc: 0.5891
test Loss: 1.8914 Acc: 0.4143

Training complete in 5m 0s