-
Notifications
You must be signed in to change notification settings - Fork 0
/
model.py
216 lines (159 loc) · 6.48 KB
/
model.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
#import libraries
%matplotlib inline
import os
import shutil
import random
import torch
import torchvision
import numpy as np
from PIL import Image
from matplotlib import pyplot as plt
torch.manual_seed(0)
# split the data to train and test
class_names = ['normal', 'viral', 'covid']
root_dir = 'COVID-19 Radiography Database'
source_dirs = ['NORMAL', 'Viral Pneumonia', 'COVID-19']
if os.path.isdir(os.path.join(root_dir, source_dirs[1])):
os.mkdir(os.path.join(root_dir, 'test'))
for i, d in enumerate(source_dirs):
os.rename(os.path.join(root_dir, d), os.path.join(root_dir, class_names[i]))
for c in class_names:
os.mkdir(os.path.join(root_dir, 'test', c))
for c in class_names:
images = [x for x in os.listdir(os.path.join(root_dir, c)) if x.lower().endswith('png')]
selected_images = random.sample(images, 30)
for image in selected_images:
source_path = os.path.join(root_dir, c, image)
target_path = os.path.join(root_dir, 'test', c, image)
shutil.move(source_path, target_path)
#create custom dataset
class ChestXRayDataset(torch.utils.data.Dataset):
def __init__(self, image_dirs, transform):
def get_images(class_name):
images = [x for x in os.listdir(image_dirs[class_name]) if x[-3:].lower().endswith('png')]
print(f'Found {len(images)} {class_name} examples')
return images
self.images = {}
self.class_names = ['normal', 'viral', 'covid']
for class_name in self.class_names:
self.images[class_name] = get_images(class_name)
self.image_dirs = image_dirs
self.transform = transform
def __len__(self):
return sum([len(self.images[class_name]) for class_name in self.class_names])
def __getitem__(self, index):
class_name = random.choice(self.class_names)
index = index % len(self.images[class_name])
image_name = self.images[class_name][index]
image_path = os.path.join(self.image_dirs[class_name], image_name)
image = Image.open(image_path).convert('RGB')
return self.transform(image), self.class_names.index(class_name)
#image transformation
train_transform = torchvision.transforms.Compose([
torchvision.transforms.Resize(size=(224, 224)),
torchvision.transforms.RandomHorizontalFlip(),
torchvision.transforms.ToTensor(),
torchvision.transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])
test_transform = torchvision.transforms.Compose([
torchvision.transforms.Resize(size=(224, 224)),
torchvision.transforms.ToTensor(),
torchvision.transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])
#prepare dataloader
train_dirs = {
'normal': 'COVID-19 Radiography Database/normal',
'viral': 'COVID-19 Radiography Database/viral',
'covid': 'COVID-19 Radiography Database/covid'
}
train_dataset = ChestXRayDataset(train_dirs, train_transform)
test_dirs = {
'normal': 'COVID-19 Radiography Database/test/normal',
'viral': 'COVID-19 Radiography Database/test/viral',
'covid': 'COVID-19 Radiography Database/test/covid'
}
test_dataset = ChestXRayDataset(test_dirs, test_transform)
batch_size = 5
dl_train = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
dl_test = torch.utils.data.DataLoader(test_dataset, batch_size=batch_size, shuffle=True)
print('Number of training batches', len(dl_train))
print('Number of test batches', len(dl_test))
#visualizing
class_names = train_dataset.class_names
def show_images(images, labels, preds):
plt.figure(figsize=(8, 4))
for i, image in enumerate(images):
plt.subplot(1, 6, i + 1, xticks=[], yticks=[])
image = image.numpy().transpose((1, 2, 0))
mean = np.array([0.485, 0.456, 0.406])
std = np.array([0.229, 0.224, 0.225])
image = image * std + mean
image = np.clip(image, 0., 1.)
plt.imshow(image)
col = 'green'
if preds[i] != labels[i]:
col = 'red'
plt.xlabel(f'{class_names[int(labels[i].numpy())]}')
plt.ylabel(f'{class_names[int(preds[i].numpy())]}', color=col)
plt.tight_layout()
plt.show()
images, labels = next(iter(dl_train))
show_images(images, labels, labels)
images, labels = next(iter(dl_test))
show_images(images, labels, labels)
#creating the model
resnet18 = torchvision.models.resnet18(pretrained=True)
print(resnet18)
resnet18.fc = torch.nn.Linear(in_features=512, out_features=3)
loss_fn = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(resnet18.parameters(), lr=3e-5)
def show_preds():
resnet18.eval()
images, labels = next(iter(dl_test))
outputs = resnet18(images)
_, preds = torch.max(outputs, 1)
show_images(images, labels, preds)
show_preds()
#training the model
def train(epochs):
print('Starting training..')
for e in range(0, epochs):
print('='*20)
print(f'Starting epoch {e + 1}/{epochs}')
print('='*20)
train_loss = 0.
val_loss = 0.
resnet18.train() # set model to training phase
for train_step, (images, labels) in enumerate(dl_train):
optimizer.zero_grad()
outputs = resnet18(images)
loss = loss_fn(outputs, labels)
loss.backward()
optimizer.step()
train_loss += loss.item()
if train_step % 20 == 0:
print('Evaluating at step', train_step)
accuracy = 0
val_loss = 0.
resnet18.eval() # set model to eval phase
for val_step, (images, labels) in enumerate(dl_test):
outputs = resnet18(images)
loss = loss_fn(outputs, labels)
val_loss += loss.item()
_, preds = torch.max(outputs, 1)
accuracy += sum((preds == labels).numpy())
val_loss /= (val_step + 1)
accuracy = accuracy/len(test_dataset)
print(f'Validation Loss: {val_loss:.4f}, Accuracy: {accuracy:.4f}')
show_preds()
resnet18.train()
if accuracy >= 0.95:
print('Performance condition satisfied, stopping..')
return
train_loss /= (train_step + 1)
print(f'Training Loss: {train_loss:.4f}')
print('Training complete..')
%%time
train(epochs=1)
#final result
show_preds()