-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathTransferLearning.py
168 lines (134 loc) · 5.2 KB
/
TransferLearning.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
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()
#load the data
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])
]
)
}
data_dir='data/hymenoptera_data'
image_datasets={x:datasets.ImageFolder(os.path.join(data_dir,x),data_transforms[x])
for x in ['train','val']}
dataLoaders={x: torch.utils.data.DataLoader(image_datasets[x],batch_size=4,shuffle=True,num_workers=4)
for x in ['train','val']}
dataset_sizes={x: len(image_datasets[x]) for x in ['train','val']}
class_names=image_datasets['train'].classes
device=torch.device("cuda:0" if torch.cuda.is_available() else 'cpu')
#visualize the images
def imshow(inp,title=None):
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=inp*std+mean
inp=np.clip(inp,0,1)
plt.imshow(inp)
if title is not None:
plt.title(title)
plt.pause(5.001)
def run():
inputs,classes=next(iter(dataLoaders['train']))
out=torchvision.utils.make_grid(inputs)
imshow(out,title=[class_names[x] for x in classes])
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(f'epoch {epoch+1}/{num_epochs}\n')
print('-'*20)
for phase in ['train','val']:
if phase=='train':
model.train()
else:
model.eval()
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 gradients
optimizer.zero_grad()
#forward
with torch.set_grad_enabled(phase=='train'):
outputs=model(inputs)
_,preds=torch.max(outputs,1)
loss=criterion(outputs,labels)
if phase=='train':
loss.backward()
optimizer.step()
running_loss+=loss.item()*inputs.size(0)
running_corrects+=torch.sum(preds==labels.data)
if phase=='train':
scheduler.step()
#statistics
epoch_loss=running_corrects/dataset_sizes[phase]
epoch_acc=running_corrects.double()/dataset_sizes[phase]
print(f'phase: {phase} loss:{epoch_loss} acc:{epoch_acc}\n')
if phase=='val' and epoch_acc>best_acc:
best_acc=epoch_acc
best_model_wts=copy.deepcopy(model.state_dict())
#training complete
time_elapsed=time.time()-since
print(f'training complete in {time_elapsed//60}m {time_elapsed%60}s \n')
print(f'Best acc: {best_acc}')
#return the model with best acc
model.load_state_dict(best_model_wts)
return model
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['val']):
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(f'predicted:{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)
if __name__=='__main__':
model_ft = models.resnet18(pretrained=True)
num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs, 2)
model_ft = model_ft.to(device)
criterion = nn.CrossEntropyLoss()
# 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)
model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler, num_epochs=25)
visualize_model(model_ft)