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
217
218
219
220
221
222
223
224
225
226
| import os, sys, glob, argparse
import pandas as pd
import numpy as np
from tqdm import tqdm
import matplotlib.pyplot as plt
import time
import cv2
from PIL import Image
from sklearn.model_selection import train_test_split, StratifiedKFold, KFold
import torch
torch.manual_seed(0)
torch.backends.cudnn.deterministic = False
torch.backends.cudnn.benchmark = True
import torchvision.models as models
import torchvision.transforms as transforms
import torchvision.datasets as datasets
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.autograd import Variable
from torch.utils.data import Dataset
import albumentations as A
train_path = glob.glob('./苹果病害图像识别挑战赛公开数据/train/*/*')
test_path = glob.glob('./苹果病害图像识别挑战赛公开数据/test/*')
np.random.shuffle(train_path)
np.random.shuffle(test_path)
DATA_CACHE = {}
class XunFeiDataset(Dataset):
def __init__(self, img_path, transform=None):
self.img_path = img_path
if transform is not None:
self.transform = transform
else:
self.transform = None
def __getitem__(self, index):
if self.img_path[index] in DATA_CACHE:
img = DATA_CACHE[self.img_path[index]]
else:
img = cv2.imdecode(np.fromfile(self.img_path[index], dtype=np.uint8), -1)
DATA_CACHE[self.img_path[index]] = img
if self.transform is not None:
img = self.transform(image = img)['image']
if self.img_path[index].split('\\')[1] in ['d1', 'd2', 'd3', 'd4', 'd5', 'd6', 'd7', 'd8', 'd9']:
label = ['d1', 'd2', 'd3', 'd4', 'd5', 'd6', 'd7', 'd8', 'd9'].index(self.img_path[index].split('\\')[1])
else:
label = -1
img = img.transpose([2,0,1])
return img, torch.from_numpy(np.array(label))
def __len__(self):
return len(self.img_path)
class XunFeiNet(nn.Module):
def __init__(self,l=None):
super(XunFeiNet, self).__init__()
model = models.resnet18(weights=models.ResNet18_Weights.DEFAULT)
model.avgpool = nn.AdaptiveAvgPool2d(1)
model.fc = nn.Linear(512, 9)
if l!=None:
model=model.load_state_dict(torch.load('model1.pth'))
self.resnet = model
def forward(self, img):
out = self.resnet(img)
return out
def train(train_loader, model, criterion, optimizer):
model.train()
train_loss = 0.0
for i, (x, target) in enumerate(train_loader):
x = x.cuda(non_blocking=True)
target=target.float()
target = target.cuda(non_blocking=True)
output = model(x)
loss = criterion(output, target.long())
optimizer.zero_grad()
loss.backward()
optimizer.step()
if i % 20 == 0:
print('Train loss', loss.item())
train_loss += loss.item()
return train_loss/len(train_loader)
def validate(val_loader, model, criterion):
model.eval()
val_acc = 0.0
with torch.no_grad():
end = time.time()
for i, (x, target) in enumerate(val_loader):
x = x.cuda()
target=target.float()
target = target.cuda()
output = model(x)
loss = criterion(output, target.long())
val_acc += (output.argmax(1) == target).sum().item()
return val_acc / len(val_loader.dataset)
def predict(test_loader, model, criterion):
model.eval()
val_acc = 0.0
test_pred = []
with torch.no_grad():
end = time.time()
for i, (x, target) in enumerate(test_loader):
x = x.cuda()
target=target.float()
target = target.cuda()
output = model(x)
test_pred.append(output.data.cpu().numpy())
return np.vstack(test_pred)
train_loader = torch.utils.data.DataLoader(
XunFeiDataset(train_path[:-1000],
A.Compose([
A.RandomRotate90(),
A.Resize(256, 256),
A.RandomCrop(224, 224),
A.HorizontalFlip(p=0.5),
A.RandomBrightnessContrast(p=0.5),
A.RandomBrightnessContrast(p=0.5),
A.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225))
])
), batch_size=30, shuffle=True, num_workers=4
)
val_loader = torch.utils.data.DataLoader(
XunFeiDataset(train_path[-1000:],
A.Compose([
A.Resize(256, 256),
A.RandomCrop(224, 224),
A.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225))
])
), batch_size=30, shuffle=False, num_workers=4
)
test_loader = torch.utils.data.DataLoader(
XunFeiDataset(test_path,
A.Compose([
A.Resize(256, 256),
A.RandomCrop(224, 224),
A.HorizontalFlip(p=0.5),
A.RandomBrightnessContrast(p=0.5),
A.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225))
])
), batch_size=2, shuffle=False, num_workers=4
)
model = XunFeiNet()
model = model.to('cuda')
criterion = nn.CrossEntropyLoss().cuda()
optimizer = torch.optim.AdamW(model.parameters(), 0.00005)
if __name__ == '__main__':
for i in range(2):
print(i,'开始')
train_loss = train(train_loader, model, criterion, optimizer)
val_acc = validate(val_loader, model, criterion)
train_acc = validate(train_loader, model, criterion)
print(train_loss, train_acc, val_acc)
torch.save(model.state_dict(), 'model1.pth')
pred = None
for _ in range(10):
if pred is None:
pred = predict(test_loader, model, criterion)
else:
pred += predict(test_loader, model, criterion)
submit = pd.DataFrame(
{
'uuid': [(x.split("\\")[-1]).split("/")[-1] for x in test_path],
'label': [['d1', 'd2', 'd3', 'd4', 'd5', 'd6', 'd7', 'd8', 'd9'][x] for x in pred.argmax(1)]
})
submit = submit.sort_values(by='uuid')
submit.to_csv('submit1.csv', index=None)
|