/
tutorial_code.py
162 lines (131 loc) · 4.9 KB
/
tutorial_code.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
import torch
import torchvision
import torchvision.transforms as transforms
# import matplotlib.pyplot as plt
# import numpy as np
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from time import time
class Net(nn.Module):
def __init__(self):
super().__init__()
self.conv1 = nn.Conv2d(3, 6, 5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16 * 5 * 5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = torch.flatten(x, 1) # flatten all dimensions except batch
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
if __name__ == "__main__":
start = time()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
net = Net()
net.to(device)
# Assuming that we are on a CUDA machine, this should print a CUDA device:
print(device)
transform = transforms.Compose(
[transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]
)
batch_size = 1000
trainset = torchvision.datasets.CIFAR10(
root="./data", train=True, download=True, transform=transform
)
trainloader = torch.utils.data.DataLoader(
trainset, batch_size=batch_size, shuffle=True, num_workers=2, drop_last=True
)
testset = torchvision.datasets.CIFAR10(
root="./data", train=False, download=True, transform=transform
)
testloader = torch.utils.data.DataLoader(
testset, batch_size=batch_size, shuffle=False, num_workers=2, drop_last=True
)
classes = (
"plane",
"car",
"bird",
"cat",
"deer",
"dog",
"frog",
"horse",
"ship",
"truck",
)
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
for epoch in range(10000): # loop over the dataset multiple times
loop = time()
print(loop - start)
print(epoch)
running_loss = 0.0
for i, data in enumerate(trainloader, 0):
# get the inputs; data is a list of [inputs, labels]
inputs, labels = data[0].to(device), data[1].to(device)
# zero the parameter gradients
optimizer.zero_grad()
# forward + backward + optimize
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
if i % 2000 == 1999: # print every 2000 mini-batches
print(f"[{epoch + 1}, {i + 1:5d}] loss: {running_loss / 2000:.3f}")
running_loss = 0.0
print("Finished Training")
PATH = "./cifar_net.pth"
torch.save(net.state_dict(), PATH)
dataiter = iter(testloader)
images, labels = next(dataiter)
net = Net()
net.load_state_dict(torch.load(PATH))
outputs = net(images)
_, predicted = torch.max(outputs, 1)
print("Predicted: ", " ".join(f"{classes[predicted[j]]:5s}" for j in range(4)))
correct = 0
total = 0
# since we're not training, we don't need to calculate the gradients for our outputs
with torch.no_grad():
for data in testloader:
inputs, labels = data[0], data[1]
# calculate outputs by running images through the network
outputs = net(inputs)
# the class with the highest energy is what we choose as prediction
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print(
f"Accuracy of the network on the 10000 test images: {100 * correct // total} %"
)
# prepare to count predictions for each class
correct_pred = {classname: 0 for classname in classes}
total_pred = {classname: 0 for classname in classes}
# again no gradients needed
with torch.no_grad():
for data in testloader:
images, labels = data[0], data[1]
outputs = net(images)
_, predictions = torch.max(outputs, 1)
# collect the correct predictions for each class
for label, prediction in zip(labels, predictions):
# print("test")
# print(label)
# print(prediction)
if label == prediction:
correct_pred[classes[label]] += 1
total_pred[classes[label]] += 1
# print accuracy for each class
for classname, correct_count in correct_pred.items():
accuracy = 100 * float(correct_count) / total_pred[classname]
print(f"Accuracy for class: {classname:5s} is {accuracy:.1f} %")
end = time() - start
print(end)