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
|
import torch
import torchvision
import torchvision.transforms.transforms as transforms
import os
import torch.quantization
from torchvision.models.quantization.resnet import resnet18
from torch.autograd import Variable
# Setup warnings
import warnings
warnings.filterwarnings(
action='ignore',
category=DeprecationWarning,
module=r'.*'
)
warnings.filterwarnings(
action='default',
module=r'torch.quantization'
)
"""
Define helper functions for APoT PTQ and QAT
"""
# Specify random seed for repeatable results
_ = torch.manual_seed(191009)
train_batch_size = 30
eval_batch_size = 50
class AverageMeter(object):
"""Computes and stores the average and current value"""
def __init__(self, name, fmt=':f'):
self.name = name
self.fmt = fmt
self.reset()
def reset(self):
self.val = 0
self.avg = 0.0
self.sum = 0
self.count = 0
def update(self, val, n=1):
self.val = val
self.sum += val * n
self.count += n
self.avg = self.sum / self.count
def __str__(self):
fmtstr = '{name} {val' + self.fmt + '} ({avg' + self.fmt + '})'
return fmtstr.format(**self.__dict__)
def accuracy(output, target, topk=(1,)):
"""Computes the accuracy over the k top predictions for the specified values of k"""
with torch.no_grad():
maxk = max(topk)
batch_size = target.size(0)
_, pred = output.topk(maxk, 1, True, True)
pred = pred.t()
correct = pred.eq(target.view(1, -1).expand_as(pred))
res = []
for k in topk:
correct_k = correct[:k].reshape(-1).float().sum(0, keepdim=True)
res.append(correct_k.mul_(100.0 / batch_size))
return res
def evaluate(model, criterion, data_loader):
model.eval()
top1 = AverageMeter('Acc@1', ':6.2f')
top5 = AverageMeter('Acc@5', ':6.2f')
with torch.no_grad():
for image, target in data_loader:
output = model(image)
loss = criterion(output, target)
acc1, acc5 = accuracy(output, target, topk=(1, 5))
top1.update(acc1[0], image.size(0))
top5.update(acc5[0], image.size(0))
print('')
return top1, top5
def load_model(model_file):
model = resnet18(pretrained=False)
state_dict = torch.load(model_file)
model.load_state_dict(state_dict)
model.to("cpu")
return model
def print_size_of_model(model):
if isinstance(model, torch.jit.RecursiveScriptModule):
torch.jit.save(model, "temp.p")
else:
torch.jit.save(torch.jit.script(model), "temp.p")
print("Size (MB):", os.path.getsize("temp.p") / 1e6)
os.remove("temp.p")
def prepare_data_loaders(data_path):
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
dataset = torchvision.datasets.ImageNet(data_path,
split="train",
transform=transforms.Compose([transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
normalize]))
dataset_test = torchvision.datasets.ImageNet(data_path,
split="val",
transform=transforms.Compose([transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
normalize]))
train_sampler = torch.utils.data.RandomSampler(dataset)
test_sampler = torch.utils.data.SequentialSampler(dataset_test)
data_loader = torch.utils.data.DataLoader(
dataset, batch_size=train_batch_size,
sampler=train_sampler)
data_loader_test = torch.utils.data.DataLoader(
dataset_test, batch_size=eval_batch_size,
sampler=test_sampler)
return data_loader, data_loader_test
def training_loop(model, criterion, data_loader):
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
train_loss, correct, total = 0, 0, 0
model.train()
for i in range(10):
for data, target in data_loader:
optimizer.zero_grad()
output = model(data)
loss = criterion(output, target)
loss = Variable(loss, requires_grad=True)
loss.backward()
optimizer.step()
train_loss += loss.item()
_, predicted = torch.max(output, 1)
total += target.size(0)
correct += (predicted == target).sum().item()
return train_loss, correct, total
|
