Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
model_speedup.py 5.25 KB
Newer Older
QuanluZhang's avatar
Dev compression speedup (#1999)  
QuanluZhang committed
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 
import argparse
import time
import torch
import torch.nn as nn
import torch.nn.functional as F
from torchvision import datasets, transforms
from models.cifar10.vgg import VGG
from nni.compression.speedup.torch import ModelSpeedup
from nni.compression.torch import apply_compression_results

torch.manual_seed(0)
use_mask = False

def apoz_speedup(masks_file, model_checkpoint):
    device = torch.device('cuda')
    model = VGG(depth=16)
    model.to(device)
    model.eval()

    dummy_input = torch.randn(64, 3, 32, 32)
    if use_mask:
        apply_compression_results(model, masks_file)
        dummy_input = dummy_input.to(device)
        start = time.time()
        for _ in range(32):
            out = model(dummy_input)
        #print(out.size(), out)
        print('mask elapsed time: ', time.time() - start)
        return
    else:
        #print("model before: ", model)
        m_speedup = ModelSpeedup(model, dummy_input.to(device), masks_file)
        m_speedup.speedup_model()
        #print("model after: ", model)
        dummy_input = dummy_input.to(device)
        start = time.time()
        for _ in range(32):
            out = model(dummy_input)
        #print(out.size(), out)
        print('speedup elapsed time: ', time.time() - start)
        return

def l1filter_speedup(masks_file, model_checkpoint):
    device = torch.device('cuda')
    model = VGG(depth=16)
    model.to(device)
    model.eval()

    dummy_input = torch.randn(64, 3, 32, 32)
    if use_mask:
        apply_compression_results(model, masks_file)
        dummy_input = dummy_input.to(device)
        start = time.time()
        for _ in range(32):
            out = model(dummy_input)
        #print(out.size(), out)
        print('mask elapsed time: ', time.time() - start)
        return
    else:
        #print("model before: ", model)
        m_speedup = ModelSpeedup(model, dummy_input.to(device), masks_file)
        m_speedup.speedup_model()
        #print("model after: ", model)
        dummy_input = dummy_input.to(device)
        start = time.time()
        for _ in range(32):
            out = model(dummy_input)
        #print(out.size(), out)
        print('speedup elapsed time: ', time.time() - start)
        return

def fpgm_speedup(masks_file, model_checkpoint):
    from fpgm_torch_mnist import Mnist
    device = torch.device('cpu')
    model = Mnist()
    model.to(device)
    model.print_conv_filter_sparsity()

    dummy_input = torch.randn(64, 1, 28, 28)
    if use_mask:
        apply_compression_results(model, masks_file)
        dummy_input = dummy_input.to(device)
        start = time.time()
        for _ in range(40):
            out = model(dummy_input)
        print('mask elapsed time: ', time.time() - start)
        #print(out.size(), out)
        return
    else:
        m_speedup = ModelSpeedup(model, dummy_input.to(device), masks_file)
        m_speedup.speedup_model()
        dummy_input = dummy_input.to(device)
        start = time.time()
        for _ in range(40):
            out = model(dummy_input)
        print('speedup elapsed time: ', time.time() - start)
        #print(out.size(), out)
        return

def slim_speedup(masks_file, model_checkpoint):
    device = torch.device('cuda')
    model = VGG(depth=19)
    model.to(device)
    model.eval()

    dummy_input = torch.randn(64, 3, 32, 32)
    if use_mask:
        apply_compression_results(model, masks_file)
        dummy_input = dummy_input.to(device)
        start = time.time()
        for _ in range(32):
            out = model(dummy_input)
        #print(out.size(), out)
        print('mask elapsed time: ', time.time() - start)
        return
    else:
        #print("model before: ", model)
        m_speedup = ModelSpeedup(model, dummy_input.to(device), masks_file)
        m_speedup.speedup_model()
        #print("model after: ", model)
        dummy_input = dummy_input.to(device)
        start = time.time()
        for _ in range(32):
            out = model(dummy_input)
        #print(out.size(), out)
        print('speedup elapsed time: ', time.time() - start)
        return

if __name__ == '__main__':
    parser = argparse.ArgumentParser("speedup")
    parser.add_argument("--example_name", type=str, default="slim", help="the name of pruning example")
    parser.add_argument("--masks_file", type=str, default=None, help="the path of the masks file")
    parser.add_argument("--model_checkpoint", type=str, default=None, help="the path of checkpointed model")
    args = parser.parse_args()
    
    if args.example_name == 'slim':
        if args.masks_file is None:
            args.masks_file = 'mask_vgg19_cifar10.pth'
        slim_speedup(args.masks_file, args.model_checkpoint)
    elif args.example_name == 'fpgm':
        if args.masks_file is None:
            args.masks_file = 'mask.pth'
        fpgm_speedup(args.masks_file, args.model_checkpoint)
    elif args.example_name == 'l1filter':
        if args.masks_file is None:
            args.masks_file = 'mask_vgg16_cifar10.pth'
        l1filter_speedup(args.masks_file, args.model_checkpoint)
    elif args.example_name == 'apoz':
        if args.masks_file is None:
            args.masks_file = 'mask_vgg16_cifar10.pth'
        apoz_speedup(args.masks_file, args.model_checkpoint)
    else:
        raise ValueError('unsupported example_name: {}'.format(args.example_name))