Pytorch骨干网络性能测试
Pytorch骨干网络性能测试
测试平台:
- Intel® Core™ i7-8700 CPU @ 3.20GHz × 12
- GeForce RTX 2070/PCIe/SSE2
| backbone | input size | output size | run time /ms | GPU/MiB |
|---|---|---|---|---|
| mobilenet_v2 |
[1,3,112,112] | 512 | 4.743 | 910 |
| reset18 |
[1,3,112,112] | 512 | 2.372 | 960 |
| resnet34 |
[1,3,112,112] | 512 | 3.974 | 1010 |
| vgg16 |
[1,3,112,112] | 512 | 3.844 | 1460 |
| squeezenet1_0 | [1,3,112,112] | 512 | 2.103 |
897 |
| squeezenet1_1 | [1,3,112,112] | 512 | 2.095 |
891 |
| mnasnet1_0 | [1,3,112,112] | 512 | 4.248 |
909 |
| shufflenet_v2_x1_0 | [1,3,112,112] | 512 | 5.449 |
891 |
| inception_v3 |
[1,3,112,112] | 512 | 12.341 | 1203 |
| googlenet | [1,3,112,112] | 512 | 5.752 | 935 |
| MixNet_S |
[1,3,112,112] | 512 | 8.260 | 930 |
| MixNet_M |
[1,3,112,112] | 512 | 9.914 | 960 |
| MixNet_L |
[1,3,112,112] | 512 | 10.020 | 990 |
测试代码:
# -*-coding: utf-8 -*-
"""
@Project: pytorch-learning-tutorials
@File : main.py
@Author : panjq
@E-mail : [email protected]
@Date : 2019-06-27 13:46:20
"""
import torch
from torchvision import models
from utils import debug
import performance.core.mixnet as mixnet
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
# device = 'cpu'
print("-----device:{}".format(device))
print("-----Pytorch version:{}".format(torch.__version__))
# @debug.run_time_decorator()
def model_forward(model, input_tensor):
T0 = debug.TIME()
out = model(input_tensor)
torch.cuda.synchronize()
T1 = debug.TIME()
time = debug.RUN_TIME(T1 - T0)
return out, time
def iter_model(model, input_tensor, iter):
out, time = model_forward(model, input_tensor)
all_time = 0
for i in range(iter):
out, time = model_forward(model, input_tensor)
all_time += time
return all_time
def squeezenet1_0(input_tensor, out_features, iter=10):
model = models.squeezenet.squeezenet1_0(pretrained=False, num_classes=out_features).to(device)
model.eval()
all_time = iter_model(model, input_tensor, iter)
print("squeezenet1_0,mean run time :{:.3f}".format(all_time / iter))
def squeezenet1_1(input_tensor, out_features, iter=10):
model = models.squeezenet.squeezenet1_1(pretrained=False, num_classes=out_features).to(device)
model.eval()
all_time = iter_model(model, input_tensor, iter)
print("squeezenet1_1,mean run time :{:.3f}".format(all_time / iter))
def mnasnet1_0(input_tensor, out_features, iter=10):
model = models.mnasnet.mnasnet1_0(pretrained=False, num_classes=out_features).to(device)
model.eval()
all_time = iter_model(model, input_tensor, iter)
print("mnasnet1_0,mean run time :{:.3f}".format(all_time / iter))
def shufflenet_v2_x1_0(input_tensor, out_features, iter=10):
model = models.shufflenetv2.shufflenet_v2_x1_0(pretrained=False, num_classes=out_features).to(device)
model.eval()
all_time = iter_model(model, input_tensor, iter)
print("shufflenet_v2_x1_0,mean run time :{:.3f}".format(all_time / iter))
def mobilenet_v2(input_tensor, out_features, iter=10):
model = models.mobilenet_v2(pretrained=False, num_classes=out_features).to(device)
model.eval()
all_time = iter_model(model, input_tensor, iter)
print("mobilenet_v2,mean run time :{:.3f}".format(all_time / iter))
def resnet18(input_tensor, out_features, iter=10):
model = models.resnet18(pretrained=False, num_classes=out_features).to(device)
model.eval()
all_time = iter_model(model, input_tensor, iter)
print("reset18,mean run time :{:.3f}".format(all_time / iter))
def resnet34(input_tensor, out_features, iter=10):
model = models.resnet34(pretrained=False, num_classes=out_features).to(device)
model.eval()
all_time = iter_model(model, input_tensor, iter)
print("resnet34,mean run time :{:.3f}".format(all_time / iter))
def vgg16(input_tensor, out_features, iter=10):
model = models.vgg16(pretrained=False, num_classes=out_features).to(device)
model.eval()
all_time = iter_model(model, input_tensor, iter)
print("vgg16,mean run time :{:.3f}".format(all_time / iter))
def MixNet_L(input_tensor, input_size, out_features, iter=10):
model = mixnet.MixNet_L(input_size, out_features).to(device)
model.eval()
all_time = iter_model(model, input_tensor, iter)
print("MixNet_L,mean run time :{:.3f}".format(all_time / iter))
def MixNet_M(input_tensor, input_size, out_features, iter=10):
model = mixnet.MixNet_M(input_size, out_features).to(device)
model.eval()
all_time = iter_model(model, input_tensor, iter)
print("MixNet_M,mean run time :{:.3f}".format(all_time / iter))
def MixNet_S(input_tensor, input_size, out_features, iter=10):
model = mixnet.MixNet_S(input_size, out_features).to(device)
model.eval()
all_time = iter_model(model, input_tensor, iter)
print("MixNet_S,mean run time :{:.3f}".format(all_time / iter))
def inception_v3(input_tensor, out_features, iter=10):
model = models.inception.inception_v3(pretrained=False, num_classes=out_features).to(device)
model.eval()
all_time = iter_model(model, input_tensor, iter)
print("inception_v3,mean run time :{:.3f}".format(all_time / iter))
def googlenet(input_tensor, out_features, iter=10):
model = models.googlenet(pretrained=False, num_classes=out_features).to(device)
model.eval()
all_time = iter_model(model, input_tensor, iter)
print("googlenet,mean run time :{:.3f}".format(all_time / iter))
if __name__ == "__main__":
input_size = [112, 112]
out_features = 512
input_tensor = torch.randn(1, 3, input_size[0], input_size[1]).to(device)
print('input_tensor:', input_tensor.shape)
iter = 10000
# mobilenet_v2(input_tensor, out_features, iter)
# resnet18(input_tensor, out_features, iter)
# resnet34(input_tensor, out_features, iter)
# vgg16(input_tensor, out_features, iter)
# squeezenet1_0(input_tensor, out_features, iter)
# squeezenet1_1(input_tensor, out_features, iter)
# inception_v3(input_tensor, out_features, iter)
googlenet(input_tensor, out_features, iter)
# mnasnet1_0(input_tensor, out_features, iter)
# shufflenet_v2_x1_0(input_tensor, out_features, iter)
# MixNet_S(input_tensor, input_size, out_features, iter)
# MixNet_M(input_tensor, input_size, out_features, iter)
# MixNet_L(input_tensor, input_size, out_features, iter)