Pytorch骨干网络性能测试

迷南。 2021-10-29 11:20 343阅读 0赞

# 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

<table> 
 <tbody> 
 <tr> 
 <th>backbone</th> 
 <th>input size</th> 
 <th>output size</th> 
 <th>run time /ms</th> 
 <th colspan="1">GPU/MiB</th> 
 </tr> 
 <tr> 
 <td> mobilenet_v2 </td> 
 <td>[1,3,112,112]</td> 
 <td>512</td> 
 <td>4.743</td> 
 <td colspan="1">910</td> 
 </tr> 
 <tr> 
 <td> reset18 </td> 
 <td>[1,3,112,112]</td> 
 <td>512</td> 
 <td>2.372</td> 
 <td colspan="1">960</td> 
 </tr> 
 <tr> 
 <td colspan="1"> resnet34 </td> 
 <td colspan="1">[1,3,112,112]</td> 
 <td colspan="1">512</td> 
 <td colspan="1">3.974</td> 
 <td colspan="1">1010</td> 
 </tr> 
 <tr> 
 <td colspan="1"> vgg16 </td> 
 <td colspan="1">[1,3,112,112]</td> 
 <td colspan="1">512</td> 
 <td colspan="1">3.844</td> 
 <td colspan="1">1460</td> 
 </tr> 
 <tr> 
 <td colspan="1">squeezenet1_0</td> 
 <td colspan="1">[1,3,112,112]</td> 
 <td colspan="1">512</td> 
 <td colspan="1"> 2.103 </td> 
 <td colspan="1">897</td> 
 </tr> 
 <tr> 
 <td colspan="1">squeezenet1_1</td> 
 <td colspan="1">[1,3,112,112]</td> 
 <td colspan="1">512</td> 
 <td colspan="1"> 2.095 </td> 
 <td colspan="1">891</td> 
 </tr> 
 <tr> 
 <td colspan="1">mnasnet1_0</td> 
 <td colspan="1">[1,3,112,112]</td> 
 <td colspan="1">512</td> 
 <td colspan="1"> 4.248 </td> 
 <td colspan="1">909</td> 
 </tr> 
 <tr> 
 <td colspan="1">shufflenet_v2_x1_0</td> 
 <td colspan="1">[1,3,112,112]</td> 
 <td colspan="1">512</td> 
 <td colspan="1"> 5.449 </td> 
 <td colspan="1">891</td> 
 </tr> 
 <tr> 
 <td colspan="1"> inception_v3 </td> 
 <td colspan="1">[1,3,112,112]</td> 
 <td colspan="1">512</td> 
 <td colspan="1">12.341</td> 
 <td colspan="1">1203</td> 
 </tr> 
 <tr> 
 <td colspan="1">googlenet</td> 
 <td colspan="1">[1,3,112,112]</td> 
 <td colspan="1">512</td> 
 <td colspan="1">5.752</td> 
 <td colspan="1">935</td> 
 </tr> 
 <tr> 
 <td colspan="1"> MixNet_S </td> 
 <td colspan="1">[1,3,112,112]</td> 
 <td colspan="1">512</td> 
 <td colspan="1">8.260</td> 
 <td colspan="1">930</td> 
 </tr> 
 <tr> 
 <td> MixNet_M </td> 
 <td>[1,3,112,112]</td> 
 <td>512</td> 
 <td>9.914</td> 
 <td colspan="1">960</td> 
 </tr> 
 <tr> 
 <td colspan="1"> MixNet_L </td> 
 <td colspan="1">[1,3,112,112]</td> 
 <td colspan="1">512</td> 
 <td colspan="1">10.020</td> 
 <td colspan="1">990</td> 
 </tr> 
 <tr> 
 <td colspan="1">&nbsp;</td> 
 <td colspan="1">&nbsp;</td> 
 <td colspan="1">&nbsp;</td> 
 <td colspan="1">&nbsp;</td> 
 <td colspan="1">&nbsp;</td> 
 </tr> 
 </tbody> 
</table>

测试代码:

# -*-coding: utf-8 -*-
    """
        @Project: pytorch-learning-tutorials
        @File   : main.py
        @Author : panjq
        @E-mail : pan_jinquan@163.com
        @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)