pytorch从预训练模型提取图像特征计算featureless

1.背景描述

想借助一个预训练好的网络（非集成好的）计算feature-loss，预训练网络地址：表情识别net

2具体实操

2.1 加载模型

作者已经给出了预训练好的模型参数和模型代码，首先我们要把模型load进来：

    from Expression.VGG import VGG
    model = VGG('VGG19')
    #check_pth 从网站上download下来PrivateTest_model.t7
    checkpoint = torch.load(check_pth)
    model.load_state_dict(checkpoint['net'])
    model.cuda()
    model.eval()

我们可以看一下该模型的结构

print(torch.nn.Sequential(*list(model.children())[:]))

结果为：

Sequential(
  (0): Sequential(
    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (2): ReLU(inplace)
    (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (5): ReLU(inplace)
    (6): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (7): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (8): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (9): ReLU(inplace)
    (10): Conv2d(128, 128