AlexNet纸张与他们报告的尺寸不匹配?

时间:2018-10-15 16:52:09

标签: deep-learning conv-neural-network pytorch

我遵循的是paper where AlexNet was introduced,他们报告的尺寸与所附数字不符。

第一个conv层的输出(即96 11x11x3卷积)为55x55x96(对于简单的1GPU情况)。现在,论文指出将第二个conv层应用于maxpooling层的输出。假设MaxPool是3x3的内核,步幅为2(因为它们报告s和z),这意味着第二个卷积层的输入应为(55-3)/ 2 + 1 = 27,但在提供的图片中他们为AlexNet编写了一个最大池化操作,但没有执行池化的降维操作!

所以第二个conv层应该应用于宽度和高度= 27而不是55的体积上,对吗?

enter image description here

此外,我看了看PyTorch如何实现它,看看我是否丢失了什么,他们只是从64个内核开始更改了配置...:

AlexNet(
  (features): Sequential(
    (0): Conv2d(3, 64, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2))
    (1): ReLU(inplace)
    (2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
    (3): Conv2d(64, 192, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
    (4): ReLU(inplace)
    (5): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
    (6): Conv2d(192, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (7): ReLU(inplace)
    (8): Conv2d(384, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (9): ReLU(inplace)
    (10): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (11): ReLU(inplace)
    (12): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (classifier): Sequential(
    (0): Dropout(p=0.5)
    (1): Linear(in_features=9216, out_features=4096, bias=True)
    (2): ReLU(inplace)
    (3): Dropout(p=0.5)
    (4): Linear(in_features=4096, out_features=4096, bias=True)
    (5): ReLU(inplace)
    (6): Linear(in_features=4096, out_features=1000, bias=True)
  )
)

0 个答案:

没有答案