溫馨提示×
您好，登錄后才能下訂單哦！
點擊 登錄注冊 即表示同意《億速云用戶服務條款》
您好，登錄后才能下訂單哦！
這篇文章主要介紹了pytorch中卷積和池化計算方式的示例分析，具有一定借鑒價值，感興趣的朋友可以參考下，希望大家閱讀完這篇文章之后大有收獲，下面讓小編帶著大家一起了解一下。
TensorFlow里面的padding只有兩個選項也就是valid和same
pytorch里面的padding么有這兩個選項，它是數字0,1,2,3等等，默認是0
所以輸出的h和w的計算方式也是稍微有一點點不同的：tf中的輸出大小是和原來的大小成倍數關系，不能任意的輸出大小；而nn輸出大小可以通過padding進行改變
nn里面的卷積操作或者是池化操作的H和W部分都是一樣的計算公式：H和W的計算
class torch.nn.MaxPool2d(kernel_size, stride=None, padding=0, dilation=1, return_indices=False, ceil_mode=False): """ Parameters: kernel_size – the size of the window to take a max over stride – the stride of the window. 默認值是kernel_size padding – implicit zero padding to be added on both side,默認值是0 dilation – a parameter that controls the stride of elements in the window，默認值是1 return_indices – if True, will return the max indices along with the outputs. Useful when Unpooling later ceil_mode – when True, will use ceil instead of floor to compute the output shape，向上取整和向下取整，默認是向下取整 """
不一樣的地方在于：第一點，步長stride默認值，上面默認和設定的kernel_size一樣，下面默認是1；第二點，輸出通道的不一樣，上面的輸出通道和輸入通道是一樣的也就是沒有改變特征圖的數目，下面改變特征圖的數目為out_channels
class torch.nn.Conv2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True): pass """ Parameters: in_channels (int) – Number of channels in the input image out_channels (int) – Number of channels produced by the convolution kernel_size (int or tuple) – Size of the convolving kernel stride (int or tuple, optional) – Stride of the convolution. Default: 1,默認是1 padding (int or tuple, optional) – Zero-padding added to both sides of the input. Default: 0 dilation (int or tuple, optional) – Spacing between kernel elements. Default: 1 groups (int, optional) – Number of blocked connections from input channels to output channels. Default: 1 bias (bool, optional) – If True, adds a learnable bias to the output. Default: True """
第三點不一樣是卷積有一個參數groups,將特征圖分開給不同的卷積進行操作然后再整合到一起，xception就是利用這一個。
""" At groups=1, all inputs are convolved to all outputs. At groups=2, the operation becomes equivalent to having two conv layers side by side, each seeing half the input channels, and producing half the output channels, and both subsequently concatenated. At groups= in_channels, each input channel is convolved with its own set of filters (of size ?out_channelsin_channels? ). """
pytorch AvgPool2d函數
class torch.nn.AvgPool2d(kernel_size, stride=None, padding=0, ceil_mode=False, count_include_pad=True): pass """ kernel_size: the size of the window stride: the stride of the window. Default value is :attr:`kernel_size` padding: implicit zero padding to be added on both sides ceil_mode: when True, will use `ceil` instead of `floor` to compute the output shape count_include_pad: when True, will include the zero-padding in the averaging calculation """
shape的計算公式，在（h,w)位置處的輸出值的計算。
pytorch中的F.avg_pool1d（）平均池化操作作用于一維，input 的維度是三維比如［２,２,７］。F.avg_pool1d（）中核ｓｉｚｅ是３，步長是２表示每三個數取平均，每隔兩個數取一次．比如[1,3,3,4,5,6,7]安照3個數取均值，兩步取一次，那么結果就是[ 2.3333 ,4 ,6 ]，也就是核是一維的，也只作用于一個維度。按照池化操作計算公式input size為[2,2,7],kernel size為3，步長為2，則輸出維度計算（7-3）/2+1=3所以輸出維度是[2,2,3]，這與輸出結果是一致的。
pytorch中的F.avg_pool2d（），input 是維度是４維如［２，２，４，４］，表示這里批量數是２也就是兩張圖像，這里通道數量是２，圖像是size 是４＊４的．核size是（２，２），步長是（２，２）表示被核覆蓋的數取平均，橫向縱向的步長都是２．那么核是二維的，所以取均值時也是覆蓋二維取的。輸出中第一個1.5的計算是：(1+2+1+2)/4=1.5.表示第一張圖像左上角的四個像素點的均值。按照池化操作計算公式input size為[2,2,4,4],kernel size為2*2，步長為2，則輸出維度計算（4-2）/2+1=2所以輸出維度是[2,2,2,2]，這與輸出結果是一致的。
Conv3d函數
class torch.nn.Conv3d(in_channels, out_channels, kernel_size, stride=1,
padding=0, dilation=1, groups=1, bias=True):
pass
"""
in_channels (int): Number of channels in the input image
out_channels (int): Number of channels produced by the convolution
kernel_size (int or tuple): Size of the convolving kernel
stride (int or tuple, optional): Stride of the convolution. Default: 1
padding (int or tuple, optional): Zero-padding added to all three sides of the input. Default: 0
dilation (int or tuple, optional): Spacing between kernel elements. Default: 1
groups (int, optional): Number of blocked connections from input channels to output channels. Default: 1
bias (bool, optional): If ``True``, adds a learnable bias to the output. Default: ``True``
Shape:
- Input: :math:`(N, C_{in}, D_{in}, H_{in}, W_{in})`
- Output: :math:`(N, C_{out}, D_{out}, H_{out}, W_{out})`
"""
C_out = out_channels
感謝你能夠認真閱讀完這篇文章，希望小編分享的“pytorch中卷積和池化計算方式的示例分析”這篇文章對大家有幫助，同時也希望大家多多支持億速云，關注億速云行業資訊頻道，更多相關知識等著你來學習!
免責聲明：本站發布的內容（圖片、視頻和文字）以原創、轉載和分享為主，文章觀點不代表本網站立場，如果涉及侵權請聯系站長郵箱：is@yisu.com進行舉報，并提供相關證據，一經查實，將立刻刪除涉嫌侵權內容。
