Numpy实现Conv2D

举报
AI浩 发表于 2021/12/23 00:25:06 2021/12/23
【摘要】 class Conv2D(Layer): """A 2D Convolution Layer. Parameters: ----------- n_filters: in...
class Conv2D(Layer):
    """A 2D Convolution Layer.

    Parameters:
    -----------
    n_filters: int
        The number of filters that will convolve over the input matrix. The number of channels
        of the output shape.
    filter_shape: tuple
        A tuple (filter_height, filter_width).
    input_shape: tuple
        The shape of the expected input of the layer. (batch_size, channels, height, width)
        Only needs to be specified for first layer in the network.
    padding: string
        Either 'same' or 'valid'. 'same' results in padding being added so that the output height and width
        matches the input height and width. For 'valid' no padding is added.
    stride: int
        The stride length of the filters during the convolution over the input.
    """
    def __init__(self, n_filters, filter_shape, input_shape=None, padding='same', stride=1):
        self.n_filters = n_filters
        self.filter_shape = filter_shape
        self.padding = padding
        self.stride = stride
        self.input_shape = input_shape
        self.trainable = True

    def initialize(self, optimizer):
        # Initialize the weights
        filter_height, filter_width = self.filter_shape
        channels = self.input_shape[0]
        limit = 1 / math.sqrt(np.prod(self.filter_shape))
        self.W  = np.random.uniform(-limit, limit, size=(self.n_filters, channels, filter_height, filter_width))
        self.w0 = np.zeros((self.n_filters, 1))
        # Weight optimizers
        self.W_opt  = copy.copy(optimizer)
        self.w0_opt = copy.copy(optimizer)

    def parameters(self):
        return np.prod(self.W.shape) + np.prod(self.w0.shape)

    def forward_pass(self, X, training=True):
        batch_size, channels, height, width = X.shape
        self.layer_input = X
        # Turn image shape into column shape
        # (enables dot product between input and weights)
        self.X_col = image_to_column(X, self.filter_shape, stride=self.stride, output_shape=self.padding)
        # Turn weights into column shape
        self.W_col = self.W.reshape((self.n_filters, -1))
        # Calculate output
        output = self.W_col.dot(self.X_col) + self.w0
        # Reshape into (n_filters, out_height, out_width, batch_size)
        output = output.reshape(self.output_shape() + (batch_size, ))
        # Redistribute axises so that batch size comes first
        return output.transpose(3,0,1,2)

    def backward_pass(self, accum_grad):
        # Reshape accumulated gradient into column shape
        accum_grad = accum_grad.transpose(1, 2, 3, 0).reshape(self.n_filters, -1)

        if self.trainable:
            # Take dot product between column shaped accum. gradient and column shape
            # layer input to determine the gradient at the layer with respect to layer weights
            grad_w = accum_grad.dot(self.X_col.T).reshape(self.W.shape)
            # The gradient with respect to bias terms is the sum similarly to in Dense layer
            grad_w0 = np.sum(accum_grad, axis=1, keepdims=True)

            # Update the layers weights
            self.W = self.W_opt.update(self.W, grad_w)
            self.w0 = self.w0_opt.update(self.w0, grad_w0)

        # Recalculate the gradient which will be propogated back to prev. layer
        accum_grad = self.W_col.T.dot(accum_grad)
        # Reshape from column shape to image shape
        accum_grad = column_to_image(accum_grad,
                                self.layer_input.shape,
                                self.filter_shape,
                                stride=self.stride,
                                output_shape=self.padding)

        return accum_grad

    def output_shape(self):
        channels, height, width = self.input_shape
        pad_h, pad_w = determine_padding(self.filter_shape, output_shape=self.padding)
        output_height = (height + np.sum(pad_h) - self.filter_shape[0]) / self.stride + 1
        output_width = (width + np.sum(pad_w) - self.filter_shape[1]) / self.stride + 1
        return self.n_filters, int(output_height), int(output_width)


  
 
  • 1
  • 2
  • 3
  • 4
  • 5
  • 6
  • 7
  • 8
  • 9
  • 10
  • 11
  • 12
  • 13
  • 14
  • 15
  • 16
  • 17
  • 18
  • 19
  • 20
  • 21
  • 22
  • 23
  • 24
  • 25
  • 26
  • 27
  • 28
  • 29
  • 30
  • 31
  • 32
  • 33
  • 34
  • 35
  • 36
  • 37
  • 38
  • 39
  • 40
  • 41
  • 42
  • 43
  • 44
  • 45
  • 46
  • 47
  • 48
  • 49
  • 50
  • 51
  • 52
  • 53
  • 54
  • 55
  • 56
  • 57
  • 58
  • 59
  • 60
  • 61
  • 62
  • 63
  • 64
  • 65
  • 66
  • 67
  • 68
  • 69
  • 70
  • 71
  • 72
  • 73
  • 74
  • 75
  • 76
  • 77
  • 78
  • 79
  • 80
  • 81
  • 82
  • 83
  • 84
  • 85
  • 86
  • 87
  • 88
  • 89

文章来源: wanghao.blog.csdn.net,作者:AI浩,版权归原作者所有,如需转载,请联系作者。

原文链接:wanghao.blog.csdn.net/article/details/120322026

【版权声明】本文为华为云社区用户转载文章,如果您发现本社区中有涉嫌抄袭的内容,欢迎发送邮件进行举报,并提供相关证据,一经查实,本社区将立刻删除涉嫌侵权内容,举报邮箱: cloudbbs@huaweicloud.com
  • 点赞
  • 收藏
  • 关注作者

评论(0

0/1000
抱歉,系统识别当前为高风险访问,暂不支持该操作

全部回复

上滑加载中

设置昵称

在此一键设置昵称,即可参与社区互动!

*长度不超过10个汉字或20个英文字符,设置后3个月内不可修改。

*长度不超过10个汉字或20个英文字符,设置后3个月内不可修改。