ゼロから作るDeepLearningのCNNのコードです https://github.com/oreilly-japan/deep-learning-from-scratch/blob/471ff64c25d27eaad58d8b5a9e787249db974d44/ch07/apply_filter.py

convolution.py

# coding: utf-8
import numpy as np
from im2col import im2col

class Convolution:
    def __init__(self, W, b, stride=1, pad=0):
        self.W = W
        self.b = b
        self.stride = stride
        self.pad = pad
  
    def forward(self, x):
        FN, C, FH, FW = self.W.shape
        N, C, H, W = x.shape
        out_h = int(1 + (H + 2*self.pad - FH) / self.stride)
        out_w = int(1 + (W + 2*self.pad - FW) / self.stride)

        col = im2col(x, FH, FW, self.stride, self.pad)
        col_W = self.W.reshape(FN, -1).T
        out = np.dot(col, col_W) + self.b

        out = out.reshape(N, out_h, out_w, -1).transpose(0, 3, 1, 2)

        return out

im2col.py

# coding: utf-8
import numpy as np

def im2col(input_data, filter_h, filter_w, stride=1, pad=0):
    """
    Parameters
    ----------
    input_data : (データ数, チャンネル, 高さ, 幅)の4次元配列からなる入力データ
    filter_h : フィルターの高さ
    filter_w : フィルターの幅
    stride : ストライド
    pad : パディング
    Returns
    -------
    col : 2次元配列
    """
    N, C, H, W = input_data.shape
    out_h = (H + 2*pad - filter_h)//stride + 1
    out_w = (W + 2*pad - filter_w)//stride + 1

    img = np.pad(input_data, [(0,0), (0,0), (pad, pad), (pad, pad)], 'constant')
    col = np.zeros((N, C, filter_h, filter_w, out_h, out_w))

    for y in range(filter_h):
        y_max = y + stride*out_h
        for x in range(filter_w):
            x_max = x + stride*out_w
            col[:, :, y, x, :, :] = img[:, :, y:y_max:stride, x:x_max:stride]

    col = col.transpose(0, 4, 5, 1, 2, 3).reshape(N*out_h*out_w, -1)
    return col

pooling.py

# coding: utf-8
import numpy as np
from im2col import im2col

class Pooling:
    def __init__(self, pool_h, pool_w, stride=1, pad=0):
        self.pool_h = pool_h
        self.pool_w = pool_w
        self.stride = stride
        self.pad = pad

    def forward(self, x):
        N, C, H, W = x.shape
        out_h = int(1 + (H - self.pool_h) / self.stride)
        out_w = int(1 + (W - self.pool_w) / self.stride)

        col = im2col(x, self.pool_h, self.pool_w, self.stride, self.pad)
        col = reshape(-1, self.pool_h*self.pool_w)

        out = np.max(col, axis=1)
        out = out.reshape(N, out_h, out_w, C).transpose(0, 3, 1, 2)

        return out