Numpy实现卷积神经网络前向运算

首先是卷积运算

在numpy中通过im2col算法实现。

通过将输入，卷积核拉平做矩阵乘法，得到输出。

import numpy as np


def im2col(image, size, stride=1):
    N, H, W, C = image.shape
    out_h = (H - size) // stride + 1
    out_w = (W - size) // stride + 1

    col = np.zeros((N * out_h * out_w, size * size * C))
    out_size = out_h * out_w
    for h in range(out_h):
        h_start = h*stride
        h_end = h_start + size
        h_next = h*out_w
        for w in range(out_w):
            w_start = w*stride
            w_end = w_start + size
            col[h_next+w::out_size, :] = image[:, h_start:h_end, w_start:w_end, :].reshape(N, -1)
    return col


def conv_forward(X, W, stride=1, padding='same'):
    filters, size, size, C = W.shape
    if padding == 'same':
        p = size // 2
        X = np.pad(X, ((0, 0), (p, p), (p, p), (0, 0)), 'constant')

    N, H_input, W_input, C = X.shape
    col = im2col(X, size, stride)
    logit = np.dot(col, W.reshape(W.shape[0], -1).transpose())
    logit = logit.reshape((N, logit.shape[0] // N, -1))
    out_h = (H_input - size) // stride + 1
    return np.reshape(logit, (N, out_h, -1, filters))


def pooling(X, pool_size, stride=2, pooling='max'):
    N, H_input, W_input, C = X.shape
    # [N*out_size, pool_size*pool_size*C]
    col = im2col(X, pool_size, stride)
    col = col.reshape((col.shape[0], C, -1))
    out_h = (H_input - pool_size) // stride + 1
    if pooling == 'max':
        max_out = np.zeros((col.shape[0], C, 1))
        for row in range(col.shape[0]):
            for c in range(C):
                max_out[row, c, :] = np.max(col[row, c])
        return max_out.reshape((N, out_h, -1, C))
    elif pooling == 'avg':
        avg_out = np.zeros((col.shape[0], C, 1))
        for row in range(col.shape[0]):
            for c in range(C):
                avg_out[row, c, :] = np.average(col[row, c])
        return avg_out.reshape((N, out_h, -1, C))


def main():
    x_data = np.random.randn(10, 224, 224, 3)
    w = np.random.randn(16, 3, 3, 3)
    logit = conv_forward(x_data, w)


if __name__ == '__main__':
    main()