for (size_t y = 0; y < out_height; ++y) {
    for (size_t x = 0; x < out_width; ++x) {
        for (size_t i = 0; i < pool_y; ++i) {
            for (size_t j = 0; j < pool_x; ++j) {
                for (size_t c = 0; c < depth; ++c) {
                    float value = in[y * pool_y + i][x * pool_x + j][c];
                    out[y][x][c] = max(out[y][x][c], value);
                }
            }
        }
    }
}