import os
import math
import random
import numpy as np
import torch
import cv2
from torchvision.utils import make_grid
from datetime import datetime
# import torchvision.transforms as transforms
import matplotlib.pyplot as plt

'''
modified by Kai Zhang (github: https://github.com/cszn)
03/03/2019
https://github.com/twhui/SRGAN-pyTorch
https://github.com/xinntao/BasicSR
'''

IMG_EXTENSIONS = ['.jpg', '.JPG', '.jpeg', '.JPEG', '.png', '.PNG', '.ppm', '.PPM', '.bmp', '.BMP']


def is_image_file(filename):
    return any(filename.endswith(extension) for extension in IMG_EXTENSIONS)


def get_timestamp():
    return datetime.now().strftime('%y%m%d-%H%M%S')


def imshow(x, title=None, cbar=False, figsize=None):
    plt.figure(figsize=figsize)
    plt.imshow(np.squeeze(x), interpolation='nearest', cmap='gray')
    if title:
        plt.title(title)
    if cbar:
        plt.colorbar()
    plt.show()


'''
# =======================================
# get image pathes of files
# =======================================
'''


def get_image_paths(dataroot):
    paths = None  # return None if dataroot is None
    if dataroot is not None:
        paths = sorted(_get_paths_from_images(dataroot))
    return paths


def _get_paths_from_images(path):
    assert os.path.isdir(path), '{:s} is not a valid directory'.format(path)
    images = []
    for dirpath, _, fnames in sorted(os.walk(path)):
        for fname in sorted(fnames):
            if is_image_file(fname):
                img_path = os.path.join(dirpath, fname)
                images.append(img_path)
    assert images, '{:s} has no valid image file'.format(path)
    return images


'''
# =======================================
# makedir
# =======================================
'''


def mkdir(path):
    if not os.path.exists(path):
        os.makedirs(path)


def mkdirs(paths):
    if isinstance(paths, str):
        mkdir(paths)
    else:
        for path in paths:
            mkdir(path)


def mkdir_and_rename(path):
    if os.path.exists(path):
        new_name = path + '_archived_' + get_timestamp()
        print('Path already exists. Rename it to [{:s}]'.format(new_name))
        os.rename(path, new_name)
    os.makedirs(path)


'''
# =======================================
# read image from path
# Note: opencv is fast
# but read BGR numpy image
# =======================================
'''


# ----------------------------------------
# get single image of size HxWxn_channles (BGR)
# ----------------------------------------
def read_img(path):
    # read image by cv2
    # return: Numpy float32, HWC, BGR, [0,1]
    img = cv2.imread(path, cv2.IMREAD_UNCHANGED)  # cv2.IMREAD_GRAYSCALE
    img = img.astype(np.float32) / 255.
    if img.ndim == 2:
        img = np.expand_dims(img, axis=2)
    # some images have 4 channels
    if img.shape[2] > 3:
        img = img[:, :, :3]
    return img


# ----------------------------------------
# get uint8 image of size HxWxn_channles (RGB)
# ----------------------------------------
def imread_uint(path, n_channels=3):
    #  input: path
    # output: HxWx3(RGB or GGG), or HxWx1 (G)
    if n_channels == 1:
        img = cv2.imread(path, 0)  # cv2.IMREAD_GRAYSCALE
        img = np.expand_dims(img, axis=2)  # HxWx1
    elif n_channels == 3:
        img = cv2.imread(path, cv2.IMREAD_UNCHANGED)  # BGR or G
        if img.ndim == 2:
            img = cv2.cvtColor(img, cv2.COLOR_GRAY2RGB)  # GGG
        else:
            img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)  # RGB
    return img


def imsave(img, img_path):
    img = np.squeeze(img)
    if img.ndim == 3:
        img = img[:, :, [2, 1, 0]]
    cv2.imwrite(img_path, img)


'''
# =======================================
# numpy(single) <--->  numpy(uint)
# numpy(single) <--->  tensor
# numpy(uint)   <--->  tensor
# =======================================
'''


# --------------------------------
# numpy(single) <--->  numpy(uint)
# --------------------------------


def uint2single(img):

    return np.float32(img/255.)


def uint2single1(img):

    return np.float32(np.squeeze(img)/255.)


def single2uint(img):

    return np.uint8((img.clip(0, 1)*255.).round())


def uint162single(img):

    return np.float32(img/65535.)


def single2uint16(img):

    return np.uint8((img.clip(0, 1)*65535.).round())


# --------------------------------
# numpy(uint) <--->  tensor
# uint (HxWxn_channels (RGB) or G)
# --------------------------------


# convert uint (HxWxn_channels) to 4-dimensional torch tensor
def uint2tensor4(img):
    if img.ndim == 2:
        img = np.expand_dims(img, axis=2)
    return torch.from_numpy(np.ascontiguousarray(img)).permute(2, 0, 1).float().div(255.).unsqueeze(0)


# convert uint (HxWxn_channels) to 3-dimensional torch tensor
def uint2tensor3(img):
    if img.ndim == 2:
        img = np.expand_dims(img, axis=2)
    return torch.from_numpy(np.ascontiguousarray(img)).permute(2, 0, 1).float().div(255.)


# convert torch tensor to uint
def tensor2uint(img):
    img = img.data.squeeze().float().clamp_(0, 1).cpu().numpy()
    if img.ndim == 3:
        img = np.transpose(img, (1, 2, 0))
    return np.uint8((img*255.0).round())


# --------------------------------
# numpy(single) <--->  tensor
# single (HxWxn_channels (RGB) or G)
# --------------------------------


# convert single (HxWxn_channels) to 4-dimensional torch tensor
def single2tensor4(img):
    return torch.from_numpy(np.ascontiguousarray(img)).permute(2, 0, 1).float().unsqueeze(0)


# convert single (HxWxn_channels) to 3-dimensional torch tensor
def single2tensor3(img):
    return torch.from_numpy(np.ascontiguousarray(img)).permute(2, 0, 1).float()


# convert torch tensor to single
def tensor2single(img):
    img = img.data.squeeze().float().clamp_(0, 1).cpu().numpy()
    if img.ndim == 3:
        img = np.transpose(img, (1, 2, 0))

    return img

def tensor2single3(img):
    img = img.data.squeeze().float().clamp_(0, 1).cpu().numpy()
    if img.ndim == 3:
        img = np.transpose(img, (1, 2, 0))
    elif img.ndim == 2:
        img = np.expand_dims(img, axis=2)
    return img


# from skimage.io import imread, imsave
def tensor2img(tensor, out_type=np.uint8, min_max=(0, 1)):
    '''
    Converts a torch Tensor into an image Numpy array of BGR channel order
    Input: 4D(B,(3/1),H,W), 3D(C,H,W), or 2D(H,W), any range, RGB channel order
    Output: 3D(H,W,C) or 2D(H,W), [0,255], np.uint8 (default)
    '''
    tensor = tensor.squeeze().float().cpu().clamp_(*min_max)  # squeeze first, then clamp
    tensor = (tensor - min_max[0]) / (min_max[1] - min_max[0])  # to range [0,1]
    n_dim = tensor.dim()
    if n_dim == 4:
        n_img = len(tensor)
        img_np = make_grid(tensor, nrow=int(math.sqrt(n_img)), normalize=False).numpy()
        img_np = np.transpose(img_np[[2, 1, 0], :, :], (1, 2, 0))  # HWC, BGR
    elif n_dim == 3:
        img_np = tensor.numpy()
        img_np = np.transpose(img_np[[2, 1, 0], :, :], (1, 2, 0))  # HWC, BGR
    elif n_dim == 2:
        img_np = tensor.numpy()
    else:
        raise TypeError(
            'Only support 4D, 3D and 2D tensor. But received with dimension: {:d}'.format(n_dim))
    if out_type == np.uint8:
        img_np = (img_np * 255.0).round()
        # Important. Unlike matlab, numpy.uint8() WILL NOT round by default.
    return img_np.astype(out_type)


'''
# =======================================
# image processing process on numpy image
# augment(img_list, hflip=True, rot=True):
# =======================================
'''


def augment_img(img, mode=0):
    if mode == 0:
        return img
    elif mode == 1:
        return np.flipud(np.rot90(img))
    elif mode == 2:
        return np.flipud(img)
    elif mode == 3:
        return np.rot90(img, k=3)
    elif mode == 4:
        return np.flipud(np.rot90(img, k=2))
    elif mode == 5:
        return np.rot90(img)
    elif mode == 6:
        return np.rot90(img, k=2)
    elif mode == 7:
        return np.flipud(np.rot90(img, k=3))


def augment_img_np3(img, mode=0):
    if mode == 0:
        return img
    elif mode == 1:
        return img.transpose(1, 0, 2)
    elif mode == 2:
        return img[::-1, :, :]
    elif mode == 3:
        img = img[::-1, :, :]
        img = img.transpose(1, 0, 2)
        return img
    elif mode == 4:
        return img[:, ::-1, :]
    elif mode == 5:
        img = img[:, ::-1, :]
        img = img.transpose(1, 0, 2)
        return img
    elif mode == 6:
        img = img[:, ::-1, :]
        img = img[::-1, :, :]
        return img
    elif mode == 7:
        img = img[:, ::-1, :]
        img = img[::-1, :, :]
        img = img.transpose(1, 0, 2)
        return img


def augment_img_tensor(img, mode=0):
    img_size = img.size()
    img_np = img.data.cpu().numpy()
    if len(img_size) == 3:
        img_np = np.transpose(img_np, (1, 2, 0))
    elif len(img_size) == 4:
        img_np = np.transpose(img_np, (2, 3, 1, 0))
    img_np = augment_img(img_np, mode=mode)
    img_tensor = torch.from_numpy(np.ascontiguousarray(img_np))
    if len(img_size) == 3:
        img_tensor = img_tensor.permute(2, 0, 1)
    elif len(img_size) == 4:
        img_tensor = img_tensor.permute(3, 2, 0, 1)

    return img_tensor.type_as(img)


def augment_imgs(img_list, hflip=True, rot=True):
    # horizontal flip OR rotate
    hflip = hflip and random.random() < 0.5
    vflip = rot and random.random() < 0.5
    rot90 = rot and random.random() < 0.5

    def _augment(img):
        if hflip:
            img = img[:, ::-1, :]
        if vflip:
            img = img[::-1, :, :]
        if rot90:
            img = img.transpose(1, 0, 2)
        return img

    return [_augment(img) for img in img_list]


'''
# =======================================
# image processing process on numpy image
# channel_convert(in_c, tar_type, img_list):
# rgb2ycbcr(img, only_y=True):
# bgr2ycbcr(img, only_y=True):
# ycbcr2rgb(img):
# modcrop(img_in, scale):
# =======================================
'''


def rgb2ycbcr(img, only_y=True):
    '''same as matlab rgb2ycbcr
    only_y: only return Y channel
    Input:
        uint8, [0, 255]
        float, [0, 1]
    '''
    in_img_type = img.dtype
    img.astype(np.float32)
    if in_img_type != np.uint8:
        img *= 255.
    # convert
    if only_y:
        rlt = np.dot(img, [65.481, 128.553, 24.966]) / 255.0 + 16.0
    else:
        rlt = np.matmul(img, [[65.481, -37.797, 112.0], [128.553, -74.203, -93.786],
                              [24.966, 112.0, -18.214]]) / 255.0 + [16, 128, 128]
    if in_img_type == np.uint8:
        rlt = rlt.round()
    else:
        rlt /= 255.
    return rlt.astype(in_img_type)


def ycbcr2rgb(img):
    '''same as matlab ycbcr2rgb
    Input:
        uint8, [0, 255]
        float, [0, 1]
    '''
    in_img_type = img.dtype
    img.astype(np.float32)
    if in_img_type != np.uint8:
        img *= 255.
    # convert
    rlt = np.matmul(img, [[0.00456621, 0.00456621, 0.00456621], [0, -0.00153632, 0.00791071],
                          [0.00625893, -0.00318811, 0]]) * 255.0 + [-222.921, 135.576, -276.836]
    if in_img_type == np.uint8:
        rlt = rlt.round()
    else:
        rlt /= 255.
    return rlt.astype(in_img_type)


def bgr2ycbcr(img, only_y=True):
    '''bgr version of rgb2ycbcr
    only_y: only return Y channel
    Input:
        uint8, [0, 255]
        float, [0, 1]
    '''
    in_img_type = img.dtype
    img.astype(np.float32)
    if in_img_type != np.uint8:
        img *= 255.
    # convert
    if only_y:
        rlt = np.dot(img, [24.966, 128.553, 65.481]) / 255.0 + 16.0
    else:
        rlt = np.matmul(img, [[24.966, 112.0, -18.214], [128.553, -74.203, -93.786],
                              [65.481, -37.797, 112.0]]) / 255.0 + [16, 128, 128]
    if in_img_type == np.uint8:
        rlt = rlt.round()
    else:
        rlt /= 255.
    return rlt.astype(in_img_type)


def modcrop(img_in, scale):
    # img_in: Numpy, HWC or HW
    img = np.copy(img_in)
    if img.ndim == 2:
        H, W = img.shape
        H_r, W_r = H % scale, W % scale
        img = img[:H - H_r, :W - W_r]
    elif img.ndim == 3:
        H, W, C = img.shape
        H_r, W_r = H % scale, W % scale
        img = img[:H - H_r, :W - W_r, :]
    else:
        raise ValueError('Wrong img ndim: [{:d}].'.format(img.ndim))
    return img


def shave(img_in, border=0):
    # img_in: Numpy, HWC or HW
    img = np.copy(img_in)
    h, w = img.shape[:2]
    img = img[border:h-border, border:w-border]
    return img


def channel_convert(in_c, tar_type, img_list):
    # conversion among BGR, gray and y
    if in_c == 3 and tar_type == 'gray':  # BGR to gray
        gray_list = [cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) for img in img_list]
        return [np.expand_dims(img, axis=2) for img in gray_list]
    elif in_c == 3 and tar_type == 'y':  # BGR to y
        y_list = [bgr2ycbcr(img, only_y=True) for img in img_list]
        return [np.expand_dims(img, axis=2) for img in y_list]
    elif in_c == 1 and tar_type == 'RGB':  # gray/y to BGR
        return [cv2.cvtColor(img, cv2.COLOR_GRAY2BGR) for img in img_list]
    else:
        return img_list


'''
# =======================================
# metric, PSNR and SSIM
# =======================================
'''


# ----------
# PSNR
# ----------
def calculate_psnr(img1, img2, border=0):
    # img1 and img2 have range [0, 255]
    if not img1.shape == img2.shape:
        raise ValueError('Input images must have the same dimensions.')
    h, w = img1.shape[:2]
    img1 = img1[border:h-border, border:w-border]
    img2 = img2[border:h-border, border:w-border]

    img1 = img1.astype(np.float64)
    img2 = img2.astype(np.float64)
    mse = np.mean((img1 - img2)**2)
    if mse == 0:
        return float('inf')
    return 20 * math.log10(255.0 / math.sqrt(mse))


# ----------
# SSIM
# ----------
def calculate_ssim(img1, img2, border=0):
    '''calculate SSIM
    the same outputs as MATLAB's
    img1, img2: [0, 255]
    '''
    if not img1.shape == img2.shape:
        raise ValueError('Input images must have the same dimensions.')
    h, w = img1.shape[:2]
    img1 = img1[border:h-border, border:w-border]
    img2 = img2[border:h-border, border:w-border]

    if img1.ndim == 2:
        return ssim(img1, img2)
    elif img1.ndim == 3:
        if img1.shape[2] == 3:
            ssims = []
            for i in range(3):
                ssims.append(ssim(img1, img2))
            return np.array(ssims).mean()
        elif img1.shape[2] == 1:
            return ssim(np.squeeze(img1), np.squeeze(img2))
    else:
        raise ValueError('Wrong input image dimensions.')


def ssim(img1, img2):
    C1 = (0.01 * 255)**2
    C2 = (0.03 * 255)**2

    img1 = img1.astype(np.float64)
    img2 = img2.astype(np.float64)
    kernel = cv2.getGaussianKernel(11, 1.5)
    window = np.outer(kernel, kernel.transpose())

    mu1 = cv2.filter2D(img1, -1, window)[5:-5, 5:-5]  # valid
    mu2 = cv2.filter2D(img2, -1, window)[5:-5, 5:-5]
    mu1_sq = mu1**2
    mu2_sq = mu2**2
    mu1_mu2 = mu1 * mu2
    sigma1_sq = cv2.filter2D(img1**2, -1, window)[5:-5, 5:-5] - mu1_sq
    sigma2_sq = cv2.filter2D(img2**2, -1, window)[5:-5, 5:-5] - mu2_sq
    sigma12 = cv2.filter2D(img1 * img2, -1, window)[5:-5, 5:-5] - mu1_mu2

    ssim_map = ((2 * mu1_mu2 + C1) * (2 * sigma12 + C2)) / ((mu1_sq + mu2_sq + C1) *
                                                            (sigma1_sq + sigma2_sq + C2))
    return ssim_map.mean()


'''
# =======================================
# pytorch version of matlab imresize
# =======================================
'''


# matlab 'imresize' function, now only support 'bicubic'
def cubic(x):
    absx = torch.abs(x)
    absx2 = absx**2
    absx3 = absx**3
    return (1.5*absx3 - 2.5*absx2 + 1) * ((absx <= 1).type_as(absx)) + \
        (-0.5*absx3 + 2.5*absx2 - 4*absx + 2) * (((absx > 1)*(absx <= 2)).type_as(absx))


def calculate_weights_indices(in_length, out_length, scale, kernel, kernel_width, antialiasing):
    if (scale < 1) and (antialiasing):
        # Use a modified kernel to simultaneously interpolate and antialias- larger kernel width
        kernel_width = kernel_width / scale

    # Output-space coordinates
    x = torch.linspace(1, out_length, out_length)

    # Input-space coordinates. Calculate the inverse mapping such that 0.5
    # in output space maps to 0.5 in input space, and 0.5+scale in output
    # space maps to 1.5 in input space.
    u = x / scale + 0.5 * (1 - 1 / scale)

    # What is the left-most pixel that can be involved in the computation?
    left = torch.floor(u - kernel_width / 2)

    # What is the maximum number of pixels that can be involved in the
    # computation?  Note: it's OK to use an extra pixel here; if the
    # corresponding weights are all zero, it will be eliminated at the end
    # of this function.
    P = math.ceil(kernel_width) + 2

    # The indices of the input pixels involved in computing the k-th output
    # pixel are in row k of the indices matrix.
    indices = left.view(out_length, 1).expand(out_length, P) + torch.linspace(0, P - 1, P).view(
        1, P).expand(out_length, P)

    # The weights used to compute the k-th output pixel are in row k of the
    # weights matrix.
    distance_to_center = u.view(out_length, 1).expand(out_length, P) - indices
    # apply cubic kernel
    if (scale < 1) and (antialiasing):
        weights = scale * cubic(distance_to_center * scale)
    else:
        weights = cubic(distance_to_center)
    # Normalize the weights matrix so that each row sums to 1.
    weights_sum = torch.sum(weights, 1).view(out_length, 1)
    weights = weights / weights_sum.expand(out_length, P)

    # If a column in weights is all zero, get rid of it. only consider the first and last column.
    weights_zero_tmp = torch.sum((weights == 0), 0)
    if not math.isclose(weights_zero_tmp[0], 0, rel_tol=1e-6):
        indices = indices.narrow(1, 1, P - 2)
        weights = weights.narrow(1, 1, P - 2)
    if not math.isclose(weights_zero_tmp[-1], 0, rel_tol=1e-6):
        indices = indices.narrow(1, 0, P - 2)
        weights = weights.narrow(1, 0, P - 2)
    weights = weights.contiguous()
    indices = indices.contiguous()
    sym_len_s = -indices.min() + 1
    sym_len_e = indices.max() - in_length
    indices = indices + sym_len_s - 1
    return weights, indices, int(sym_len_s), int(sym_len_e)


# --------------------------------
# imresize for tensor image
# --------------------------------
def imresize(img, scale, antialiasing=True):
    # Now the scale should be the same for H and W
    # input: img: pytorch tensor, CHW or HW [0,1]
    # output: CHW or HW [0,1] w/o round
    need_squeeze = True if img.dim() == 2 else False
    if need_squeeze:
        img.unsqueeze_(0)
    in_C, in_H, in_W = img.size()
    out_C, out_H, out_W = in_C, math.ceil(in_H * scale), math.ceil(in_W * scale)
    kernel_width = 4
    kernel = 'cubic'

    # Return the desired dimension order for performing the resize.  The
    # strategy is to perform the resize first along the dimension with the
    # smallest scale factor.
    # Now we do not support this.

    # get weights and indices
    weights_H, indices_H, sym_len_Hs, sym_len_He = calculate_weights_indices(
        in_H, out_H, scale, kernel, kernel_width, antialiasing)
    weights_W, indices_W, sym_len_Ws, sym_len_We = calculate_weights_indices(
        in_W, out_W, scale, kernel, kernel_width, antialiasing)
    # process H dimension
    # symmetric copying
    img_aug = torch.FloatTensor(in_C, in_H + sym_len_Hs + sym_len_He, in_W)
    img_aug.narrow(1, sym_len_Hs, in_H).copy_(img)

    sym_patch = img[:, :sym_len_Hs, :]
    inv_idx = torch.arange(sym_patch.size(1) - 1, -1, -1).long()
    sym_patch_inv = sym_patch.index_select(1, inv_idx)
    img_aug.narrow(1, 0, sym_len_Hs).copy_(sym_patch_inv)

    sym_patch = img[:, -sym_len_He:, :]
    inv_idx = torch.arange(sym_patch.size(1) - 1, -1, -1).long()
    sym_patch_inv = sym_patch.index_select(1, inv_idx)
    img_aug.narrow(1, sym_len_Hs + in_H, sym_len_He).copy_(sym_patch_inv)

    out_1 = torch.FloatTensor(in_C, out_H, in_W)
    kernel_width = weights_H.size(1)
    for i in range(out_H):
        idx = int(indices_H[i][0])
        for j in range(out_C):
            out_1[j, i, :] = img_aug[j, idx:idx + kernel_width, :].transpose(0, 1).mv(weights_H[i])

    # process W dimension
    # symmetric copying
    out_1_aug = torch.FloatTensor(in_C, out_H, in_W + sym_len_Ws + sym_len_We)
    out_1_aug.narrow(2, sym_len_Ws, in_W).copy_(out_1)

    sym_patch = out_1[:, :, :sym_len_Ws]
    inv_idx = torch.arange(sym_patch.size(2) - 1, -1, -1).long()
    sym_patch_inv = sym_patch.index_select(2, inv_idx)
    out_1_aug.narrow(2, 0, sym_len_Ws).copy_(sym_patch_inv)

    sym_patch = out_1[:, :, -sym_len_We:]
    inv_idx = torch.arange(sym_patch.size(2) - 1, -1, -1).long()
    sym_patch_inv = sym_patch.index_select(2, inv_idx)
    out_1_aug.narrow(2, sym_len_Ws + in_W, sym_len_We).copy_(sym_patch_inv)

    out_2 = torch.FloatTensor(in_C, out_H, out_W)
    kernel_width = weights_W.size(1)
    for i in range(out_W):
        idx = int(indices_W[i][0])
        for j in range(out_C):
            out_2[j, :, i] = out_1_aug[j, :, idx:idx + kernel_width].mv(weights_W[i])
    if need_squeeze:
        out_2.squeeze_()
    return out_2


# --------------------------------
# imresize for numpy image
# --------------------------------
def imresize_np(img, scale, antialiasing=True):
    # Now the scale should be the same for H and W
    # input: img: Numpy, HWC or HW [0,1]
    # output: HWC or HW [0,1] w/o round
    img = torch.from_numpy(img)
    need_squeeze = True if img.dim() == 2 else False
    if need_squeeze:
        img.unsqueeze_(2)

    in_H, in_W, in_C = img.size()
    out_C, out_H, out_W = in_C, math.ceil(in_H * scale), math.ceil(in_W * scale)
    kernel_width = 4
    kernel = 'cubic'

    # Return the desired dimension order for performing the resize.  The
    # strategy is to perform the resize first along the dimension with the
    # smallest scale factor.
    # Now we do not support this.

    # get weights and indices
    weights_H, indices_H, sym_len_Hs, sym_len_He = calculate_weights_indices(
        in_H, out_H, scale, kernel, kernel_width, antialiasing)
    weights_W, indices_W, sym_len_Ws, sym_len_We = calculate_weights_indices(
        in_W, out_W, scale, kernel, kernel_width, antialiasing)
    # process H dimension
    # symmetric copying
    img_aug = torch.FloatTensor(in_H + sym_len_Hs + sym_len_He, in_W, in_C)
    img_aug.narrow(0, sym_len_Hs, in_H).copy_(img)

    sym_patch = img[:sym_len_Hs, :, :]
    inv_idx = torch.arange(sym_patch.size(0) - 1, -1, -1).long()
    sym_patch_inv = sym_patch.index_select(0, inv_idx)
    img_aug.narrow(0, 0, sym_len_Hs).copy_(sym_patch_inv)

    sym_patch = img[-sym_len_He:, :, :]
    inv_idx = torch.arange(sym_patch.size(0) - 1, -1, -1).long()
    sym_patch_inv = sym_patch.index_select(0, inv_idx)
    img_aug.narrow(0, sym_len_Hs + in_H, sym_len_He).copy_(sym_patch_inv)

    out_1 = torch.FloatTensor(out_H, in_W, in_C)
    kernel_width = weights_H.size(1)
    for i in range(out_H):
        idx = int(indices_H[i][0])
        for j in range(out_C):
            out_1[i, :, j] = img_aug[idx:idx + kernel_width, :, j].transpose(0, 1).mv(weights_H[i])

    # process W dimension
    # symmetric copying
    out_1_aug = torch.FloatTensor(out_H, in_W + sym_len_Ws + sym_len_We, in_C)
    out_1_aug.narrow(1, sym_len_Ws, in_W).copy_(out_1)

    sym_patch = out_1[:, :sym_len_Ws, :]
    inv_idx = torch.arange(sym_patch.size(1) - 1, -1, -1).long()
    sym_patch_inv = sym_patch.index_select(1, inv_idx)
    out_1_aug.narrow(1, 0, sym_len_Ws).copy_(sym_patch_inv)

    sym_patch = out_1[:, -sym_len_We:, :]
    inv_idx = torch.arange(sym_patch.size(1) - 1, -1, -1).long()
    sym_patch_inv = sym_patch.index_select(1, inv_idx)
    out_1_aug.narrow(1, sym_len_Ws + in_W, sym_len_We).copy_(sym_patch_inv)

    out_2 = torch.FloatTensor(out_H, out_W, in_C)
    kernel_width = weights_W.size(1)
    for i in range(out_W):
        idx = int(indices_W[i][0])
        for j in range(out_C):
            out_2[:, i, j] = out_1_aug[:, idx:idx + kernel_width, j].mv(weights_W[i])
    if need_squeeze:
        out_2.squeeze_()

    return out_2.numpy()


if __name__ == '__main__':
    img = imread_uint('test.bmp',3)