'''Some helper functions for PyTorch, including:
    - get_mean_and_std: calculate the mean and std value of dataset.
    - msr_init: net parameter initialization.
    - progress_bar: progress bar mimic xlua.progress.
'''
import os
import sys
import time
import math

import logging
from datetime import datetime
import torch
import numpy as np
from torch.nn import Parameter


def get_logger(out_dir):
    logger = logging.getLogger('Exp')
    logger.setLevel(logging.INFO)
    formatter = logging.Formatter("%(asctime)s %(levelname)s %(message)s")

    ts = str(datetime.now()).split(".")[0].replace(" ", "_")
    ts = ts.replace(":", "_").replace("-", "_")
    file_path = os.path.join(out_dir, "run_{}.log".format(ts)) if os.path.isdir(out_dir) else out_dir.replace('.pth.tar', '')
    file_hdlr = logging.FileHandler(file_path)
    file_hdlr.setFormatter(formatter)

    strm_hdlr = logging.StreamHandler(sys.stdout)
    strm_hdlr.setFormatter(formatter)

    logger.addHandler(file_hdlr)
    logger.addHandler(strm_hdlr)
    return logger


class AverageMeter(object):
    """Computes and stores the average and current value"""
    def __init__(self):
        self.reset()

    def reset(self):
        self.val = 0
        self.avg = 0
        self.sum = 0
        self.count = 0

    def update(self, val, n=1):
        self.val = val
        self.sum += val * n
        self.count += n
        self.avg = self.sum / self.count


def accuracy(output, target, topk=(1,)):
    """Computes the accuracy over the k top predictions for the specified values of k"""
    with torch.no_grad():
        maxk = max(topk)
        batch_size = target.size()[0]

        _, pred = output.topk(maxk, 1, True, True)
        pred = pred.t()
        correct = pred.eq(target.view(1, -1).expand_as(pred))

        res = []
        for k in topk:
            correct_k = correct[:k].view(-1).float().sum(0, keepdim=True)
            res.append(correct_k.mul_(100.0 / batch_size))
        return res


def update_lr(iteration, warmup_iter, total_iter, max_lr, min_lr) :
    if iteration < warmup_iter:
        current_lr = max_lr * iteration / warmup_iter 
    else:
        current_lr = min_lr + (max_lr - min_lr) * 0.5 * \
            (1. + math.cos(math.pi * (iteration - warmup_iter) / (total_iter - warmup_iter)))
    return current_lr


def adjust_learning_rate(optimizer, iteration, warmup_iter, total_iter, max_lr, min_lr):
    """Decay the learning rate with half-cycle cosine after warmup"""
    current_lr = update_lr(iteration, warmup_iter, total_iter, max_lr, min_lr)
    for param_group in optimizer.param_groups:
        if "lr_scale" in param_group:
            param_group["lr"] = current_lr * param_group["lr_scale"]
        else:
            param_group["lr"] = current_lr
    return current_lr

    
def get_2d_sincos_pos_embed(embed_dim, grid_size, cls_token=False):
    """
    grid_size: int of the grid height and width
    return:
    pos_embed: [grid_size*grid_size, embed_dim] or [1+grid_size*grid_size, embed_dim] (w/ or w/o cls_token)
    """
    grid_h = np.arange(grid_size, dtype=np.float32)
    grid_w = np.arange(grid_size, dtype=np.float32)
    grid = np.meshgrid(grid_w, grid_h)  # here w goes first
    grid = np.stack(grid, axis=0)

    grid = grid.reshape([2, 1, grid_size, grid_size])
    pos_embed = get_2d_sincos_pos_embed_from_grid(embed_dim, grid)
    if cls_token:
        pos_embed = np.concatenate([np.zeros([1, embed_dim]), pos_embed], axis=0)
    return pos_embed


def get_2d_sincos_pos_embed_from_grid(embed_dim, grid):
    assert embed_dim % 2 == 0

    # use half of dimensions to encode grid_h
    emb_h = get_1d_sincos_pos_embed_from_grid(embed_dim // 2, grid[0])  # (H*W, D/2)
    emb_w = get_1d_sincos_pos_embed_from_grid(embed_dim // 2, grid[1])  # (H*W, D/2)

    emb = np.concatenate([emb_h, emb_w], axis=1) # (H*W, D)
    return emb


def get_1d_sincos_pos_embed_from_grid(embed_dim, pos):
    """
    embed_dim: output dimension for each position
    pos: a list of positions to be encoded: size (M,)
    out: (M, D)
    """
    assert embed_dim % 2 == 0
    omega = np.arange(embed_dim // 2, dtype=float)
    omega /= embed_dim / 2.
    omega = 1. / 10000**omega  # (D/2,)

    pos = pos.reshape(-1)  # (M,)
    out = np.einsum('m,d->md', pos, omega)  # (M, D/2), outer product

    emb_sin = np.sin(out) # (M, D/2)
    emb_cos = np.cos(out) # (M, D/2)

    emb = np.concatenate([emb_sin, emb_cos], axis=1)  # (M, D)
    return emb

# --------------------------------------------------------
# Interpolate position embeddings for high-resolution
# References:
# DeiT: https://github.com/facebookresearch/deit
# --------------------------------------------------------
def interpolate_pos_embed(model, checkpoint_model):
    if 'pos_embed' in checkpoint_model:
        pos_embed_checkpoint = checkpoint_model['pos_embed']
        embedding_size = pos_embed_checkpoint.shape[-1]
        num_patches = model.patch_embed.num_patches
        num_extra_tokens = model.pos_embed.shape[-2] - num_patches
        # height (== width) for the checkpoint position embedding
        orig_size = int((pos_embed_checkpoint.shape[-2] - num_extra_tokens) ** 0.5)
        # height (== width) for the new position embedding
        new_size = int(num_patches ** 0.5)
        # class_token and dist_token are kept unchanged
        if orig_size != new_size:
            print("Position interpolate from %dx%d to %dx%d" % (orig_size, orig_size, new_size, new_size))
            extra_tokens = pos_embed_checkpoint[:, :num_extra_tokens]
            # only the position tokens are interpolated
            pos_tokens = pos_embed_checkpoint[:, num_extra_tokens:]
            pos_tokens = pos_tokens.reshape(-1, orig_size, orig_size, embedding_size).permute(0, 3, 1, 2)
            pos_tokens = torch.nn.functional.interpolate(
                pos_tokens, size=(new_size, new_size), mode='bicubic', align_corners=False)
            pos_tokens = pos_tokens.permute(0, 2, 3, 1).flatten(1, 2)
            new_pos_embed = torch.cat((extra_tokens, pos_tokens), dim=1)
            checkpoint_model['pos_embed'] = new_pos_embed


def load_my_state_dict(net, state_dict):
    own_state = net.state_dict()
    for name, param in state_dict.items():
        name = name.replace('module.','')
        if name not in own_state:
            continue
        if isinstance(param, Parameter):
            # backwards compatibility for serialized parameters
            param = param.data
        own_state[name].copy_(param)

# Fix for non-interactive environments
try:
    _, term_width = os.popen('stty size', 'r').read().split()
    term_width = int(term_width)
except ValueError:
    term_width = 80  # Set a default value if the stty command fails

TOTAL_BAR_LENGTH = 65.
last_time = time.time()
begin_time = last_time


def progress_bar(current, total, msg=None):
    global last_time, begin_time
    if current == 0:
        begin_time = time.time()  # reset for new bar.

    cur_len = int(TOTAL_BAR_LENGTH*current/total)
    rest_len = int(TOTAL_BAR_LENGTH - cur_len) - 1

    sys.stdout.write(' [')
    for i in range(cur_len):
        sys.stdout.write('=')
    sys.stdout.write('>')
    for i in range(rest_len):
        sys.stdout.write('.')
    sys.stdout.write(']')

    cur_time = time.time()
    step_time = cur_time - last_time
    last_time = cur_time
    tot_time = cur_time - begin_time

    L = []
    L.append('  Step: %s' % format_time(step_time))
    L.append(' | Tot: %s' % format_time(tot_time))
    if msg:
        L.append(' | ' + msg)

    msg = ''.join(L)
    sys.stdout.write(msg)
    for i in range(term_width-int(TOTAL_BAR_LENGTH)-len(msg)-3):
        sys.stdout.write(' ')

    # Go back to the center of the bar.
    for i in range(term_width-int(TOTAL_BAR_LENGTH/2)+2):
        sys.stdout.write('\b')
    sys.stdout.write(' %d/%d ' % (current+1, total))

    if current < total-1:
        sys.stdout.write('\r')
    else:
        sys.stdout.write('\n')
    sys.stdout.flush()


def format_time(seconds):
    days = int(seconds / 3600/24)
    seconds = seconds - days*3600*24
    hours = int(seconds / 3600)
    seconds = seconds - hours*3600
    minutes = int(seconds / 60)
    seconds = seconds - minutes*60
    secondsf = int(seconds)
    seconds = seconds - secondsf
    millis = int(seconds*1000)

    f = ''
    i = 1
    if days > 0:
        f += str(days) + 'D'
        i += 1
    if hours > 0 and i <= 2:
        f += str(hours) + 'h'
        i += 1
    if minutes > 0 and i <= 2:
        f += str(minutes) + 'm'
        i += 1
    if secondsf > 0 and i <= 2:
        f += str(secondsf) + 's'
        i += 1
    if millis > 0 and i <= 2:
        f += str(millis) + 'ms'
        i += 1
    if f == '':
        f = '0ms'
    return f