import os

import torch


def init_seeds(seed=0):
    torch.manual_seed(seed)

    # Remove randomness (may be slower on Tesla GPUs) # https://pytorch.org/docs/stable/notes/randomness.html
    if seed == 0:
        torch.backends.cudnn.deterministic = True
        torch.backends.cudnn.benchmark = False


def select_device(device='', apex=False, batch_size=None):
    # device = 'cpu' or '0' or '0,1,2,3'
    cpu_request = device.lower() == 'cpu'
    if device and not cpu_request:  # if device requested other than 'cpu'
        os.environ['CUDA_VISIBLE_DEVICES'] = device  # set environment variable
        assert torch.cuda.is_available(), 'CUDA unavailable, invalid device %s requested' % device  # check availablity

    cuda = False if cpu_request else torch.cuda.is_available()
    if cuda:
        c = 1024 ** 2  # bytes to MB
        ng = torch.cuda.device_count()
        if ng > 1 and batch_size:  # check that batch_size is compatible with device_count
            assert batch_size % ng == 0, 'batch-size %g not multiple of GPU count %g' % (batch_size, ng)
        x = [torch.cuda.get_device_properties(i) for i in range(ng)]
        s = 'Using CUDA ' + ('Apex ' if apex else '')  # apex for mixed precision https://github.com/NVIDIA/apex
        for i in range(0, ng):
            if i == 1:
                s = ' ' * len(s)
            print("%sdevice%g _CudaDeviceProperties(name='%s', total_memory=%dMB)" %
                  (s, i, x[i].name, x[i].total_memory / c))
    else:
        print('Using CPU')

    print('')  # skip a line
    return torch.device('cuda:0' if cuda else 'cpu')


def fuse_conv_and_bn(conv, bn):
    # https://tehnokv.com/posts/fusing-batchnorm-and-conv/
    with torch.no_grad():
        # init
        fusedconv = torch.nn.Conv2d(conv.in_channels,
                                    conv.out_channels,
                                    kernel_size=conv.kernel_size,
                                    stride=conv.stride,
                                    padding=conv.padding,
                                    bias=True)

        # prepare filters
        w_conv = conv.weight.clone().view(conv.out_channels, -1)
        w_bn = torch.diag(bn.weight.div(torch.sqrt(bn.eps + bn.running_var)))
        fusedconv.weight.copy_(torch.mm(w_bn, w_conv).view(fusedconv.weight.size()))

        # prepare spatial bias
        if conv.bias is not None:
            b_conv = conv.bias
        else:
            b_conv = torch.zeros(conv.weight.size(0))
        b_bn = bn.bias - bn.weight.mul(bn.running_mean).div(torch.sqrt(bn.running_var + bn.eps))
        fusedconv.bias.copy_(b_conv + b_bn)

        return fusedconv


def model_info(model, report='summary'):
    # Plots a line-by-line description of a PyTorch model
    n_p = sum(x.numel() for x in model.parameters())  # number parameters
    n_g = sum(x.numel() for x in model.parameters() if x.requires_grad)  # number gradients
    if report is 'full':
        print('%5s %40s %9s %12s %20s %10s %10s' % ('layer', 'name', 'gradient', 'parameters', 'shape', 'mu', 'sigma'))
        for i, (name, p) in enumerate(model.named_parameters()):
            name = name.replace('module_list.', '')
            print('%5g %40s %9s %12g %20s %10.3g %10.3g' %
                  (i, name, p.requires_grad, p.numel(), list(p.shape), p.mean(), p.std()))
    print('Model Summary: %g layers, %g parameters, %g gradients' % (len(list(model.parameters())), n_p, n_g))


def load_classifier(name='resnet101', n=2):
    # Loads a pretrained model reshaped to n-class output
    import pretrainedmodels  # https://github.com/Cadene/pretrained-models.pytorch#torchvision
    model = pretrainedmodels.__dict__[name](num_classes=1000, pretrained='imagenet')

    # Display model properties
    for x in ['model.input_size', 'model.input_space', 'model.input_range', 'model.mean', 'model.std']:
        print(x + ' =', eval(x))

    # Reshape output to n classes
    filters = model.last_linear.weight.shape[1]
    model.last_linear.bias = torch.nn.Parameter(torch.zeros(n))
    model.last_linear.weight = torch.nn.Parameter(torch.zeros(n, filters))
    model.last_linear.out_features = n
    return model


from collections import defaultdict
from torch.optim import Optimizer


class Lookahead(Optimizer):
    def __init__(self, optimizer, k=5, alpha=0.5):
        self.optimizer = optimizer
        self.k = k
        self.alpha = alpha
        self.param_groups = self.optimizer.param_groups
        self.state = defaultdict(dict)
        self.fast_state = self.optimizer.state
        for group in self.param_groups:
            group["counter"] = 0

    def update(self, group):
        for fast in group["params"]:
            param_state = self.state[fast]
            if "slow_param" not in param_state:
                param_state["slow_param"] = torch.zeros_like(fast.data)
                param_state["slow_param"].copy_(fast.data)
            slow = param_state["slow_param"]
            slow += (fast.data - slow) * self.alpha
            fast.data.copy_(slow)

    def update_lookahead(self):
        for group in self.param_groups:
            self.update(group)

    def step(self, closure=None):
        loss = self.optimizer.step(closure)
        for group in self.param_groups:
            if group["counter"] == 0:
                self.update(group)
            group["counter"] += 1
            if group["counter"] >= self.k:
                group["counter"] = 0
        return loss

    def state_dict(self):
        fast_state_dict = self.optimizer.state_dict()
        slow_state = {
            (id(k) if isinstance(k, torch.Tensor) else k): v
            for k, v in self.state.items()
        }
        fast_state = fast_state_dict["state"]
        param_groups = fast_state_dict["param_groups"]
        return {
            "fast_state": fast_state,
            "slow_state": slow_state,
            "param_groups": param_groups,
        }

    def load_state_dict(self, state_dict):
        slow_state_dict = {
            "state": state_dict["slow_state"],
            "param_groups": state_dict["param_groups"],
        }
        fast_state_dict = {
            "state": state_dict["fast_state"],
            "param_groups": state_dict["param_groups"],
        }
        super(Lookahead, self).load_state_dict(slow_state_dict)
        self.optimizer.load_state_dict(fast_state_dict)
        self.fast_state = self.optimizer.state

    def add_param_group(self, param_group):
        param_group["counter"] = 0
        self.optimizer.add_param_group(param_group)