import sys
from functools import reduce

from torch import nn
import torch.distributed as dist


def summary(model: nn.Module, file=sys.stdout):
    def repr(model):
        # We treat the extra repr like the sub-module, one item per line
        extra_lines = []
        extra_repr = model.extra_repr()
        # empty string will be split into list ['']
        if extra_repr:
            extra_lines = extra_repr.split('\n')
        child_lines = []
        total_params = 0
        for key, module in model._modules.items():
            mod_str, num_params = repr(module)
            mod_str = nn.modules.module._addindent(mod_str, 2)
            child_lines.append('(' + key + '): ' + mod_str)
            total_params += num_params
        lines = extra_lines + child_lines

        for name, p in model._parameters.items():
            if hasattr(p, 'shape'):
                total_params += reduce(lambda x, y: x * y, p.shape)

        main_str = model._get_name() + '('
        if lines:
            # simple one-liner info, which most builtin Modules will use
            if len(extra_lines) == 1 and not child_lines:
                main_str += extra_lines[0]
            else:
                main_str += '\n  ' + '\n  '.join(lines) + '\n'

        main_str += ')'
        if file is sys.stdout:
            main_str += ', \033[92m{:,}\033[0m params'.format(total_params)
        else:
            main_str += ', {:,} params'.format(total_params)
        return main_str, total_params

    string, count = repr(model)
    if file is not None:
        if isinstance(file, str):
            file = open(file, 'w')
        print(string, file=file)
        file.flush()

    return count


def grad_norm(model: nn.Module):
    total_norm = 0
    for p in model.parameters():
        param_norm = p.grad.data.norm(2)
        total_norm += param_norm.item() ** 2
    return total_norm ** 0.5

def distributed():
    return dist.is_available() and dist.is_initialized()