import math
import torch
import torch.nn as nn
from einops import repeat


def checkpoint(func, inputs, params, flag):
    """
    Evaluate a function without caching intermediate activations, allowing for
    reduced memory at the expense of extra compute in the backward pass.
    :param func: the function to evaluate.
    :param inputs: the argument sequence to pass to `func`.
    :param params: a sequence of parameters `func` depends on but does not
                   explicitly take as arguments.
    :param flag: if False, disable gradient checkpointing.
    """
    if flag:
        args = tuple(inputs) + tuple(params)
        return CheckpointFunction.apply(func, len(inputs), *args)
    else:
        return func(*inputs)


class CheckpointFunction(torch.autograd.Function):
    @staticmethod
    def forward(ctx, run_function, length, *args):
        ctx.run_function = run_function
        ctx.input_tensors = list(args[:length])
        ctx.input_params = list(args[length:])

        with torch.no_grad():
            output_tensors = ctx.run_function(*ctx.input_tensors)
        return output_tensors

    @staticmethod
    def backward(ctx, *output_grads):
        ctx.input_tensors = [x.detach().requires_grad_(True) for x in ctx.input_tensors]
        with torch.enable_grad():
            # Fixes a bug where the first op in run_function modifies the
            # Tensor storage in place, which is not allowed for detach()'d
            # Tensors.
            shallow_copies = [x.view_as(x) for x in ctx.input_tensors]
            output_tensors = ctx.run_function(*shallow_copies)
        input_grads = torch.autograd.grad(
            output_tensors,
            ctx.input_tensors + ctx.input_params,
            output_grads,
            allow_unused=True,
        )
        del ctx.input_tensors
        del ctx.input_params
        del output_tensors
        return (None, None) + input_grads


def timestep_embedding(timesteps, dim, max_period=10000, repeat_only=False):
    """
    Create sinusoidal timestep embeddings.
    :param timesteps: a 1-D Tensor of N indices, one per batch element.
                      These may be fractional.
    :param dim: the dimension of the output.
    :param max_period: controls the minimum frequency of the embeddings.
    :return: an [N x dim] Tensor of positional embeddings.
    """
    if not repeat_only:
        half = dim // 2
        freqs = torch.exp(
            -math.log(max_period)
            * torch.arange(start=0, end=half, dtype=torch.float32)
            / half
        ).to(device=timesteps.device)
        args = timesteps[:, None] * freqs[None]
        embedding = torch.cat([torch.cos(args), torch.sin(args)], dim=-1)
        if dim % 2:
            embedding = torch.cat(
                [embedding, torch.zeros_like(embedding[:, :1])], dim=-1
            )
    else:
        embedding = repeat(timesteps, "b -> b d", d=dim)
    # import pdb; pdb.set_trace()
    return embedding


def zero_module(module):
    """
    Zero out the parameters of a module and return it.
    """
    for p in module.parameters():
        p.detach().zero_()
    return module


def conv_nd(dims, *args, **kwargs):
    """
    Create a 1D, 2D, or 3D convolution module.
    """
    if dims == 1:
        return nn.Conv1d(*args, **kwargs)
    elif dims == 2:
        return nn.Conv2d(*args, **kwargs)
    elif dims == 3:
        return nn.Conv3d(*args, **kwargs)
    raise ValueError(f"unsupported dimensions: {dims}")


def avg_pool_nd(dims, *args, **kwargs):
    """
    Create a 1D, 2D, or 3D average pooling module.
    """
    if dims == 1:
        return nn.AvgPool1d(*args, **kwargs)
    elif dims == 2:
        return nn.AvgPool2d(*args, **kwargs)
    elif dims == 3:
        return nn.AvgPool3d(*args, **kwargs)
    raise ValueError(f"unsupported dimensions: {dims}")