import os
import sys
sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/..')

import importlib
import argparse
parser = argparse.ArgumentParser(description='')
parser.add_argument('--name', type=str)
parser.add_argument('--config', type=str)
parser.add_argument('--debug', action='store_true')
args = vars(parser.parse_args())


from configs.iccvw.pyr_64_2 import config

os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = '5'
if args['debug']:
    os.environ["CUDA_LAUNCH_BLOCKING"] = '1'

import time
import argparse
import wandb
import tqdm
import random
import numpy as np
import plotly.graph_objects as go
import plotly.express as ex
from PIL import Image


import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torch.profiler import profile, record_function, ProfilerActivity
from data.dataset import Dataset
from utils.checkpoints import  load_model
from utils.utils import InfiniteDataLoader as DataLoader
from losses.losses import  kl_loss
from custom_utils.custom_utils import UV2Mesh, Accumulator, group_inputs_for_levels
from smpl.smpl_torch import SMPL
from models.pyramid_model import Pyramid



uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])

def train_step(batch):
    model.train()
    # with torch.autocast(device_type='cuda', dtype=torch.float16, enabled=use_amp):
    levels_input, conds = group_inputs_for_levels(batch, config)

    out_levels = model([levels_input, conds])

    if config['use_skinning']:
        mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
    else:
        mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']

    reconstr_loss_total = 0
    kl_total = 0

    #for i, res in enumerate(config['pyramid']['resolutions']):
    i = -1
    pred, mean, logvar = out_levels[i]

    mesh_pred = uv2mesh(pred)

    if config['use_skinning']:
        shape = batch['pose_shape'][:, 72:]
        gender = torch.greater_equal(shape[:, 10] , 0.5).to(dtype=torch.int64)
        shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])])

        mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None]
        mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0]
    else:
        mesh_pred_posed = mesh_pred


    kl = kl_loss(mean, logvar)

    loss: torch.Tensor =  g_balancing_coeff * kl

    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

    model.eval()
    with torch.inference_mode():
        metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred.detach()) ** 2, axis=-1))) / torch.sum(batch['mesh_mask'])


    return { **{ 'train/loss': loss, 'train/reconstr_loss_total': reconstr_loss_total, 'train/kl_total': kl_total } }


def train():
    global g_balancing_coeff
    global step

    for batch in train_dataloader:
        train_step(batch)

        step += 1
        print(step)
        profiler.step()

        if step > 300:
            break



if __name__ == '__main__':
    smpl = SMPL(orig_smpl=config['is_cape'], path='smpl', device=config['device'])
    skirt_modifier = '_skirt' if config['is_skirt'] else ''
    dataset_resolutions = config['pyramid']['resolutions'].copy()
    if 512 not in dataset_resolutions:
        dataset_resolutions.append(512)

    dataset_train = Dataset(config['train_dir'], config['signature'], device=config['device'], frames_file='frames_single.txt', use_cache=True, resolutions=dataset_resolutions, is_cape=config['is_cape'])
    train_dataloader = DataLoader(dataset_train, batch_size=4, drop_last=True, shuffle=True, )
    train_accumulator = Accumulator()

    model: Pyramid = Pyramid(config)

    optimizer = optim.Adam(model.parameters(), lr=config['lr'])

    g_balancing_coeff = config['starting_balancing_coeff']
    reg_coeff = 1

    step = 0
    if config['pretrained_model'] != '':
        # assert len(config['pyramid']['resolutions']) == 1
        load_model(model, config['pretrained_model'], optimizer=optimizer, iteration=config['pretrained_model_iteration'])

    if len(config['pyramid']['resolutions']) == 1:
        for param in model.static_enc.parameters(): param.requires_grad = False
        for param in model.body_enc.parameters(): param.requires_grad = False
        for param in model.norm_enc.parameters(): param.requires_grad = False
    else:
        load_model(model, config['pyramid']['pretrained_pyramid'], iteration=config['pyramid']['pretrained_pyramid_iteration'])
        for param in model.static_enc.parameters(): param.requires_grad = False
        for param in model.body_enc.parameters(): param.requires_grad = False
        for param in model.norm_enc.parameters(): param.requires_grad = False

    for i in range(len(model.levels)-1):
        for param in model.levels[i].parameters(): param.requires_grad = False

    # create a profiler object
    profiler = torch.profiler.profile(
        activities=[ProfilerActivity.CPU, ProfilerActivity.CUDA],
        schedule=torch.profiler.schedule(wait=2, warmup=5, active=3, repeat=2),
        on_trace_ready=torch.profiler.tensorboard_trace_handler("log_dir"),
    )

    with profiler:
        train()

    profiler.stop()
    print(profiler.key_averages().table(sort_by="cpu_time_total", row_limit=25))