import os
os.environ["CUDA_VISIBLE_DEVICES"] = "2"
import tensorflow as tf

gpus = tf.config.experimental.list_physical_devices('GPU')
if gpus:
    try:
        # Currently, memory growth needs to be the same across GPUs
        for gpu in gpus:
            tf.config.experimental.set_memory_growth(gpu, True)
        logical_gpus = tf.config.experimental.list_logical_devices('GPU')
        print(len(gpus), "Physical GPUs,", len(logical_gpus), "Logical GPUs")
    except RuntimeError as e:
        # Memory growth must be set before GPUs have been initialized
        print(e)

import time
import argparse
import wandb
import random
import cv2
import numpy as np
from custom_utils.custom_utils import UV2Mesh, get_summary_html, load_model, maskFacesBatch
import plotly.graph_objects as go
import plotly.express as ex

from tf_utils import check_tf_version, allow_memory_growth
# from losses import edge_loss, uv_mask_loss
from dataset import DatasetFactory, StaticDataset
from custom_utils.custom_utils import batch_to_dict
# from custom_utils.smpl import SMPL
# from models.upscaler import Upscaler
from models.upscaler import UpscalerBasicConv as Upscaler

# !!!!!!!!!! CHANGE SSIM BASED ON RES
# !!!!!!!!!! CHANGE SKIRT OR NOT


low_res = 128
is_skirt = False
is_cape = True
is_male = False
skirt_modifier = '_skirt' if is_skirt else ''
cape_modifier = '_cape' if is_cape else ''
gender_modifier = '' if not is_cape else ('_m' if is_male else '_f')
smpl_res = 3638 if is_cape else 14475


name=f'iccv_{low_res}_2' + skirt_modifier + cape_modifier + gender_modifier
def init_wandb():
    run = wandb.init(project='upscale', name=name,
            notes='\
changed ms-ssim scale weights | \
inpainting style | \
MLP based | \
smaller batch | \
use mask for loss | \
using ms ssim for higher res | \
training from low res to low res | \
named the layers, added tanh to final layer | \
changed l1 loss reduce axis | \
try convolutional architecture | \
smaller features  | \
', dir='/home/workspace/local-data/temp')
    artifact = wandb.Artifact('code', type='code')
    artifact.add_file('upscale_test.py')
    artifact.add_file('models/upscaler.py')
    artifact.add_file('losses.py')
    artifact.add_file('dataset.py')
    artifact.add_file('convnext/models/convnext_tf.py')
    run.log_artifact(artifact)


uv2mesh = UV2Mesh(res=256, is_skirt=is_skirt, is_smpl_orig=is_cape)


def plot_3d(mesh_gt, mesh_pred_unposed, faces):
    mesh_pred_unposed[:,2] += 1
    fig = go.Figure(data=[
        go.Mesh3d(
            # 8 vertices of a cube
            x=mesh_gt[:,0],
            y=mesh_gt[:,2],
            z=mesh_gt[:,1],
            # i, j and k give the vertices of triangles
            i = faces[:,0],
            j = faces[:,1],
            k = faces[:,2]
        ),
        go.Mesh3d(
            # 8 vertices of a cube
            x=mesh_pred_unposed[:,0],
            y=mesh_pred_unposed[:,2],
            z=mesh_pred_unposed[:,1],
            # i, j and k give the vertices of triangles
            i = faces[:,0],
            j = faces[:,1],
            k = faces[:,2],
        )
    ])

    fig.update_layout(scene_aspectmode='manual',
                    scene_aspectratio=dict(x=1, y=2, z=1))
    fig.update_layout(
        scene = dict(
            xaxis = dict(nticks=4, range=[-1,1],),
                        yaxis = dict(nticks=4, range=[-1,3],),
                        zaxis = dict(nticks=4, range=[-1,1],),)
                        )

    return fig


@tf.function
def train_step(batch):
    with tf.GradientTape() as tape:
        pred = model([batch['uv_unposed' + low_resolution_modifier], batch['uv_mask' + low_resolution_modifier]], training=True)
        pred = tf.image.resize(pred, size=(high_res, high_res//2), method=tf.image.ResizeMethod.BILINEAR)

        mesh_pred = uv2mesh(pred)
        mesh_orig = batch['mesh_unposed']

        l1_loss = tf.reduce_mean(tf.reduce_sum(((tf.math.abs(batch['uv_unposed' + high_resolution_modifier] - pred * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis]) )), axis=-1))
        
        if low_res == 32:
            ms_ssim = tf.reduce_mean(tf.image.ssim(pred * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis] + 1, batch['uv_unposed' + high_resolution_modifier] * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis] + 1, max_val=2))
        else:
            ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis] + 1, batch['uv_unposed' + high_resolution_modifier] * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis] + 1, max_val=2, power_factors=(0.5, 0.2, 0.2, 0.1)))
            
        loss = 1e3 * (1 - ms_ssim)

    metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
    gradients = tape.gradient(loss, model.trainable_variables)
    optimizer.apply_gradients(zip(gradients, model.trainable_variables))
    return { 'train/loss': loss, 'train/l1_loss': l1_loss, 'train/euclid_error': metric, 'train/ms_ssim': ms_ssim }
        

@tf.function
def valid_step(batch):
    pred = model([batch['uv_unposed' + low_resolution_modifier], batch['uv_mask' + low_resolution_modifier]], training=False)
    pred = tf.image.resize(pred, size=(high_res, high_res//2), method=tf.image.ResizeMethod.BILINEAR)

    mesh_pred = uv2mesh(pred)
    mesh_orig = batch['mesh_unposed']

    l1_loss = tf.reduce_mean(tf.reduce_sum(((tf.math.abs(batch['uv_unposed' + high_resolution_modifier] - pred * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis]) )), axis=-1))
    
    if low_res == 32:
        ms_ssim = tf.reduce_mean(tf.image.ssim(pred * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis] + 1, batch['uv_unposed' + high_resolution_modifier] * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis] + 1, max_val=2))
    else:
        ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis] + 1, batch['uv_unposed' + high_resolution_modifier] * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis] + 1, max_val=2, power_factors=(0.5, 0.2, 0.2, 0.1)))
    
    loss = 1e3 * (1 - ms_ssim)

    metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
    return { 'valid/loss': loss, 'valid/l1_loss': l1_loss, 'valid/euclid_error': metric, 'valid/ms_ssim': ms_ssim }
   

def plot_everything(batch: dict, type: str):

    pred = model([batch['uv_unposed' + low_resolution_modifier], batch['uv_mask' + low_resolution_modifier]], training=False)
    pred = tf.image.resize(pred, size=(high_res, high_res//2), method=tf.image.ResizeMethod.BILINEAR)
    
    mesh_pred = uv2mesh(pred)
    mesh_orig = batch['mesh_unposed']
    
    F = np.load("custom_utils/smpl_faces" + skirt_modifier + ("_orig" if is_cape else "") + ".npy")
    mask = batch['mesh_mask'].numpy().astype(bool)
    garment_unposed, faces = maskFacesBatch(mesh_pred.numpy(), F, mask)
    # gt = [mesh_orig[i].numpy()[mask[i], :] for i in range(pred.shape[0])]
    gt = [mesh_orig[i].numpy()[mask[i], :] for i in range(pred.shape[0])]
    
    figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], faces[i]) for i in range(4) }
    # figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], faces[i], collision[i], collision_faces[i], collision_color[i]) for i in range(4) }
    
    orig_img = batch['uv_unposed' + high_resolution_modifier]
    img = tf.concat((orig_img, pred), axis=2)
    imgs = [wandb.Image((img[i] + 1) / 2.0) for i in range(4)]

    return { **figs, **{ type + '/images': imgs} }


def train():
    valid_iterator = iter(dataset_valid)

    step = 0
    for batch in dataset_train:
        batch = static_dataset_train.expand_batch(batch_to_dict(batch, signature_dynamic))
        train_loss = train_step(batch)

        if step % 100 == 0:
            data_valid = valid_iterator.get_next()
            data_valid = static_dataset_valid.expand_batch(batch_to_dict(data_valid, signature_dynamic))
            valid_loss = valid_step(data_valid)

        to_log = { **train_loss, **valid_loss, **{ 'current_step': step} }
        if step % 10000 == 0 or (step < 2000 and step % 500 == 0):
            train_figs = plot_everything(batch, 'train')
            valid_figs = plot_everything(data_valid, 'valid')
            to_log = { **to_log, **train_figs, **valid_figs }

        if step == 0:
            to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
            
        if step % 5000 == 0:
            manager.save(checkpoint_number=step)

        wandb.log(to_log, step = step)

        print(step)

        if step > 100000:
            break

        step += 1

if __name__ == '__main__':
    init_wandb()
    # allow_memory_growth()
    parser = argparse.ArgumentParser(description='')
    parser.add_argument('--name', type=str)
    args = vars(parser.parse_args())
    
    # smpl = SMPL()
    # uv_mask_body = np.load('custom_utils/mask_256x512.npy')
    # uv_mask_body = cv2.dilate(uv_mask_body.astype(np.float32), cv2.getStructuringElement(cv2.MORPH_RECT, (2 * 2 + 1, 2 * 2 + 1), (2, 2)), iterations=2)

    high_res = 512
    uv_mask_body = tf.ones((low_res, low_res//2))
    low_resolution_modifier = '_' + str(low_res)
    high_resolution_modifier = ('_' + str(high_res)) if high_res != 512 else ''

    factory = DatasetFactory()
    signature_dynamic = { 'id': (), 'frame_nr': (),
                          'pose_shape': (72 + 11,),
                          'uv_unposed' + low_resolution_modifier: (low_res, low_res//2, 3),
                          'uv_unposed' + high_resolution_modifier: (high_res, high_res//2, 3),
                          'mesh_unposed': (smpl_res, 3,),
                          'mesh_posed': (smpl_res, 3,),
                        }
    signature_static = { 
                         'mesh_mask': (smpl_res,),
                         'uv_mask' + high_resolution_modifier: (high_res, high_res//2,),
                         'uv_mask' + low_resolution_modifier: (low_res, low_res//2,),
                        }

    if not is_skirt:
        dataset_train = factory.get_dataset(folder='/home/workspace/local-data/train', batch_size=8, signature=signature_dynamic, resolutions=[high_res, low_res], in_memory=False, is_cape=is_cape)
        static_dataset_train = StaticDataset(folder='/home/workspace/local-data/train', signature=signature_static, resolutions=[high_res, low_res], in_memory=True, is_cape=is_cape)
        dataset_valid = factory.get_dataset(folder='/home/workspace/local-data/valid', batch_size=8, signature=signature_dynamic,resolutions=[high_res, low_res], in_memory=False, is_cape=is_cape)
        static_dataset_valid = StaticDataset(folder='/home/workspace/local-data/valid', signature=signature_static, resolutions=[high_res, low_res], in_memory=True, is_cape=is_cape)

    if is_skirt:
        dataset_train = factory.get_dataset(folder='/home/workspace/data/dataset/local-cache/train_skirt', batch_size=8, signature=signature_dynamic, resolutions=[high_res, low_res], in_memory=False, is_cape=is_cape)
        static_dataset_train = StaticDataset(folder='/home/workspace/data/dataset/local-cache/train_skirt', signature=signature_static, resolutions=[high_res, low_res], in_memory=True, is_cape=is_cape)
        dataset_valid = factory.get_dataset(folder='/home/workspace/local-data/valid_skirt', batch_size=8, signature=signature_dynamic,resolutions=[high_res, low_res], in_memory=False, is_cape=is_cape)
        static_dataset_valid = StaticDataset(folder='/home/workspace/local-data/valid_skirt', signature=signature_static, resolutions=[high_res, low_res], in_memory=True, is_cape=is_cape)

    if is_cape:
        if is_male:
            dataset_train = factory.get_dataset(folder='/home/workspace/local-data/cape_processed/train/male', batch_size=8, signature=signature_dynamic, resolutions=[high_res, low_res], in_memory=False, is_cape=is_cape)
            static_dataset_train = StaticDataset(folder='/home/workspace/local-data/cape_processed/train/male', signature=signature_static, resolutions=[high_res, low_res], in_memory=True, is_cape=is_cape)
            dataset_valid = factory.get_dataset(folder='/home/workspace/local-data/cape_processed/test/male', batch_size=8, signature=signature_dynamic, resolutions=[high_res, low_res], in_memory=False, is_cape=is_cape)
            static_dataset_valid = StaticDataset(folder='/home/workspace/local-data/cape_processed/test/male', signature=signature_static, resolutions=[high_res, low_res], in_memory=True, is_cape=is_cape)
        else:
            dataset_train = factory.get_dataset(folder='/home/workspace/local-data/cape_processed/train/female', batch_size=8, signature=signature_dynamic, resolutions=[high_res, low_res], in_memory=False, is_cape=is_cape)
            static_dataset_train = StaticDataset(folder='/home/workspace/local-data/cape_processed/train/female', signature=signature_static, resolutions=[high_res, low_res], in_memory=True, is_cape=is_cape)
            dataset_valid = factory.get_dataset(folder='/home/workspace/local-data/cape_processed/test/female', batch_size=8, signature=signature_dynamic, resolutions=[high_res, low_res], in_memory=False, is_cape=is_cape)
            static_dataset_valid = StaticDataset(folder='/home/workspace/local-data/cape_processed/test/female', signature=signature_static, resolutions=[high_res, low_res], in_memory=True, is_cape=is_cape)
                    

    if low_res == 32 or low_res == 64:
        model = Upscaler(low_res=low_res, kernel_size=3)
    elif low_res == 128 or low_res == 256:
        model = Upscaler(low_res=low_res, kernel_size=5)
    else:
        model = Upscaler(low_res=low_res, kernel_size=7)


    optimizer = tf.optimizers.Adam(learning_rate=0.0001)
    folder = 'models/ae_logs/'

    ckpt = tf.train.Checkpoint(model=model)
    manager = tf.train.CheckpointManager(ckpt, 'checkpoints/iccv/' + name, max_to_keep=20)
    # load_model(model, f'checkpoints/iccv/iccv_{low_res}' + skirt_modifier)

    train()