cvpr/auto_encoder_body.py

import os
from configs.config_ae_body import config
os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']

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, plot_3d
from models.cond_encoder import AutoEncoder


def init_wandb():
    run = wandb.init(project='ae', name=config['name'], notes=config['notes'])
    artifact = wandb.Artifact('code', type='code')
    artifact.add_file('auto_encoder_body.py')
    artifact.add_file('losses.py')
    artifact.add_file('configs/config_base.py')
    artifact.add_file('configs/config_ae_body.py')
    artifact.add_file('models/base.py')
    artifact.add_file('models/cond_encoder.py')
    artifact.add_file('dataset.py')
    artifact.add_file('convnext/models/convnext_tf.py')
    run.log_artifact(artifact)

uv2mesh = UV2Mesh(res=256)


@tf.function
def train_step(batch):
    with tf.GradientTape() as tape:
        pred = model([batch['uv_body_posed' + resolution_modifier], uv_mask_body], training=True)

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

        e_loss = 1e-2 * tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, tf.ones((pred.shape[0], 14475))))
        l1_loss = tf.reduce_mean(tf.reduce_sum(((tf.math.abs(batch['uv_body_posed' + resolution_modifier] - pred))), axis=1))
        ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 1, batch['uv_body_posed' + resolution_modifier] + 1, max_val=2, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))

        loss = 1e3 * (1 - ms_ssim)

    metric = tf.reduce_mean(tf.math.sqrt(tf.reduce_sum((mesh_orig - mesh_pred) ** 2, axis=-1)))
    gradients = tape.gradient(loss, model.trainable_variables)
    optimizer.apply_gradients(zip(gradients, model.trainable_variables))
    return { 'train/loss': loss, 'train/edge_loss': e_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_body_posed' + resolution_modifier], uv_mask_body], training=False)

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

    e_loss = 1e-2 * tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, tf.ones((pred.shape[0], 14475))))
    l1_loss = tf.reduce_mean(tf.reduce_sum(((tf.math.abs(batch['uv_body_posed' + resolution_modifier] - pred))), axis=1))
    ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 1, batch['uv_body_posed' + resolution_modifier] + 1, max_val=2, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))

    loss = 1e3 * (1 - ms_ssim)

    metric = tf.reduce_mean(tf.math.sqrt(tf.reduce_sum((mesh_orig - mesh_pred) ** 2, axis=-1)))
    return { 'valid/loss': loss, 'valid/edge_loss': e_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_body_posed' + resolution_modifier], uv_mask_body], training=False)
    
    mesh_pred = uv2mesh(pred)
    mesh_orig = batch['mesh_body_posed']
    
    orig_img = batch['uv_body_posed' + resolution_modifier]
    pred_img = pred
    img = tf.concat((orig_img, pred_img), axis=2)
    imgs = [wandb.Image((img[i] + 1) / 2.0) for i in range(4)]

    F = np.load("custom_utils/smpl_faces.npy")
    garment_unposed, faces = mesh_pred.numpy(), F
    gt = [mesh_orig[i].numpy()[:, :] for i in range(pred.shape[0])]
    
    body = uv2mesh(batch['uv_body_posed' + resolution_modifier]).numpy()
    garment_posed = garment_unposed
    collision = [np.concatenate((body[i], garment_posed[i]), axis=0) for i in range(len(garment_posed))]
    collision_faces = [np.concatenate((F, faces + 14475), axis=0) for i in range(len(garment_posed))]
    collision_color = [np.concatenate((np.ones_like(body[i], dtype=np.int32)*100, np.ones_like(garment_posed[i], dtype=np.int32)*230), axis=0) for i in range(len(garment_posed))]

    figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], faces, collision[i], collision_faces[i], collision_color[i]) 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, config['signature_dynamic']))
        train_loss = train_step(batch)

        data_valid = valid_iterator.get_next()
        data_valid = static_dataset_valid.expand_batch(batch_to_dict(data_valid, config['signature_dynamic']))
        valid_loss = valid_step(data_valid)

        to_log = { **train_loss, **valid_loss }
        if step % 5000 == 0 or (step < 5000 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)) } }

        wandb.log(to_log, step=step)  
            
        if step % 10000 == 0:
            manager_enc.save(checkpoint_number=step)
            manager_dec.save(checkpoint_number=step)

        print(step)

        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())


    # TODO: different resolutions not working yet, model should be ready though
    resolution_modifier = ''
    if config['resolution'] != 512:
        resolution_modifier = '_' + str(config['resolution'])

    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)

    factory = DatasetFactory()

    dataset_train = factory.get_dataset(folder=config['train_dir'], batch_size=config['batch_size'], signature=config['signature_dynamic'], use_filled=config['use_filled'], resolutions=[config['resolution']], in_memory=config['dataset_in_memory'])
    static_dataset_train = StaticDataset(folder=config['train_dir'], signature=config['signature_static'], use_filled=config['use_filled'], resolutions=[config['resolution']], in_memory=True)
    dataset_valid = factory.get_dataset(folder=config['valid_dir'], batch_size=config['batch_size'], signature=config['signature_dynamic'], use_filled=config['use_filled'], resolutions=[config['resolution']], in_memory=config['dataset_in_memory'])
    static_dataset_valid = StaticDataset(folder=config['valid_dir'], signature=config['signature_static'], use_filled=config['use_filled'], resolutions=[config['resolution']], in_memory=True)

    model = AutoEncoder(config['cond_ae'])
    optimizer = tf.optimizers.Adam(learning_rate=config['lr'])

    ckpt_enc = tf.train.Checkpoint(model=model.encoder)
    manager_enc = tf.train.CheckpointManager(ckpt_enc, 'checkpoints/' + config['name'] + '_enc', max_to_keep=3)
    ckpt_dec = tf.train.Checkpoint(model=model.decoder)
    manager_dec = tf.train.CheckpointManager(ckpt_dec, 'checkpoints/' + config['name'] + '_dec', max_to_keep=3)

    train()