import os from configs.config_ae_body import config os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu'] import time import argparse import wandb import random import cv2 import numpy as np import tensorflow as tf from custom_utils.custom_utils import UV2Mesh, 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='vae', 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_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/edge_loss': e_loss, 'train/l1_loss': l1_loss, 'train/euclid_error': metric, 'train/ms_ssim': ms_ssim, } # UPDATE! @tf.function def valid_step(batch): pred = model([batch['uv_body_posed'], batch['uv_mask']]) mesh_pred = uv2mesh(pred) mesh_orig = batch['mesh_body_posed'] e_loss = 1e-2 * tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask'])) c_loss = 0 #1e-2 * tf.reduce_mean(collision_penalty(mesh_pred, batch['mesh_body_posed'], batch['mesh_mask'])) l1_loss = tf.reduce_mean(tf.reduce_sum((tf.math.abs(batch['uv_body_posed'] - pred)), axis=1) * batch['uv_mask']) ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(tf.transpose(pred, [0,2,3,1]) + 1, tf.transpose(batch['uv_body_posed'], [0,2,3,1]) + 1, max_val=2)) fft_loss = 0 #tf.reduce_mean(tf.reduce_sum(tf.math.abs(tf.signal.fft3d(tf.complex(pred, tf.zeros_like(pred))) - tf.signal.fft3d(tf.complex(batch['uv_body_posed'], tf.zeros_like(batch['uv_body_posed'])))), axis=[1,2,3])) loss = 1e3 * (1 - ms_ssim) mesh_orig_2 = uv2mesh(batch['uv_body_posed']) 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']) metric_2 = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig_2 - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask']) return { 'valid/loss': loss, 'valid/edge_loss': e_loss, 'valid/collision_loss': c_loss, 'valid/l1_loss': l1_loss, 'valid/euclid_error': metric, 'valid/ms_ssim': ms_ssim, 'valid/fft_loss': fft_loss, 'valid/euclid_error_reconst': metric_2 } 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) if step % 2500 == 0: train_figs = plot_everything(batch, 'train') valid_figs = {}#plot_everything(data_valid, 'valid') wandb.log({ **train_loss, **valid_loss, **train_figs, **valid_figs }, step=step) else: wandb.log({ **train_loss, **valid_loss }, 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']]) 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']) 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()