import os import sys from configs.config_ae_static 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 numpy as np from custom_utils.custom_utils import UV2Mesh, get_summary_html, load_model, maskFacesBatch, get_summary_str import plotly.graph_objects as go import plotly.express as ex if config['is_skirt']: from losses import edge_loss_skirt as edge_loss else: from losses import edge_loss from tf_utils import check_tf_version, allow_memory_growth from dataset import DatasetFactory, StaticDataset from custom_utils.custom_utils import batch_to_dict, plot_3d from models.cond_encoder import AutoEncoderNew as AutoEncoder def init_wandb(): run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/home/workspace/local-data/temp') artifact = wandb.Artifact('code', type='code') artifact.add_file('auto_encoder_static.py') artifact.add_file('losses.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') config_file_names = [key for key in sys.modules.keys() if key.startswith('configs.')] for config_file_name in config_file_names: artifact.add_file('/'.join(config_file_name.split('.')) + '.py') run.log_artifact(artifact) uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape']) @tf.function def train_step(batch): with tf.GradientTape() as tape: pred = model([batch['uv_static'], batch['uv_mask']], training=True) mesh_pred = uv2mesh(pred) mesh_orig = batch['mesh_static'] e_loss = 1e-2 * tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask'])) l1_loss = tf.reduce_mean(tf.reduce_sum((tf.math.abs(batch['uv_static'] - pred)), axis=1)) ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 1, batch['uv_static'] + 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, } @tf.function def valid_step(batch): pred = model([batch['uv_static'], batch['uv_mask']], training=False) mesh_pred = uv2mesh(pred) mesh_orig = batch['mesh_static'] e_loss = 1e-2 * tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask'])) l1_loss = tf.reduce_mean(tf.reduce_sum((tf.math.abs(batch['uv_static'] - pred)), axis=1)) ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 1, batch['uv_static'] + 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']) 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_static'], batch['uv_mask']], training=False) mesh_pred = uv2mesh(pred) mesh_orig = batch['mesh_static'] orig_img = batch['uv_static'] 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" + skirt_modifier + ("_orig" if config['is_cape'] else "") + ".npy") mask = batch['mesh_mask'].numpy().astype(bool) garment_static, faces = maskFacesBatch(mesh_pred.numpy(), F, mask) gt = [mesh_orig[i].numpy()[mask[i], :] for i in range(pred.shape[0])] body = gt garment_posed = garment_static collision = [np.concatenate((body[i], garment_posed[i]), axis=0) for i in range(len(garment_posed))] collision_faces = [np.concatenate((faces[i], faces[i] + np.sum(mask[i])), 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_static[i], faces[i], 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 = dict({ **train_loss, **valid_loss, **{ 'current_step': step } }) 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 def test(): load_model(model.encoder, 'checkpoints/' + config['name'] + '_enc') load_model(model.decoder, 'checkpoints/' + config['name'] + '_dec') dataset_test = factory.get_dataset(folder=config['test_dir'], batch_size=config['batch_size'], signature=config['signature_dynamic'], use_filled=config['use_filled'], resolutions=[config['resolution']], in_memory=False, do_repeat=False) static_dataset_test = StaticDataset(folder=config['test_dir'], signature=config['signature_static'], use_filled=config['use_filled'], resolutions=[config['resolution']], in_memory=False) avg_error = 0 count = 0 for batch in dataset_test: batch = static_dataset_test.expand_batch(batch_to_dict(batch, config['signature_dynamic'])) pred = model([batch['uv_static'], batch['uv_mask']], training=False) # orig_img = batch['uv_static'] # pred_img = pred # img = tf.concat((orig_img, pred_img), axis=2).numpy() # ex.imshow((img[0] + 1) / 2).show() mesh_pred = uv2mesh(pred) mesh_orig = batch['mesh_static'] 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']) avg_error += metric count += 1 print(count) print() 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']) skirt_modifier = '_skirt' if config['is_skirt'] else '' factory = DatasetFactory() dataset_train = factory.get_dataset(folder=config['train_dir'], batch_size=config['batch_size'], signature=config['signature_dynamic'], resolutions=[config['resolution']], in_memory=config['dataset_in_memory'], use_no_orient=config['remove_global_orientation'], frames_file=config['frames_file'] if 'frames_file' in config.keys() else None, is_cape=config['is_cape']) static_dataset_train = StaticDataset(folder=config['train_dir'], signature=config['signature_static'], resolutions=[config['resolution']], in_memory=True, is_cape=config['is_cape']) dataset_valid = factory.get_dataset(folder=config['valid_dir'], batch_size=config['batch_size'], signature=config['signature_dynamic'], resolutions=[config['resolution']], in_memory=config['dataset_in_memory'], use_no_orient=config['remove_global_orientation'], frames_file=config['frames_file_valid'] if 'frames_file_valid' in config.keys() else None, is_cape=config['is_cape']) static_dataset_valid = StaticDataset(folder=config['valid_dir'], signature=config['signature_static'], resolutions=[config['resolution']], in_memory=True, is_cape=config['is_cape']) model : AutoEncoder = AutoEncoder(config['cond_ae']) optimizer = tf.optimizers.Adam(learning_rate=config['lr']) if config['pretrained_model'] != '': load_model(model.encoder, config['pretrained_model'] + '_enc') load_model(model.decoder, config['pretrained_model'] + '_dec') ckpt_enc = tf.train.Checkpoint(model=model.encoder) manager_enc = tf.train.CheckpointManager(ckpt_enc, 'checkpoints/post/' + config['name'] + '_enc', max_to_keep=20) ckpt_dec = tf.train.Checkpoint(model=model.decoder) manager_dec = tf.train.CheckpointManager(ckpt_dec, 'checkpoints/post/' + config['name'] + '_dec', max_to_keep=20) # test() train()