import os from configs.config_ae_curv 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, UV2MeshLabel, get_summary_html, maskFacesBatch import plotly.graph_objects as go import plotly.express as ex from tf_utils import check_tf_version, allow_memory_growth from dataset import DatasetFactory, StaticDataset from custom_utils.custom_utils import batch_to_dict from models.cond_encoder import AutoEncoder testing = False def init_wandb(): if not testing: run = wandb.init(project='ae', name=config['name'], notes=config['notes']) artifact = wandb.Artifact('code', type='code') artifact.add_file('auto_encoder_curv.py') artifact.add_file('losses.py') artifact.add_file('configs/config_base.py') artifact.add_file('configs/config_ae_curv.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 = UV2MeshLabel(res=256, is_skirt=config['is_skirt']) g_mean_iou = tf.keras.metrics.MeanIoU(num_classes=7) def get_mean_iou(y_true, y_pred): g_mean_iou.reset_state() g_mean_iou.update_state(y_true, y_pred) return g_mean_iou.result() g_mean_iou_mesh = tf.keras.metrics.MeanIoU(num_classes=7) def get_mean_iou_mesh(y_true, y_pred): g_mean_iou_mesh.reset_state() g_mean_iou_mesh.update_state(y_true, y_pred) return g_mean_iou_mesh.result() # https://github.com/NifTK/NiftyNet/blob/dev/niftynet/layer/loss_segmentation.py def dice_dense(prediction, ground_truth, weight_map=None): """ Computing mean-class Dice similarity. :param prediction: last dimension should have ``num_classes`` :param ground_truth: segmentation ground truth (encoded as a binary matrix) last dimension should be ``num_classes`` :param weight_map: :return: ``1.0 - mean(Dice similarity per class)`` """ if weight_map is not None: raise NotImplementedError prediction = tf.cast(prediction, dtype=tf.float32) ground_truth = tf.cast(ground_truth, dtype=tf.float32) ground_truth = tf.reshape(ground_truth, prediction.shape) # computing Dice over the spatial dimensions reduce_axes = list(range(len(prediction.shape) - 1)) dice_numerator = 2.0 * tf.reduce_sum( prediction * ground_truth, axis=reduce_axes) dice_denominator = \ tf.reduce_sum(tf.square(prediction), axis=reduce_axes) + \ tf.reduce_sum(tf.square(ground_truth), axis=reduce_axes) epsilon = 0.00001 dice_score = (dice_numerator + epsilon) / (dice_denominator + epsilon) return tf.reduce_mean(dice_score) @tf.function def train_step(batch): with tf.GradientTape() as tape: pred = model([batch['uv_curvature'], batch['uv_mask']], training=True) ce_uv_loss = scce(tf.math.argmax(batch['uv_curvature'], axis=-1), pred) ms_ssim = tf.reduce_mean(tf.image.ssim(pred, batch['uv_curvature'], max_val=1)) loss = ce_uv_loss pred_mesh = tf.math.argmax(uv2mesh(pred), axis=-1) mean_iou = get_mean_iou(tf.math.argmax(batch['uv_curvature'], axis=-1), tf.math.argmax(pred, axis=-1)) mean_iou_mesh = get_mean_iou(tf.cast(batch['mesh_curvature'], tf.float32) * batch['mesh_mask'], tf.cast(pred_mesh, tf.float32) * batch['mesh_mask']) dice = dice_dense(pred, batch['uv_curvature']) gradients = tape.gradient(loss, model.trainable_variables) optimizer.apply_gradients(zip(gradients, model.trainable_variables)) return { 'train/loss': loss, 'train/ce_uv_loss': ce_uv_loss, 'train/ssim': ms_ssim, 'train/mean_iou': mean_iou, 'train/mean_iou_mesh': mean_iou_mesh, 'train/dice': dice } @tf.function def valid_step(batch): pred = model([batch['uv_curvature'], batch['uv_mask']], training=False) ce_uv_loss = scce(tf.math.argmax(batch['uv_curvature'], axis=-1), pred) ms_ssim = tf.reduce_mean(tf.image.ssim(pred, batch['uv_curvature'], max_val=1)) loss = ce_uv_loss pred_mesh = tf.math.argmax(uv2mesh(pred), axis=-1) mean_iou = get_mean_iou(tf.math.argmax(batch['uv_curvature'], axis=-1), tf.math.argmax(pred, axis=-1)) mean_iou_mesh = get_mean_iou(tf.cast(batch['mesh_curvature'], tf.float32) * batch['mesh_mask'], tf.cast(pred_mesh, tf.float32) * batch['mesh_mask']) dice = dice_dense(pred, batch['uv_curvature']) return { 'valid/loss': loss, 'valid/ce_uv_loss': ce_uv_loss, 'valid/ssim': ms_ssim, 'valid/mean_iou': mean_iou, 'valid/mean_iou_mesh': mean_iou_mesh, 'valid/dice': dice } def plot_everything(batch: dict, type: str): pred = model([batch['uv_curvature'], batch['uv_mask']], training=False) orig_img = tf.math.argmax(batch['uv_curvature'], axis=-1, output_type=tf.dtypes.int32) pred_img = tf.math.argmax(pred, axis=-1, output_type=tf.dtypes.int32) img = tf.concat((orig_img, pred_img), axis=2).numpy() imgs = { type + '/images': [wandb.Image(img[i,:,:,np.newaxis] / 6.0) for i in range(img.shape[0])] } return 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) print(step) if step % 10000 == 0: manager_enc.save(checkpoint_number=step) manager_dec.save(checkpoint_number=step) step += 1 def test(): #TODO # ckpt.restore(manager.latest_checkpoint) for batch in dataset_train: batch = static_dataset_train.expand_batch(batch_to_dict(batch, config['signature_dynamic'])) uv_curvature = tf.one_hot(batch['uv_curvature'], 7) pred = model([uv_curvature, batch['uv_mask']]) orig_img = batch['uv_curvature'] pred_img = tf.math.argmax(pred, axis=-1, output_type=tf.dtypes.int32) img = tf.concat((orig_img, pred_img), axis=2).numpy() ex.imshow(img[0] / 6.0).show() print() if __name__ == '__main__': init_wandb() allow_memory_growth() parser = argparse.ArgumentParser(description='') parser.add_argument('--name', type=str) args = vars(parser.parse_args()) scce = tf.keras.losses.SparseCategoricalCrossentropy() resolution_modifier = '' if config['resolution'] != 512: resolution_modifier = '_' + str(config['resolution']) 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=20) ckpt_dec = tf.train.Checkpoint(model=model.decoder) manager_dec = tf.train.CheckpointManager(ckpt_dec, 'checkpoints/' + config['name'] + '_dec', max_to_keep=20) if testing: test() else: train()