import os import sys sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/..') import argparse import importlib parser = argparse.ArgumentParser(description='') parser.add_argument('--name', type=str) parser.add_argument('--config', type=str) parser.add_argument('--debug', action='store_true') args = vars(parser.parse_args()) config_module = importlib.import_module(args['config']) config = config_module.config if args['debug']: from configs.ae_norm_1 import config os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID" os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu'] if args['debug']: os.environ["CUDA_LAUNCH_BLOCKING"] = '1' import time import wandb import random import numpy as np import torch from torch import nn # from torchmetrics import MultiScaleStructuralSimilarityIndexMeasure as MSSSIM from custom_utils.custom_utils import UV2Mesh, get_summary_html, maskFacesBatch, get_summary_str import plotly.graph_objects as go import plotly.express as ex import torch.optim as optim if config['is_skirt']: from losses.losses import edge_loss_skirt as edge_loss else: from losses.losses import edge_loss from data.dataset import Dataset # from torch.utils.data import DataLoader from custom_utils.custom_utils import plot_3d from models.cond_encoder import AutoEncoder from utils.checkpoints import CheckpointSaver, load_model from custom_utils.custom_utils import Accumulator from utils.utils import InfiniteDataLoader as DataLoader from pytorch_msssim import MS_SSIM def init_wandb(): wandb.login(host='https://wandb2.lnrweb.com', key='local-2a78b434e9bc51e9f12625f8321a9e3ee34af16d', relogin=True, force=True) run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/data-local/127/temp', tags=config['tags']) artifact = wandb.Artifact('code', type='code') artifact.add_file('scripts/ae_norm_train.py') artifact.add_file('losses/losses.py') artifact.add_file('models/base.py') artifact.add_file('models/cond_encoder.py') artifact.add_file('models/convnext.py') artifact.add_file('data/dataset.py') config_file_names = [key for key in sys.modules.keys() if key.startswith('configs.')] for config_file_name in config_file_names: file_name = '/'.join(config_file_name.split('.')) + '.py' if os.path.exists(file_name): artifact.add_file(file_name) run.log_artifact(artifact) uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape']) def train_step(batch): model.train() pred = model([batch['uv_normals'], batch['uv_mask']]) * 1.4 ms_ssim = torch.mean(_MSSSIM(pred + 1.4, batch['uv_normals'] + 1.4)) loss = 1e3 * (1 - ms_ssim) optimizer.zero_grad() loss.backward() optimizer.step() model.eval() with torch.inference_mode(): mesh_pred = uv2mesh(pred) mesh_orig = batch['mesh_normals'] l1_loss = torch.mean(torch.sum((torch.abs(batch['uv_normals'] - pred)), axis=1)) metric = torch.mean(torch.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred) ** 2, axis=-1))) return { 'train/loss': loss, 'train/l1_loss': l1_loss, 'train/euclid_error': metric, 'train/ms_ssim': ms_ssim, } def valid_step(batch): model.eval() with torch.inference_mode(): pred = model([batch['uv_normals'], batch['uv_mask']]) * 1.4 mesh_pred = uv2mesh(pred) mesh_orig = batch['mesh_normals'] l1_loss = torch.mean(torch.sum((torch.abs(batch['uv_normals'] - pred)), axis=1)) ms_ssim = torch.mean(_MSSSIM(pred + 1.4, batch['uv_normals'] + 1.4)) loss = 1e3 * (1 - ms_ssim) metric = torch.mean(torch.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred) ** 2, axis=-1))) 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): model.eval() pred = model([batch['uv_normals'], batch['uv_mask']]).detach() * 1.4 # mesh_pred = uv2mesh(pred) # mesh_orig = batch['mesh_normals'] orig_img = torch.permute(batch['uv_normals'], [0,2,3,1]) pred_img = torch.permute(pred, [0,2,3,1]) img = torch.concat((orig_img, pred_img), axis=2) imgs = [wandb.Image((img[i].cpu().numpy() + 1.4) / 2.8) for i in range(4)] # F = np.load("smpl/smpl_faces" + skirt_modifier + ("_orig" if config['is_cape'] else "") + ".npy") # garment_unposed, faces = mesh_pred.cpu().numpy(), F # gt = [mesh_orig[i].cpu().numpy() for i in range(pred.shape[0])] # body = uv2mesh(batch['uv_body_posed']).cpu().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 + (3638 if config['is_cape'] else 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) } figs = {} return { **figs, **{ type + '/images': imgs } } def train(): valid_iterator = iter(valid_dataloader) step = 0 for batch in train_dataloader: train_loss = train_step(batch) train_accumulator.update(train_loss) if step % 25 == 0: data_valid = next(valid_iterator) valid_loss = valid_step(data_valid) valid_accumulator.update(valid_loss) if step % 1000 == 0 or (step < 1000 and step % 100 == 0): to_log = dict({ **train_loss, **valid_loss, **{ 'current_step': step } }) if step % 5000 == 0 or (step < 5000 and step % 1000 == 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 not args['debug']: wandb.log(to_log, step=step) train_accumulator.reset() valid_accumulator.reset() print(step) if step % 10000 == 0: ckpt_saver_enc(model.encoder, step, optimizer, scaler=None) ckpt_saver_dec(model.decoder, step, optimizer, scaler=None) step += 1 class Scale(torch.nn.Module): def __init__(self, scale_factor): super().__init__() self.scale_factor = scale_factor def forward(self, x): return x * self.scale_factor if __name__ == '__main__': if not args['debug']: init_wandb() skirt_modifier = '_skirt' if config['is_skirt'] else '' dataset_train = Dataset(config['train_dir'], config['signature'], device=config['device'], frames_file=config['train_frames'], use_cache=config['dataset_in_memory'], is_cape=config['is_cape']) dataset_valid = Dataset(config['valid_dir'], config['signature'], device=config['device'], frames_file=config['valid_frames'], use_cache=config['dataset_in_memory'], is_cape=config['is_cape']) train_dataloader = DataLoader(dataset_train, batch_size=4, drop_last=True, shuffle=True) valid_dataloader = DataLoader(dataset_valid, batch_size=4, drop_last=True, shuffle=True) train_accumulator = Accumulator() valid_accumulator = Accumulator() model : AutoEncoder = AutoEncoder(config['cond_ae']) optimizer = optim.Adam(model.parameters(), lr=config['lr']) # _MSSSIM = MSSSIM(data_range=2).to(config['device']) _MSSSIM = MS_SSIM(data_range=2.8, size_average=True, channel=3) if config['pretrained_model'] != '': load_model(model.encoder, config['pretrained_model'] + '_enc') load_model(model.decoder, config['pretrained_model'] + '_dec') ckpt_saver_enc = CheckpointSaver('checkpoints/iccv/torch/' + config['name'] + '_enc', top_n=5) ckpt_saver_dec = CheckpointSaver('checkpoints/iccv/torch/' + config['name'] + '_dec', top_n=5) run_name = config['name'] print(f'started training: {run_name}') if not args['debug']: # model = torch.compile(model) wandb.watch(model, log='all', log_freq=10000, log_graph=True) train()