import os import sys sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/..') import importlib import argparse 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()) os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID" os.environ["CUDA_VISIBLE_DEVICES"] = '7' import time import argparse import wandb import random import numpy as np import torch # 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 import torch.nn.functional as F from data.dataset import Dataset # from torch.utils.data import DataLoader from custom_utils.custom_utils import plot_3d from models.upscaler import Upscaler 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 low_res = 64 is_skirt = False is_cape = True is_male = True skirt_modifier = '_skirt' if is_skirt else '' cape_modifier = '_cape' if is_cape else '' gender_modifier = '' if not is_cape else ('_m' if is_male else '_f') smpl_res = 3638 if is_cape else 14475 use_cache = False name=f'iccv_{low_res}' + skirt_modifier + cape_modifier + gender_modifier if not is_skirt: train_dir = '/data-local/127/train' valid_dir = '/data-local/127/valid' else: train_dir = '/data-local/128/train_skirt' valid_dir = '/data-local/127/valid_skirt' if is_cape: if is_male: train_dir = '/data-local/127/cape_processed/train/male' valid_dir = '/data-local/127/cape_processed/test/male' else: train_dir = '/data-local/127/cape_processed/train/female' valid_dir = '/data-local/127/cape_processed/test/female' def init_wandb(): run = wandb.init(project='upscale', name=name, notes='', dir='/data-local/127/temp', tags=['upscaler', 'iccv']) artifact = wandb.Artifact('code', type='code') artifact.add_file('scripts/upscaler_train.py') artifact.add_file('losses/losses.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=is_skirt, is_smpl_orig=is_cape) def plot_3d(mesh_gt, mesh_pred_unposed, faces): mesh_pred_unposed[:,2] += 1 fig = go.Figure(data=[ go.Mesh3d( # 8 vertices of a cube x=mesh_gt[:,0], y=mesh_gt[:,2], z=mesh_gt[:,1], # i, j and k give the vertices of triangles i = faces[:,0], j = faces[:,1], k = faces[:,2] ), go.Mesh3d( # 8 vertices of a cube x=mesh_pred_unposed[:,0], y=mesh_pred_unposed[:,2], z=mesh_pred_unposed[:,1], # i, j and k give the vertices of triangles i = faces[:,0], j = faces[:,1], k = faces[:,2], ) ]) fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=2, z=1)) fig.update_layout( scene = dict( xaxis = dict(nticks=4, range=[-1,1],), yaxis = dict(nticks=4, range=[-1,3],), zaxis = dict(nticks=4, range=[-1,1],),) ) return fig def train_step(batch): model.train() with torch.autocast(device_type='cuda', dtype=torch.float16, enabled=use_amp): pred = model([batch['uv_unposed' + low_resolution_modifier], batch['uv_mask' + low_resolution_modifier]]) pred = F.interpolate(pred, size=(512, 256), mode='bilinear') l1_loss = torch.mean(torch.sum(torch.abs(batch['uv_unposed'] - pred * batch['uv_mask'].unsqueeze(1)), dim=-1)) if low_res == 32: ms_ssim = torch.mean(_MSSSIM_small(pred * batch['uv_mask'].unsqueeze(1) + 1, batch['uv_unposed'] * batch['uv_mask'].unsqueeze(1) + 1)) else: ms_ssim = torch.mean(_MSSSIM(pred * batch['uv_mask'].unsqueeze(1) + 1, batch['uv_unposed'] * batch['uv_mask'].unsqueeze(1) + 1)) loss = 1e3 * (1 - ms_ssim) scaler.scale(loss).backward() scaler.step(optimizer) scaler.update() optimizer.zero_grad() model.eval() with torch.inference_mode(): mesh_pred = uv2mesh(pred) mesh_orig = batch['mesh_unposed'] metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_mask'].unsqueeze(2) * (mesh_orig - mesh_pred) ** 2, dim=-1))) / torch.sum(batch['mesh_mask']) 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_unposed' + low_resolution_modifier], batch['uv_mask' + low_resolution_modifier]]) pred = F.interpolate(pred, size=(512, 256), mode='bilinear') l1_loss = torch.mean(torch.sum(torch.abs(batch['uv_unposed'] - pred * batch['uv_mask'].unsqueeze(1)), dim=-1)) if low_res == 32: ms_ssim = torch.mean(_MSSSIM_small(pred * batch['uv_mask'].unsqueeze(1) + 1, batch['uv_unposed'] * batch['uv_mask'].unsqueeze(1) + 1)) else: ms_ssim = torch.mean(_MSSSIM(pred * batch['uv_mask'].unsqueeze(1) + 1, batch['uv_unposed'] * batch['uv_mask'].unsqueeze(1) + 1)) loss = 1e3 * (1 - ms_ssim) mesh_pred = uv2mesh(pred) mesh_orig = batch['mesh_unposed'] metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_mask'].unsqueeze(2) * (mesh_orig - mesh_pred) ** 2, dim=-1))) / torch.sum(batch['mesh_mask']) 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() with torch.inference_mode(): pred = model([batch['uv_unposed' + low_resolution_modifier], batch['uv_mask' + low_resolution_modifier]]) pred = F.interpolate(pred, size=(512, 256), mode='bilinear') mesh_pred = uv2mesh(pred) mesh_orig = batch['mesh_unposed'] _F = np.load("smpl/smpl_faces" + skirt_modifier + ("_orig" if is_cape else "") + ".npy") mask = batch['mesh_mask'].cpu().numpy().astype(bool) garment_unposed, faces = maskFacesBatch(mesh_pred.cpu().numpy(), _F, mask) # gt = [mesh_orig[i].numpy()[mask[i], :] for i in range(pred.shape[0])] gt = [mesh_orig[i].cpu().numpy()[mask[i], :] for i in range(pred.shape[0])] figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], faces[i]) for i in range(4) } # figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], faces[i], collision[i], collision_faces[i], collision_color[i]) for i in range(4) } orig_img = batch['uv_unposed'] img = torch.concat((orig_img, pred), axis=2) imgs = [wandb.Image((img[i] + 1) / 2.0) for i in range(4)] return { **figs, **{ type + '/images': imgs} } def train(): global step valid_iterator = iter(valid_dataloader) 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 % 1000 == 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(model, step, optimizer, scaler) step += 1 if __name__ == '__main__': if not args['debug']: init_wandb() use_amp = True uv_mask_body = torch.ones((low_res, low_res//2), device='cuda') low_resolution_modifier = '_' + str(low_res) signature = { 'id', 'frame_nr', 'pose_shape', 'uv_unposed' + low_resolution_modifier, 'uv_unposed', 'mesh_unposed', 'mesh_posed', 'mesh_mask', 'uv_mask', 'uv_mask' + low_resolution_modifier, } # dataset = Dataset('/data-local/127/train', config['signature'], resolutions=[512], device=device, frames_file='frames_jumpsuit.txt') dataset_train = Dataset(train_dir, device='cuda', use_cache=use_cache, signature=signature, frames_file=None, resolutions=[512, low_res], is_cape=is_cape) dataset_valid = Dataset(valid_dir, device='cuda', use_cache=use_cache, signature=signature, frames_file=None, resolutions=[512, low_res], is_cape=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() if low_res == 32 or low_res == 64: kernel_size = 3 elif low_res == 128 or low_res == 256: kernel_size = 5 else: kernel_size = 7 model : Upscaler = Upscaler(kernel_size=kernel_size).to('cuda') optimizer = optim.Adam(model.parameters(), lr=0.0001) scaler = torch.cuda.amp.GradScaler(enabled=use_amp) # _MSSSIM = MSSSIM(data_range=2).to(config['device']) _MSSSIM = MS_SSIM(data_range=2, size_average=True, channel=3, weights=[0.5, 0.2, 0.2, 0.1]) _MSSSIM_small = MS_SSIM(data_range=2, size_average=True, channel=3, weights=[1.0]) step = 0 ckpt_saver = CheckpointSaver('checkpoints/iccv/torch/' + name, top_n=5) print(f'started training: {name}') if not args['debug']: # model = torch.compile(model) wandb.watch(model, log='all', log_freq=1000, log_graph=True) train()