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()) config_module = importlib.import_module(args['config']) config = config_module.config if args['debug']: from configs.pyr_64_cape_m 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 argparse import wandb import tqdm import random import numpy as np import plotly.graph_objects as go import plotly.express as ex from PIL import Image if config['is_skirt']: from losses.losses import edge_loss_skirt as edge_loss else: from losses.losses import edge_loss import torch import torch.nn as nn import torch.optim as optim import torch.nn.functional as F from data.dataset import Dataset from utils.checkpoints import CheckpointSaver, load_model from utils.utils import InfiniteDataLoader as DataLoader from utils.postprocess import fix_collision from losses.losses import collision_loss, normal_loss, kl_loss from pytorch_msssim import MS_SSIM from custom_utils.custom_utils import UV2Mesh, Accumulator, plot_3d, get_summary_html, maskFacesBatch, get_summary_str, plot_3d_collision, group_inputs_for_levels from smpl.smpl_torch import SMPL from plotly.subplots import make_subplots from models.pyramid_model import Pyramid def init_wandb(): run = wandb.init(project='iccv', name=config['name'], notes=config['notes'], dir='/data-local/127/temp', tags=config['tags']) artifact = wandb.Artifact('code', type='code') artifact.add_file('scripts/cvae_pyramid.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('models/pyramid_model.py') artifact.add_file('models/pyramid_level.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 plot_3d(mesh_gt, mesh_pred_unposed_levels, faces, mesh_posed, collision, collision_faces, collision_color): fig = make_subplots(rows=1, cols=1+len(mesh_pred_unposed_levels)+1+1, start_cell="top-left", specs = [ [{ 'type': 'scene' } for _ in range(1+len(mesh_pred_unposed_levels)+1+1)] ]) fig.add_trace(go.Mesh3d( x=mesh_gt[:,0], y=mesh_gt[:,2], z=mesh_gt[:,1], i = faces[:,0], j = faces[:,1], k = faces[:,2], text="Ground Truth" ), row=1, col=1) for i, mesh in enumerate(mesh_pred_unposed_levels): fig.add_trace(go.Mesh3d( x=mesh[:,0], y=mesh[:,2], z=mesh[:,1], i = faces[:,0], j = faces[:,1], k = faces[:,2], text='Unposed level_' + str(i) ), row=1, col=i+2) fig.add_trace(go.Mesh3d( x=mesh_posed[:,0], y=mesh_posed[:,1], z=mesh_posed[:,2], i = faces[:,0], j = faces[:,1], k = faces[:,2], text='Posed GT' ), row=1, col=1+len(mesh_pred_unposed_levels)+1) fig.add_trace(go.Mesh3d( x=collision[:,0], y=collision[:,2], z=collision[:,1], i = collision_faces[:,0], j = collision_faces[:,1], k = collision_faces[:,2], vertexcolor=collision_color, text='Posed output on body' ), row=1, col=1+len(mesh_pred_unposed_levels)+1+1) if len(mesh_pred_unposed_levels) == 1: fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1), scene2_aspectmode='manual', scene2_aspectratio=dict(x=1, y=1, z=1), scene3_aspectmode='manual', scene3_aspectratio=dict(x=1, y=1, z=1), scene4_aspectmode='manual', scene4_aspectratio=dict(x=1, y=1, z=1), ) helper = dict(xaxis = dict(nticks=4, range=[-1,1],), yaxis = dict(nticks=4, range=[-1,1],), zaxis = dict(nticks=4, range=[-1,1],),) fig.update_layout(scene = helper, scene2 = helper, scene3 = helper, scene4 = helper, ) if len(mesh_pred_unposed_levels) == 2: fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1), scene2_aspectmode='manual', scene2_aspectratio=dict(x=1, y=1, z=1), scene3_aspectmode='manual', scene3_aspectratio=dict(x=1, y=1, z=1), scene4_aspectmode='manual', scene4_aspectratio=dict(x=1, y=1, z=1), scene5_aspectmode='manual', scene5_aspectratio=dict(x=1, y=1, z=1), ) helper = dict(xaxis = dict(nticks=4, range=[-1,1],), yaxis = dict(nticks=4, range=[-1,1],), zaxis = dict(nticks=4, range=[-1,1],),) fig.update_layout(scene = helper, scene2 = helper, scene3 = helper, scene4 = helper, scene5 = helper, ) if len(mesh_pred_unposed_levels) == 3: fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1), scene2_aspectmode='manual', scene2_aspectratio=dict(x=1, y=1, z=1), scene3_aspectmode='manual', scene3_aspectratio=dict(x=1, y=1, z=1), scene4_aspectmode='manual', scene4_aspectratio=dict(x=1, y=1, z=1), scene5_aspectmode='manual', scene5_aspectratio=dict(x=1, y=1, z=1), scene6_aspectmode='manual', scene6_aspectratio=dict(x=1, y=1, z=1,) ) helper = dict(xaxis = dict(nticks=4, range=[-1,1],), yaxis = dict(nticks=4, range=[-1,1],), zaxis = dict(nticks=4, range=[-1,1],),) fig.update_layout(scene = helper, scene2 = helper, scene3 = helper, scene4 = helper, scene5 = helper, scene6 = helper, ) if len(mesh_pred_unposed_levels) == 4: fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1), scene2_aspectmode='manual', scene2_aspectratio=dict(x=1, y=1, z=1), scene3_aspectmode='manual', scene3_aspectratio=dict(x=1, y=1, z=1), scene4_aspectmode='manual', scene4_aspectratio=dict(x=1, y=1, z=1), scene5_aspectmode='manual', scene5_aspectratio=dict(x=1, y=1, z=1), scene6_aspectmode='manual', scene6_aspectratio=dict(x=1, y=1, z=1,), scene7_aspectmode='manual', scene7_aspectratio=dict(x=1, y=1, z=1,), ) helper = dict(xaxis = dict(nticks=4, range=[-1,1],), yaxis = dict(nticks=4, range=[-1,1],), zaxis = dict(nticks=4, range=[-1,1],),) fig.update_layout(scene = helper, scene2 = helper, scene3 = helper, scene4 = helper, scene5 = helper, scene6 = helper, scene7 = helper, ) if len(mesh_pred_unposed_levels) == 5: fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1), scene2_aspectmode='manual', scene2_aspectratio=dict(x=1, y=1, z=1), scene3_aspectmode='manual', scene3_aspectratio=dict(x=1, y=1, z=1), scene4_aspectmode='manual', scene4_aspectratio=dict(x=1, y=1, z=1), scene5_aspectmode='manual', scene5_aspectratio=dict(x=1, y=1, z=1), scene6_aspectmode='manual', scene6_aspectratio=dict(x=1, y=1, z=1,), scene7_aspectmode='manual', scene7_aspectratio=dict(x=1, y=1, z=1,), scene8_aspectmode='manual', scene8_aspectratio=dict(x=1, y=1, z=1,), ) helper = dict(xaxis = dict(nticks=4, range=[-1,1],), yaxis = dict(nticks=4, range=[-1,1],), zaxis = dict(nticks=4, range=[-1,1],),) fig.update_layout(scene = helper, scene2 = helper, scene3 = helper, scene4 = helper, scene5 = helper, scene6 = helper, scene7 = helper, scene8 = helper, ) return fig def train_step(batch): model.train() # with torch.autocast(device_type='cuda', dtype=torch.float16, enabled=use_amp): levels_input, conds = group_inputs_for_levels(batch, config) out_levels = model([levels_input, conds]) if config['use_skinning']: mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed'] else: mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed'] output = dict() reconstr_loss_total = 0 kl_total = 0 #for i, res in enumerate(config['pyramid']['resolutions']): i = -1 res = config['pyramid']['resolutions'][-1] res_modifier = '_' + str(res) if res != 512 else '' pred, mean, logvar = out_levels[i] mesh_pred = uv2mesh(pred) if config['use_skinning']: shape = batch['pose_shape'][:, 72:] gender = torch.greater_equal(shape[:, 10] , 0.5).to(dtype=torch.int64) shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])]) mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None] mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0] else: mesh_pred_posed = mesh_pred # is the output already masked? # ms_ssim = torch.mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1))) # ms_ssim = torch.mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3)) e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask'])) c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask']) c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio) l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((uv_orig - pred) ** 2), dim=-1), dim=[1, 2])) l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, dim=-1), dim=-1)) n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape']) kl = kl_loss(mean, logvar) if config['use_extra_losses']: reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss) if not config['is_cape']: reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] else: reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss) if config['use_norm_loss'] and step > 2000: reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff'] kl_total += kl loss = reconstr_loss_total + g_balancing_coeff * kl_total # scaler.scale(loss).backward() # scaler.step(optimizer) # scaler.update() # optimizer.zero_grad() optimizer.zero_grad() loss.backward() optimizer.step() model.eval() with torch.inference_mode(): mean = torch.mean(mean) logvar = torch.mean(logvar) ms_ssim = torch.mean(_MSSSIM(pred + 1, batch['uv_static'] + 1)) metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred.detach()) ** 2, axis=-1))) / torch.sum(batch['mesh_mask']) output = { **output, **{ 'train/edge_loss' + res_modifier: e_loss, 'train/collision_loss' + res_modifier: c_loss,'train/euclid_error' + res_modifier: metric, 'train/mean' + res_modifier: mean, 'train/logvar' + res_modifier: logvar, 'train/kl_loss' + res_modifier: kl, 'train/var' + res_modifier: np.e ** logvar, 'train/l2_loss' + res_modifier: l2_loss, 'train/normal_loss': n_loss, 'train/euclid_error': metric, 'train/l2_mesh_loss': l2_mesh_loss, 'train/ms_ssim' + res_modifier: ms_ssim, } } # return { **{ 'train/loss': loss, 'train/reconstr_loss_total': reconstr_loss_total, 'train/kl_total': kl_total }, **output } def valid_step(batch): model.eval() with torch.inference_mode(): levels_input, conds = group_inputs_for_levels(batch, config) out_levels = model([levels_input, conds]) if config['use_skinning']: mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed'] else: mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed'] output = dict() reconstr_loss_total = 0 kl_total = 0 #for i, res in enumerate(config['pyramid']['resolutions']): i = -1 res = config['pyramid']['resolutions'][-1] res_modifier = '_' + str(res) if res != 512 else '' pred, mean, logvar = out_levels[i] mesh_pred = uv2mesh(pred) if config['use_skinning']: shape = batch['pose_shape'][:, 72:] gender = torch.greater_equal(shape[:, 10] , 0.5).to(dtype=torch.int64) shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])]) mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None] mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0] else: mesh_pred_posed = mesh_pred # is the output already masked? # ms_ssim = torch.mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1))) # ms_ssim = torch.mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3)) e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask'])) c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask']) c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio) l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((uv_orig - pred) ** 2), dim=-1), dim=[1, 2])) l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, dim=-1), dim=-1)) n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape']) kl = kl_loss(mean, logvar) if config['use_extra_losses']: reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss) if not config['is_cape']: reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] else: reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss) if config['use_norm_loss'] and step > 2000: reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff'] kl_total += kl loss = reconstr_loss_total + g_balancing_coeff * kl_total mean = torch.mean(mean) logvar = torch.mean(logvar) ms_ssim = torch.mean(_MSSSIM(pred + 1, batch['uv_static'] + 1)) metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred.detach()) ** 2, axis=-1))) / torch.sum(batch['mesh_mask']) output = { **output, **{ 'valid/edge_loss' + res_modifier: e_loss, 'valid/collision_loss' + res_modifier: c_loss,'valid/euclid_error' + res_modifier: metric, 'valid/mean' + res_modifier: mean, 'valid/logvar' + res_modifier: logvar, 'valid/kl_loss' + res_modifier: kl, 'valid/var' + res_modifier: np.e ** logvar, 'valid/l2_loss' + res_modifier: l2_loss, 'valid/normal_loss': n_loss, 'valid/euclid_error': metric, 'valid/l2_mesh_loss': l2_mesh_loss, 'valid/ms_ssim' + res_modifier: ms_ssim, } } # return { **{ 'valid/loss': loss, 'valid/reconstr_loss_total': reconstr_loss_total, 'valid/kl_total': kl_total }, **output } def test_step(batch): levels_input, conds = group_inputs_for_levels(batch, config) out_levels = model([levels_input, conds], training=False) shape = batch['pose_shape'][:, 72:] gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32) shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, dim=0) for i in range(shape.shape[0])]) mesh_orig = batch['mesh_unposed'] output = dict() reconstr_loss_total = 0 kl_total = 0 #for i, res in enumerate(config['pyramid']['resolutions']): i = -1 res = config['pyramid']['resolutions'][-1] res_modifier = '_' + str(res) if res != 512 else '' pred, mean, logvar = out_levels[i] mesh_pred = uv2mesh(pred) mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None] mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped) # is the output already masked? e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask'])) c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask']) c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio) l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((batch['uv_unposed'] - pred) ** 2), dim=-1), dim=[1, 2])) l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred) ** 2, dim=-1), dim=-1)) # ms_ssim = torch.mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1))) # ms_ssim = torch.mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3)) kl = kl_loss(mean, logvar) reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss) if not config['is_cape']: reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] # reconstr_loss_total += config['pyramid']['loss_weights'][i] * (l2_loss + (e_loss + c_loss) * config['reg_loss_coeff']) kl_total += kl mean = torch.mean(mean) logvar = torch.mean(logvar) metric = torch.sum(tf.math.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred) ** 2, dim=-1))) / torch.sum(batch['mesh_mask']) euclid_error_per_garment = torch.sum(tf.math.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred) ** 2, dim=-1)), dim=1) / torch.sum(batch['mesh_mask'], dim=1) output = { **output, **{ 'test/edge_loss' + res_modifier: e_loss, 'test/collision_loss' + res_modifier: c_loss,'test/euclid_error' + res_modifier: metric, 'test/mean' + res_modifier: mean, 'test/logvar' + res_modifier: logvar, 'test/kl_loss' + res_modifier: kl, 'test/var' + res_modifier: np.e ** logvar, 'test/l2_loss' + res_modifier: l2_loss, 'test/euclid_error': metric, 'test/collision_ratio' + res_modifier: c_ratio } } loss = reconstr_loss_total + balancing_coeff * kl_total return { **{ 'test/loss': loss, 'test/reconstr_loss_total': reconstr_loss_total, 'test/kl_total': kl_total }, **output }, euclid_error_per_garment def plot_everything(batch: dict, type: str): if config['use_skinning']: mesh_orig, uv_orig = batch['mesh_unposed'].cpu().numpy(), batch['uv_unposed'] else: mesh_orig, uv_orig = batch['mesh_posed'].cpu().numpy(), batch['uv_posed'] model.eval() with torch.inference_mode(): levels_input = group_inputs_for_levels(batch, config) output_levels = model(levels_input) mesh_pred_levels = [uv2mesh(output_levels[i][0]).detach().cpu().numpy() for i in range(len(output_levels))] mesh_orig_posed = batch['mesh_posed'].cpu().numpy() body = batch['mesh_body_posed'].cpu().numpy() orig_img = (torch.permute(uv_orig, [0,2,3,1]) + 1) / 2 uv_static_img = (torch.permute(batch['uv_static'], [0,2,3,1]) + 1) / 2 uv_body_posed_img = (torch.permute(batch['uv_body_posed'], [0,2,3,1]) + 1) / 2 uv_curvature = (torch.tile(torch.argmax(torch.permute(batch['uv_curvature'], [0,2,3,1]), dim=-1)[:,:,:,None], [1,1,1,3]) / 6) pred_img = torch.concatenate([torch.permute(F.interpolate(output_levels[i][0], size=(512, 256), mode='bilinear'), [0,2,3,1]) for i in range(len(output_levels))], dim=3) # pred_img = (pred_img - pred_img.min(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis]) / (pred_img.max(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis] - pred_img.min(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis]) pred_img = (pred_img - pred_img.flatten().reshape(pred_img.shape[0], -1).min(1)[0][:,None,None,None]) / (pred_img.flatten().reshape(pred_img.shape[0], -1).max(1)[0][:,None,None,None] - pred_img.flatten().reshape(pred_img.shape[0], -1).min(1)[0][:,None,None,None]) img = torch.concat((uv_static_img, uv_body_posed_img, uv_curvature, orig_img, pred_img), axis=2) imgs = [wandb.Image(img[i].cpu().numpy()) for i in range(4)] _F = np.load("smpl/smpl_faces" + skirt_modifier + ("_orig" if config['is_cape'] else "") + ".npy") mask = batch['mesh_mask'].cpu().numpy().astype(bool) _, faces = maskFacesBatch(np.ones_like(mesh_orig), _F, mask) if config['use_skinning']: shape = batch['pose_shape'][:, 72:] gender = torch.greater_equal(shape[:, 10] , 0.5).to(torch.long) shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])]).cpu().numpy() gt = [mesh_orig[i][mask[i], :] + shape_offsets[i, mask[i], :] for i in range(mask.shape[0])] mesh_unposed_shaped_levels = [[] for _ in range(mask.shape[0])] for i in range(len(output_levels)): mesh_unposed_shaped = [mesh_pred_levels[i][j, mask[j], :] + shape_offsets[j, mask[j]] for j in range(mask.shape[0])] for k in range(mask.shape[0]): mesh_unposed_shaped_levels[k].append(mesh_unposed_shaped[k]) # full res version mesh_unposed_shaped_full = np.zeros((mask.shape[0], config['smpl_res'], 3), dtype=np.float32) for i in range(mask.shape[0]): mesh_unposed_shaped_full[i, mask[i], :] = mesh_unposed_shaped[i] mesh_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], torch.tensor(mesh_unposed_shaped_full, device=config['device']))[0].cpu().numpy() else: mesh_posed = mesh_pred_levels[-1] gt = [mesh_orig[i][mask[i], :] for i in range(mesh_posed.shape[0])] mesh_unposed_shaped_levels = [[mesh_pred_levels[i][j, mask[j], :] for i in range(len(output_levels))] for j in range(mask.shape[0])] gt_posed = [mesh_orig_posed[i, mask[i], :] for i in range(mask.shape[0])] mesh_posed_fixed = fix_collision(torch.Tensor(mesh_posed).to('cuda'), torch.Tensor(body).to('cuda'), torch.Tensor(mask).to('cuda')).cpu().numpy() mesh_posed = [mesh_posed[j, mask[j], :] for j in range(mask.shape[0])] if config['is_cape']: collision = mesh_posed collision_faces = faces collision_color = [np.ones_like(mesh_posed[i], dtype=np.int32)*230 for i in range(len(mesh_posed))] else: collision = [np.concatenate((body[i], mesh_posed[i]), axis=0) for i in range(len(mesh_posed))] collision_faces = [np.concatenate((_F, faces[i] + config['smpl_res']), axis=0) for i in range(len(mesh_posed))] collision_color = [np.concatenate((np.ones_like(body[i], dtype=np.int32)*100, np.ones_like(mesh_posed[i], dtype=np.int32)*230), axis=0) for i in range(len(mesh_posed))] figs = { type + "/garment_" + str(i): plot_3d(gt[i], mesh_unposed_shaped_levels[i], faces[i], gt_posed[i], collision[i], collision_faces[i], collision_color[i]) for i in range(4) } if config['is_cape']: figs_coll = dict() else: garment_posed_fixed = [mesh_posed_fixed[i, mask[i], :] for i in range(body.shape[0])] collision_fixed = [np.concatenate((body[i], garment_posed_fixed[i]), axis=0) for i in range(len(mesh_posed))] gt_posed = [batch['mesh_posed'].cpu().numpy()[i, mask[i], :] for i in range(mask.shape[0])] collision_gt = [np.concatenate((body[i], gt_posed[i]), axis=0) for i in range(len(gt_posed))] figs_coll = { type + "/garment_" + str(i) + '_collision': plot_3d_collision(collision_gt[i], collision[i], collision_fixed[i], collision_faces[i], collision_color[i]) for i in range(4) } return { **figs, **figs_coll, **{ type + '/images': imgs, } } def sample(folder): # run = wandb.init(project='vae_plots', name=folder.split('/')[-1]) load_model(model,folder) count = 0 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) nr_of_samples=2 pred = model.sample(batch['uv_static'][0], batch['uv_body_posed'][0], uv_curvature[0], batch['uv_mask'][0], nr_of_samples=nr_of_samples) pose, shape = batch['pose_shape'][0, :72], batch['pose_shape'][0, 72:] pose, shape = tf.tile(pose[None,:], [nr_of_samples,1]), tf.tile(shape[None,:], [nr_of_samples,1]) mesh_pred = uv2mesh(tf.transpose(pred, [0,3,1,2])) mesh_posed = smpl.run_garment(pose, shape, mesh_pred).numpy() mesh_orig = batch['mesh_posed'][0].numpy() mesh_orig_reposed = smpl.run_garment(pose[:1], shape[:1], batch['mesh_unposed'][:1]).numpy()[0] body = batch['mesh_body_posed'][0].numpy() body_color = np.ones_like(body, dtype=np.int32)*100 F = np.load("custom_utils/smpl_faces.npy") mask = batch['mesh_mask'].numpy().astype(bool)[0] _, faces = _maskFaces(np.ones((14475, 3)), F, mask) pred_zero = model.sample(batch['uv_static'][0], batch['uv_body_posed'][0], uv_curvature[0], batch['uv_mask'][0], nr_of_samples=nr_of_samples, zero_latent=True) mesh_pred_zero = uv2mesh(tf.transpose(pred_zero, [0,3,1,2])) mesh_posed_zero = smpl.run_garment(pose, shape, mesh_pred_zero).numpy() meshes = [] meshes.append(go.Mesh3d( # 8 vertices of a cube x=mesh_orig_reposed[mask,0], y=mesh_orig_reposed[mask,2], z=mesh_orig_reposed[mask,1], # i, j and k give the vertices of triangles i = faces[:,0], j = faces[:,1], k = faces[:,2] )) for i in range(nr_of_samples): x = mesh_posed[i][mask, :].copy() # x[:, 2] += 1 * (i + 1) x[:, 2] += 1 meshes.append(go.Mesh3d( # 8 vertices of a cube x=x[:,0], y=x[:,2], z=x[:,1], # i, j and k give the vertices of triangles i = faces[:,0], j = faces[:,1], k = faces[:,2] )) for i in range(nr_of_samples): x = mesh_posed_zero[i][mask, :].copy() # x[:, 2] += 1 * (i + 1) x[:, 2] += 2 meshes.append(go.Mesh3d( # 8 vertices of a cube x=x[:,0], y=x[:,2], z=x[:,1], # i, j and k give the vertices of triangles i = faces[:,0], j = faces[:,1], k = faces[:,2] )) # for i in range(5): # x = body.copy() # x[:, 2] += 1 * i # meshes.append(go.Mesh3d( # # 8 vertices of a cube # x=x[:,0], # y=x[:,2], # z=x[:,1], # # i, j and k give the vertices of triangles # i = F[:,0], # j = F[:,1], # k = F[:,2], # vertexcolor=body_color # )) fig = go.Figure(data=meshes) fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=2, z=1)) # fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=nr_of_samples-1, z=1)) fig.update_layout( scene = dict( xaxis = dict(nticks=4, range=[-1,1],), # yaxis = dict(nticks=4, range=[-1,nr_of_samples+1],), yaxis = dict(nticks=4, range=[-1,3],), zaxis = dict(nticks=4, range=[-1,1],),) ) # wandb.log({'plot_' + str(count): fig}) fig.show() pred = pred.numpy() frames = [Image.fromarray(((pred[i] + 1) * 128).astype(np.int8), mode='RGB') for i in range(pred.shape[0])] frames[0].save("temp/garment_1.gif", format="GIF", append_images=frames[1:], save_all=True, duration=500, loop=0) if count > 10: break print(count) count += 1 print() def test(): garment_type_table = np.load('custom_data/garment_type_table_test.npy', allow_pickle=True).item() str_split = config['name'].split('_') test_idx = str_split.index('test') checkpoint_name = '_'.join(str_split[:test_idx]) load_model(model, 'checkpoints/' + checkpoint_name) dataset_test = factory.get_dataset(folder=config['test_dir'], batch_size=config['batch_size'], signature=config['signature_dynamic'], use_filled=config['use_filled'], resolutions=dataset_resolutions, in_memory=False, do_repeat=False) static_dataset_test = StaticDataset(folder=config['test_dir'], signature=config['signature_static'], use_filled=config['use_filled'], resolutions=dataset_resolutions, in_memory=False) step = 0 losses = [] if config['is_skirt']: per_garment_errors = { 'Tshirt': [], 'Dress': [], 'Skirt': [], 'Top': [] } else: per_garment_errors = { 'Tshirt': [], 'Jumpsuit': [], 'Trousers': [], 'Top': [] } for batch in tqdm.tqdm(dataset_test): batch = static_dataset_test.expand_batch(batch_to_dict(batch, config['signature_dynamic'])) test_loss, euclid_error_per_garment = test_step(batch) losses.append(test_loss) for i, id in enumerate(batch['id']): id_str = id.numpy().decode("utf-8") per_garment_errors[garment_type_table[id_str]].append(euclid_error_per_garment[i].numpy()) to_log = { **{ 'current_step': step }, **test_loss } if step % 1000 == 0: figs = plot_everything(batch, 'test') to_log = { **to_log, **figs } wandb.log(to_log, step = step) # print(step) step += 1 # averages = dict() path_to_plotly_html = "temp/plotly_figure.html" histograms = dict() for key in test_loss.keys(): accumulated = [losses[i][key].numpy() for i in range(len(losses))] fig = ex.histogram(accumulated, title='Average: ' + str(np.asarray(accumulated).mean())) fig.write_html(path_to_plotly_html, auto_play = False) histograms['all/' + key.split('/')[-1] + '_hist'] = wandb.Html(path_to_plotly_html) # averages['all/' + key.split('/')[-1] + '_avg'] = np.asarray(accumulated).mean() for key in per_garment_errors.keys(): fig = ex.histogram(per_garment_errors[key], title='Average: ' + str(np.asarray(per_garment_errors[key]).mean())) fig.write_html(path_to_plotly_html, auto_play = False) histograms['all/' + key + 'euclid_error_hist'] = wandb.Html(path_to_plotly_html) wandb.log({ **histograms }, step = step) wandb.finish() pass def generate_results(): load_model(model, 'checkpoints/' + config['name']) dataset_test = factory.get_dataset(folder=config['test_dir'], batch_size=config['batch_size'], # batch_size=1, signature=config['signature_dynamic'], resolutions=dataset_resolutions, in_memory=config['dataset_in_memory'], is_cape=config['is_cape'], frames_file=config['frames_file'] if 'frames_file' in config.keys() else None, do_repeat=False, shuffle=False) static_dataset_test = StaticDataset(folder=config['test_dir'], signature=config['signature_static'], resolutions=dataset_resolutions, in_memory=True, is_cape=config['is_cape']) folder = os.path.join('/home/workspace/data/results/cape', config['name']) os.makedirs(folder, exist_ok=True) for batch in tqdm.tqdm(dataset_test): batch = static_dataset_test.expand_batch(batch_to_dict(batch, config['signature_dynamic'])) levels_input, conds = group_inputs_for_levels(batch, config) out_levels = model([levels_input, conds], training=False) shape = batch['pose_shape'][:, 72:] gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32) shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])]) i = -1 pred = out_levels[i][0] mesh_pred = uv2mesh(pred) mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None] mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped) for i in range(batch['id'].shape[0]): mask = batch['mesh_mask'][i].numpy().astype(bool) id, frame_nr = batch['id'][i].numpy().decode("utf-8"), batch['frame_nr'][i].numpy().decode("utf-8") unposed = mesh_pred[i].numpy()[mask, :] posed = mesh_pred_posed[i].numpy()[mask, :] np.save(os.path.join(folder, id + '_' + frame_nr + '_posed.npy'), posed) np.save(os.path.join(folder, id + '_' + frame_nr + '_unposed.npy'), unposed) pass def speed_step(levels_input, conds): return model.sample([levels_input, conds], training=False) def train(): global g_balancing_coeff 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 % 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 train_loss['train/euclid_error'] < config['balancing_activation_limit']: g_balancing_coeff += 1 / 10000 if step % 10000 == 0: ckpt_saver(model, step, optimizer, None) step += 1 if __name__ == '__main__': if not args['debug']: init_wandb() use_amp = True smpl = SMPL(orig_smpl=config['is_cape'], path='smpl', device=config['device']) skirt_modifier = '_skirt' if config['is_skirt'] else '' dataset_resolutions = config['pyramid']['resolutions'].copy() if 512 not in dataset_resolutions: dataset_resolutions.append(512) dataset_train = Dataset(config['train_dir'], config['signature'], device=config['device'], frames_file=config['train_frames'], use_cache=config['dataset_in_memory'], resolutions=dataset_resolutions, 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'], resolutions=dataset_resolutions, 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: Pyramid = Pyramid(config) optimizer = optim.Adam(model.parameters(), lr=config['lr']) _MSSSIM = MS_SSIM(data_range=2, size_average=True, channel=3) ckpt_saver = CheckpointSaver('checkpoints/iccv/torch/' + config['name'], top_n=5) scaler = torch.cuda.amp.GradScaler(enabled=use_amp) g_balancing_coeff = config['starting_balancing_coeff'] reg_coeff = 1 step = 0 if config['pretrained_model'] != '': # assert len(config['pyramid']['resolutions']) == 1 step = load_model(model, config['pretrained_model'], optimizer=optimizer, scaler=scaler, iteration=config['pretrained_model_iteration']) if not args['debug']: model = torch.compile(model) wandb.watch(model, log='all', log_freq=1000, log_graph=True) if len(config['pyramid']['resolutions']) == 1: for param in model.static_enc.parameters(): param.requires_grad = False for param in model.body_enc.parameters(): param.requires_grad = False for param in model.curv_enc.parameters(): param.requires_grad = False else: load_model(model, config['pyramid']['pretrained_pyramid'], iteration=(config['pyramid']['pretrained_pyramid_iteration'] if 'pretrained_pyramid_iteration' in config.keys() else '')) for param in model.static_enc.parameters(): param.requires_grad = False for param in model.body_enc.parameters(): param.requires_grad = False for param in model.curv_enc.parameters(): param.requires_grad = False # load_model(model.levels[0].upscale_enhancer, config['pyramid']['levels'][0]['upscale_enhancer']) # model.levels[0].upscale_enhancer.trainable = False # for i in range(len(model.levels)-1): # load_model(model.levels[i].upscale_enhancer, config['pyramid']['levels'][i]['upscale_enhancer']) # model.levels[i].upscale_enhancer.trainable = False # if config['pyramid']['resolutions'][-1] != 512: # load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer']) # model.upscale_enhancer.trainable = False for i in range(len(model.levels)-1): for param in model.levels[i].parameters(): param.requires_grad = False # load_model(model.cond_encoder, config['pyramid']['pretrained_pyramid']) # load_model(model.levels[0], config['pyramid']['pretrained_pyramid']) # load_model(model.levels[-1], 'checkpoints/cvae_19') if not args['debug']: model = torch.compile(model) wandb.watch(model, log='all', log_freq=1000, log_graph=True) train()