import os import sys from configs.config_abl_all_skirt import config as config_a from configs.config_abl_extra_loss_skirt import config as config_b from configs.config_abl_norm_skirt import config as config_c os.environ["CUDA_VISIBLE_DEVICES"] = '6' 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 glob 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 from postprocessing import fix_collision if config_a['is_skirt']: from losses import edge_loss_skirt as edge_loss else: from losses import edge_loss from losses import collision_ratio, kl_loss #, concept_loss # from losses import collision_penalty as collision_penalty from losses import collision_loss as collision_penalty from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d, UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision from dataset import DatasetFactory, StaticDataset from custom_utils.smpl import SMPL from models.cvae_model import CVAE from custom_utils.supersmpl_io import writeOBJ from plotly.subplots import make_subplots uv2mesh = UV2Mesh(res=256, is_skirt=config_a['is_skirt'], is_adaptive=False) def plot(mesh_gt, pred_a, pred_b, pred_c, body, mask): fig = make_subplots(rows=1, cols=4, start_cell="top-left", specs = [ [{ 'type': 'scene' } for _ in range(4)] ]) _, faces_garment = _maskFaces(np.zeros((14475, 3), np.float32), F, mask) faces = np.concatenate((F, faces_garment + 14475), axis=0) mesh_gt = np.concatenate((body, mesh_gt[mask, :]), axis=0) pred_a = np.concatenate((body, pred_a[mask, :]), axis=0) pred_b = np.concatenate((body, pred_b[mask, :]), axis=0) pred_c = np.concatenate((body, pred_c[mask, :]), axis=0) colors = np.concatenate((np.ones_like(body, dtype=np.int32)*100, np.ones_like(mesh_gt, dtype=np.int32)*230), axis=0) 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", vertexcolor=colors, ), row=1, col=1) fig.add_trace(go.Mesh3d( x=pred_a[:,0], y=pred_a[:,2], z=pred_a[:,1], i = faces[:,0], j = faces[:,1], k = faces[:,2], text="Pred A", vertexcolor=colors, ), row=1, col=2) fig.add_trace(go.Mesh3d( x=pred_b[:,0], y=pred_b[:,2], z=pred_b[:,1], i = faces[:,0], j = faces[:,1], k = faces[:,2], text="Pred B", vertexcolor=colors, ), row=1, col=3) fig.add_trace(go.Mesh3d( x=pred_c[:,0], y=pred_c[:,2], z=pred_c[:,1], i = faces[:,0], j = faces[:,1], k = faces[:,2], text="Pred C", vertexcolor=colors, ), row=1, col=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), ) 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, ) return fig def step(model, config, batch): if config['use_skinning']: uv_orig = batch['uv_unposed'] else: uv_orig = batch['uv_posed'] pred, _, _ = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False) mesh_pred = uv2mesh(pred) if config['use_skinning']: 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][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])]) mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis] mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped) else: mesh_pred_posed = mesh_pred # mesh_pred_posed_fixed = fix_collision(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask']) return mesh_pred_posed, None #mesh_pred_posed_fixed if __name__ == '__main__': # init_wandb() parser = argparse.ArgumentParser(description='') parser.add_argument('--name', type=str) args = vars(parser.parse_args()) skirt_modifier = '_skirt' if config_a['is_skirt'] else '' folder = config_a['test_dir'] smpl = SMPL(use_one_hot=False) model_a = CVAE(config_a) model_b = CVAE(config_b) model_c = CVAE(config_c) F = np.load("custom_utils/smpl_faces" + skirt_modifier + ".npy").astype(np.int32) iteration = '70000' load_model(model_a, 'checkpoints/' + config_a['name'], iteration=iteration) load_model(model_b, 'checkpoints/' + config_b['name'], iteration=iteration) load_model(model_c, 'checkpoints/' + config_c['name'], iteration=iteration) # load_model(model, 'checkpoints/' + 'abl_all_120k') assert config_a['remove_global_orientation'] == config_b['remove_global_orientation'] == config_c['remove_global_orientation'] factory = DatasetFactory() dataset_a = factory.get_dataset(folder=config_a['test_dir'], batch_size=config_a['batch_size'], signature=config_a['signature_dynamic'], resolutions=[config_a['resolution']], in_memory=False, do_repeat=False, use_one_hot=config_a['use_one_hot'], use_no_orient=config_a['remove_global_orientation'], shuffle=False, testing=True, # frames_file='frames_abl.txt', ) static_dataset_a = StaticDataset(folder=config_a['test_dir'], signature=config_a['signature_static'], resolutions=[config_a['resolution']], in_memory=True) dataset_b = factory.get_dataset(folder=config_b['test_dir'], batch_size=config_b['batch_size'], signature=config_b['signature_dynamic'], resolutions=[config_b['resolution']], in_memory=False, do_repeat=False, use_one_hot=config_b['use_one_hot'], use_no_orient=config_b['remove_global_orientation'], shuffle=False, testing=True, # frames_file='frames_abl.txt', ) static_dataset_b = StaticDataset(folder=config_b['test_dir'], signature=config_b['signature_static'], resolutions=[config_b['resolution']], in_memory=True) dataset_c = factory.get_dataset(folder=config_c['test_dir'], batch_size=config_c['batch_size'], signature=config_c['signature_dynamic'], resolutions=[config_c['resolution']], in_memory=False, do_repeat=False, use_one_hot=config_c['use_one_hot'], use_no_orient=config_c['remove_global_orientation'], shuffle=False, testing=True, # frames_file='frames_abl.txt', ) static_dataset_c = StaticDataset(folder=config_c['test_dir'], signature=config_c['signature_static'], resolutions=[config_c['resolution']], in_memory=True) iterator_a = iter(dataset_a) iterator_b = iter(dataset_b) iterator_c = iter(dataset_c) faces_folder = '/home/workspace/data/results/support/faces' + ('_skirt' if config_a['is_skirt'] else '') ids = os.listdir(faces_folder) ids = [id.split('.')[0] for id in ids] faces = {id : np.load(faces_folder + '/' + id + '.npy') for id in ids } while True: batch_a = iterator_a.get_next() batch_b = iterator_b.get_next() batch_c = iterator_c.get_next() batch_a = static_dataset_a.expand_batch(batch_to_dict(batch_a, config_a['signature_dynamic'])) batch_b = static_dataset_b.expand_batch(batch_to_dict(batch_b, config_b['signature_dynamic'])) batch_c = static_dataset_c.expand_batch(batch_to_dict(batch_c, config_c['signature_dynamic'])) mesh_pred_posed_a, mesh_pred_posed_fixed_a = step(model_a, config_a, batch_a) mesh_pred_posed_b, mesh_pred_posed_fixed_b = step(model_b, config_b, batch_b) mesh_pred_posed_c, mesh_pred_posed_fixed_c = step(model_c, config_c, batch_c) mesh_pred_posed_a = mesh_pred_posed_a.numpy() mesh_pred_posed_b = mesh_pred_posed_b.numpy() mesh_pred_posed_c = mesh_pred_posed_c.numpy() mask = batch_a['mesh_mask'].numpy().astype(bool) gt = batch_a['mesh_posed'].numpy() body = batch_a['mesh_body_posed'].numpy() for i in range(mask.shape[0]): id, frame_nr = batch_a['id'][i].numpy().decode("utf-8"), batch_a['frame_nr'][i].numpy().decode("utf-8") plot(gt[i], mesh_pred_posed_a[i], mesh_pred_posed_b[i], mesh_pred_posed_c[i], body[i], mask[i]).show() print()