luni/cvpr
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

pyramid update

Browse Source
This commit is contained in:
luni
2022-10-21 22:35:43 +00:00
parent c4513ad6d9
commit 474ac5fe8e
1 changed files with 147 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cvae_pyramid.py
+147 -20
View File
@@ -16,12 +16,13 @@ if gpus:
print(e)
import time
import tqdm
import argparse
import wandb
import random
import numpy as np
import scipy as sp
from custom_utils.custom_utils import UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces
from custom_utils.custom_utils import UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces, get_summary_str
import plotly.graph_objects as go
import plotly.express as ex
from plotly.subplots import make_subplots
@@ -33,17 +34,17 @@ else:
from losses import edge_loss
from tf_utils import check_tf_version, allow_memory_growth, split_gpu_for_testing
from losses import uv_mask_loss, bend_loss, kl_loss
from losses import uv_mask_loss, bend_loss, kl_loss, collision_ratio
# 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
from dataset import DatasetFactory, StaticDataset
from custom_utils.smpl import SMPL
from models.pyramid_model import Pyramid
from models.pyramid_model_optimized import Pyramid
def init_wandb():
run = wandb.init(project='cvae', name=config['name'], notes=config['notes'])
run = wandb.init(project='cvae', name=config['name'], notes=config['notes'], dir='/home/workspace/local-data/temp')
artifact = wandb.Artifact('code', type='code')
artifact.add_file('cvae_pyramid.py')
@@ -60,7 +61,7 @@ def init_wandb():
artifact.add_file('convnext/models/convnext_tf.py')
run.log_artifact(artifact)
uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'])
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)] ])
@@ -215,9 +216,9 @@ def group_inputs_for_levels(batch):
@tf.function
def train_step(batch):
levels_input, conds = group_inputs_for_levels(batch)
with tf.GradientTape() as tape:
levels_input, conds = group_inputs_for_levels(batch)
out_levels = model([levels_input, conds], training=True)
shape = batch['pose_shape'][:, 72:]
@@ -246,9 +247,10 @@ def train_step(batch):
l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((batch['uv_unposed'] - pred) ** 2), axis=-1), axis=[1, 2]))
# ms_ssim = tf.reduce_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 = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3))
l2_mesh_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1), axis=-1))
kl = kl_loss(mean, logvar)
reconstr_loss_total += config['pyramid']['loss_weights'][i] * (l2_loss + (e_loss + c_loss) * config['reg_loss_coeff'])
reconstr_loss_total += config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss + (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
@@ -260,7 +262,7 @@ def train_step(batch):
output = { **output, **{ 'train/edge_loss' + res_modifier: e_loss, 'train/collision_loss' + res_modifier: c_loss,'train/euclid_error' + res_modifier: metric,
'train/ms_ssim' + res_modifier: ms_ssim, '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/euclid_error': metric } }
'train/euclid_error': metric, 'train/l2_mesh_loss': l2_mesh_loss } }
loss = reconstr_loss_total + balancing_coeff * kl_total
@@ -300,9 +302,10 @@ def valid_step(batch):
l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((batch['uv_unposed'] - pred) ** 2), axis=-1), axis=[1, 2]))
# ms_ssim = tf.reduce_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 = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3))
l2_mesh_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1), axis=-1))
kl = kl_loss(mean, logvar)
reconstr_loss_total += config['pyramid']['loss_weights'][i] * (l2_loss + (e_loss + c_loss) * config['reg_loss_coeff'])
reconstr_loss_total += config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss + (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
@@ -314,13 +317,68 @@ def valid_step(batch):
output = { **output, **{ 'valid/edge_loss' + res_modifier: e_loss, 'valid/collision_loss' + res_modifier: c_loss,'valid/euclid_error' + res_modifier: metric,
'valid/ms_ssim' + res_modifier: ms_ssim, '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/euclid_error': metric } }
'valid/euclid_error': metric, 'valid/l2_mesh_loss': l2_mesh_loss } }
loss = reconstr_loss_total + balancing_coeff * kl_total
return { **{ 'valid/loss': loss, 'valid/reconstr_loss_total': reconstr_loss_total, 'valid/kl_total': kl_total }, **output }
@tf.function
def test_step(batch):
levels_input, conds = group_inputs_for_levels(batch)
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][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=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'][:,:,tf.newaxis]
mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
# is the output already masked?
e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
c_loss = tf.reduce_mean(collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask']))
c_ratio = tf.reduce_mean(collision_ratio(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask']))
l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((batch['uv_unposed'] - pred) ** 2), axis=-1), axis=[1, 2]))
# ms_ssim = tf.reduce_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 = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3))
kl = kl_loss(mean, logvar)
reconstr_loss_total += config['pyramid']['loss_weights'][i] * (l2_loss + (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 = tf.reduce_mean(mean)
logvar = tf.reduce_mean(logvar)
metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
euclid_error_per_garment = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1)), axis=1) / tf.reduce_sum(batch['mesh_mask'], axis=1)
output = { **output, **{ 'test/edge_loss' + res_modifier: e_loss, 'test/collision_loss' + res_modifier: c_loss,'test/euclid_error' + res_modifier: metric,
'test/ms_ssim' + res_modifier: ms_ssim, '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):
levels_input = group_inputs_for_levels(batch)
output_levels = model(levels_input, training=False)
@@ -343,7 +401,7 @@ def plot_everything(batch: dict, type: str):
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])]).numpy()
F = np.load("custom_utils/smpl_faces" + skirt_modifier + ".npy")
F = np.load("custom_utils/smpl_faces" + skirt_modifier + ("_orig" if config['is_cape'] else "") + ".npy")
mask = batch['mesh_mask'].numpy().astype(bool)
_, faces = maskFacesBatch(np.ones_like(mesh_orig), F, mask)
@@ -357,16 +415,22 @@ def plot_everything(batch: dict, type: str):
mesh_unposed_shaped_levels[k].append(mesh_unposed_shaped[k])
# full res version
mesh_unposed_shaped_full = np.zeros((mask.shape[0], 14475, 3), dtype=np.float32)
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.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_unposed_shaped_full).numpy()
mesh_posed = [mesh_posed[j, mask[j], :] for j in range(mask.shape[0])]
collision = [np.concatenate((body[i], mesh_posed[i]), axis=0) for i in range(len(mesh_posed))]
collision_faces = [np.concatenate((F, faces[i] + 14475), 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))]
# body_2 = [b.copy() for b in body]
# for i in range(len(gt_posed)):
# body_2[i][:, 1] = body[i][:,2].copy()
# body_2[i][:, 2] = body[i][:,1].copy()
# gt_posed_with_body = [np.concatenate((body_2[i], gt_posed[i]), axis=0) for i in range(len(gt_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) }
return { **figs, **{ type + '/images': imgs, } }
@@ -494,6 +558,68 @@ def sample(folder):
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
if __name__ == '__main__':
init_wandb()
allow_memory_growth()
@@ -501,17 +627,17 @@ if __name__ == '__main__':
parser.add_argument('--name', type=str)
args = vars(parser.parse_args())
smpl = SMPL()
smpl = SMPL(orig_smpl=config['is_cape'])
skirt_modifier = '_skirt' if config['is_skirt'] else ''
dataset_resolutions = config['pyramid']['resolutions'].copy()
if 512 not in dataset_resolutions:
dataset_resolutions.append(512)
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=dataset_resolutions, in_memory=config['dataset_in_memory'])
static_dataset_train = StaticDataset(folder=config['train_dir'], signature=config['signature_static'], use_filled=config['use_filled'], resolutions=dataset_resolutions)
dataset_valid = factory.get_dataset(folder=config['valid_dir'], batch_size=config['batch_size'], signature=config['signature_dynamic'], use_filled=config['use_filled'], resolutions=dataset_resolutions, in_memory=config['dataset_in_memory'])
static_dataset_valid = StaticDataset(folder=config['valid_dir'], signature=config['signature_static'], use_filled=config['use_filled'], resolutions=dataset_resolutions)
dataset_train = factory.get_dataset(folder=config['train_dir'], batch_size=config['batch_size'], signature=config['signature_dynamic'], use_filled=config['use_filled'], resolutions=dataset_resolutions, in_memory=config['dataset_in_memory'], is_cape=config['is_cape'])
static_dataset_train = StaticDataset(folder=config['train_dir'], signature=config['signature_static'], use_filled=config['use_filled'], resolutions=dataset_resolutions, is_cape=config['is_cape'])
dataset_valid = factory.get_dataset(folder=config['valid_dir'], batch_size=config['batch_size'], signature=config['signature_dynamic'], use_filled=config['use_filled'], resolutions=dataset_resolutions, in_memory=config['dataset_in_memory'], is_cape=config['is_cape'])
static_dataset_valid = StaticDataset(folder=config['valid_dir'], signature=config['signature_static'], use_filled=config['use_filled'], resolutions=dataset_resolutions, is_cape=config['is_cape'])
model: Pyramid = Pyramid(config)
@@ -523,15 +649,16 @@ if __name__ == '__main__':
balancing_activated_step = 0
# sample('checkpoints/cvae_13')
# test()
ckpt = tf.train.Checkpoint(model=model)
manager = tf.train.CheckpointManager(ckpt, 'checkpoints/' + config['name'], max_to_keep=20)
load_model(model, config['pyramid']['pretrained_pyramid'])
# load_model(model, config['pyramid']['pretrained_pyramid'])
model.static_enc.trainable = False
model.body_enc.trainable = False
model.curv_enc.trainable = False
model.cond_encoder.trainable = False
# model.cond_encoder.trainable = False
# load_model(model.levels[0].upscale_enhancer, config['pyramid']['levels'][0]['upscale_enhancer'])