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

backup

Browse Source
This commit is contained in:
luni
2022-10-04 21:50:58 +00:00
parent 5b82041acb
commit 3c798b473d
8 changed files with 270 additions and 125 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cvae_pyramid.py
+75 -39
View File
@@ -27,8 +27,13 @@ import plotly.express as ex
from plotly.subplots import make_subplots
from PIL import Image
if config['is_skirt']:
from losses import edge_loss_skirt as edge_loss
else:
from losses import edge_loss
from tf_utils import check_tf_version, allow_memory_growth, split_gpu_for_testing
from losses import edge_loss, uv_mask_loss, bend_loss, kl_loss
from losses import uv_mask_loss, bend_loss, kl_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
@@ -48,14 +53,14 @@ def init_wandb():
artifact.add_file('models/upscaler.py')
artifact.add_file('losses.py')
artifact.add_file('configs/config_base.py')
artifact.add_file('configs/config_cvae.py')
artifact.add_file('configs/config_pyramid.py')
artifact.add_file('models/base.py')
artifact.add_file('models/cond_encoder.py')
artifact.add_file('dataset.py')
artifact.add_file('convnext/models/convnext_tf.py')
run.log_artifact(artifact)
uv2mesh = UV2Mesh(res=256)
uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'])
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)] ])
@@ -148,15 +153,16 @@ def group_inputs_for_levels(batch):
for res in config['pyramid']['resolutions']:
res_modifier = '_' + str(res) if res != 512 else ''
levels_input.append([batch['uv_unposed' + res_modifier], batch['uv_static' + res_modifier], batch['uv_body_posed' + res_modifier], batch['uv_curvature' + res_modifier], batch['uv_mask' + res_modifier], batch['uv_mask']])
return levels_input
conds = [batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature']]
return levels_input, conds
@tf.function
def train_step(batch):
with tf.GradientTape() as tape:
levels_input = group_inputs_for_levels(batch)
out_levels = model(levels_input, training=True)
levels_input, conds = group_inputs_for_levels(batch)
out_levels = model([levels_input, conds], training=True)
shape = batch['pose_shape'][:, 72:]
gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
@@ -166,32 +172,37 @@ def train_step(batch):
output = dict()
reconstr_loss_total = 0
kl_total = 0
for i, res in enumerate(config['pyramid']['resolutions']):
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)
#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]
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']))
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 + 1, batch['uv_unposed'] + 1, max_val=3, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
kl = kl_loss(mean, logvar)
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)
reconstr_loss_total += l2_loss #+ e_loss + c_loss
kl_total += kl
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']))
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 - tf.reduce_min(pred), batch['uv_unposed'] - tf.reduce_min(pred), max_val=tf.reduce_max(pred) - tf.reduce_min(pred), 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)
mean = tf.reduce_mean(mean)
logvar = tf.reduce_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
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'])
mean = tf.reduce_mean(mean)
logvar = tf.reduce_mean(logvar)
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 } }
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'])
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 } }
loss = reconstr_loss_total + balancing_coeff * kl_total
@@ -248,19 +259,20 @@ def plot_everything(batch: dict, type: str):
mesh_orig_posed = batch['mesh_posed'].numpy()
body = batch['mesh_body_posed'].numpy()
orig_img = batch['uv_unposed']
uv_static_img = batch['uv_static']
uv_body_posed_img = batch['uv_body_posed']
uv_curvature = np.tile(batch['uv_curvature'].numpy().argmax(-1)[:,:,:,np.newaxis], [1,1,1,3]) / 2 - 1
pred_img = np.concatenate([output_levels[i][0] for i in range(len(output_levels))], axis=2)
orig_img = (batch['uv_unposed'].numpy() + 1) / 2
uv_static_img = (batch['uv_static'].numpy() + 1) / 2
uv_body_posed_img = (batch['uv_body_posed'].numpy() + 1) / 2
uv_curvature = (np.tile(batch['uv_curvature'].numpy().argmax(-1)[:,:,:,np.newaxis], [1,1,1,3]) / 6)
pred_img = np.concatenate([tf.image.resize(output_levels[i][0], (512, 256), tf.image.ResizeMethod.LANCZOS5) for i in range(len(output_levels))], axis=2)
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])
img = tf.concat((uv_static_img, uv_body_posed_img, uv_curvature, orig_img, pred_img), axis=2)
imgs = [wandb.Image((img[i] + 1) / 2.0) for i in range(4)]
imgs = [wandb.Image(img[i]) for i in range(4)]
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])]).numpy()
F = np.load("custom_utils/smpl_faces.npy")
F = np.load("custom_utils/smpl_faces" + skirt_modifier + ".npy")
mask = batch['mesh_mask'].numpy().astype(bool)
_, faces = maskFacesBatch(np.ones_like(mesh_orig), F, mask)
@@ -419,11 +431,15 @@ if __name__ == '__main__':
args = vars(parser.parse_args())
smpl = SMPL()
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=config['pyramid']['resolutions'])
static_dataset_train = StaticDataset(folder=config['train_dir'], signature=config['signature_static'], use_filled=config['use_filled'], resolutions=config['pyramid']['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=config['pyramid']['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'])
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'])
model: Pyramid = Pyramid(config)
@@ -440,9 +456,29 @@ if __name__ == '__main__':
ckpt = tf.train.Checkpoint(model=model)
manager = tf.train.CheckpointManager(ckpt, 'checkpoints/' + config['name'], max_to_keep=3)
load_model(model.cond_encoder, 'checkpoints/cvae_19')
load_model(model.levels[0], 'checkpoints/cvae_low_4_3_d32')
load_model(model.levels[-1], 'checkpoints/cvae_19')
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
# the last level doesn't have an upscale enhancer as it's enhanced for the final resolutin directly
# might now be necessary, as enhancing to final or a bit higher resolution seems to be the same
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
load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
model.upscale_enhancer.trainable = False
load_model(model.levels[-1], 'checkpoints/cvae_low_2_d128_cont')
for i in range(len(model.levels)-1):
model.levels[i].trainable = False
# load_model(model.cond_encoder, 'checkpoints/cvae_low_4_3_d32')
# load_model(model.levels[0], 'checkpoints/cvae_low_4_3_d32')
# load_model(model.levels[-1], 'checkpoints/cvae_19')
step = 0
for batch in dataset_train: