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

pyramid available with 128 res

Browse Source
This commit is contained in:
luni
2022-09-15 10:14:35 +00:00
parent c3a2f558de
commit c6f6f8710d
6 changed files with 337 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cvae_pyramid.py
+50 -51
View File
@@ -1,5 +1,5 @@
import os
os.environ["CUDA_VISIBLE_DEVICES"] = "1"
os.environ["CUDA_VISIBLE_DEVICES"] = "2"
import tensorflow as tf
gpus = tf.config.experimental.list_physical_devices('GPU')
@@ -37,7 +37,7 @@ from custom_utils.smpl import SMPL
from models.cvae_pyramid_model import Pyramid
name='cvae_pyr_1'
name='cvae_pyr_1_d128'
def init_wandb():
run = wandb.init(project='vae', name=name,
notes='learn offsets. smaller flattened latent vectors. with 25-85k pretraining. smaller batchsize. fixed balancing of reconst and kl loss for baseline. \
@@ -48,7 +48,7 @@ use mean l2 loss. small batch. l2 * 1000, balancing to 1 from 0.01\
fixed gender issue and retrained body encoder\
remove shape from unposed garment\
training on 100 garments with offsets over the average of these\
l2 loss on both 32 and full res, bottom predicts base, high res predicts offsets over this')
l2 loss on both 128 and full res, bottom predicts base, high res predicts offsets over this')
artifact = wandb.Artifact('code', type='code')
artifact.add_file('cvae_pyramid.py')
artifact.add_file('models/cvae_model.py')
@@ -60,9 +60,9 @@ l2 loss on both 32 and full res, bottom predicts base, high res predicts offsets
uv2mesh = UV2Mesh(res=256)
def plot_3d(mesh_gt, mesh_pred_unposed, mesh_pred_unposed_32, faces, collision, collision_faces, collision_color):
def plot_3d(mesh_gt, mesh_pred_unposed, mesh_pred_unposed_low, faces, collision, collision_faces, collision_color):
mesh_pred_unposed[:,2] += 1
mesh_pred_unposed_32[:,2] += 2
mesh_pred_unposed_low[:,2] += 2
collision[:,2] += 3
fig = go.Figure(data=[
go.Mesh3d(
@@ -82,9 +82,9 @@ def plot_3d(mesh_gt, mesh_pred_unposed, mesh_pred_unposed_32, faces, collision,
k = faces[:,2],
),
go.Mesh3d(
x=mesh_pred_unposed_32[:,0],
y=mesh_pred_unposed_32[:,2],
z=mesh_pred_unposed_32[:,1],
x=mesh_pred_unposed_low[:,0],
y=mesh_pred_unposed_low[:,2],
z=mesh_pred_unposed_low[:,1],
i = faces[:,0],
j = faces[:,1],
k = faces[:,2],
@@ -132,22 +132,22 @@ def train_step(batch):
with tf.GradientTape() as tape:
uv_curvature = tf.one_hot(batch['uv_curvature'], 7)
uv_curvature_32 = tf.one_hot(batch['uv_curvature_32'], 7)
uv_curvature_low = tf.one_hot(batch['uv_curvature' + resolution_modifier], 7)
pred_full, mean_full, logvar_full, pred_32, mean_32, logvar_32, = model([batch['uv_unposed'], batch['uv_static'], batch['uv_body_posed'], uv_curvature,
batch['uv_unposed_32'], batch['uv_static_32'], batch['uv_body_posed_32'], uv_curvature_32])
pred_full, mean_full, logvar_full, pred_low, mean_low, logvar_low, = model([batch['uv_unposed'], batch['uv_static'], batch['uv_body_posed'], uv_curvature,
batch['uv_unposed' + resolution_modifier], batch['uv_static' + resolution_modifier], batch['uv_body_posed' + resolution_modifier], uv_curvature_low])
mesh_pred_full = uv2mesh(pred_full)
mesh_pred_posed_full = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_full)
mesh_pred_32 = uv2mesh(pred_32)
mesh_pred_posed_32 = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_32)
mesh_pred_low = uv2mesh(pred_low)
mesh_pred_posed_low = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_low)
mesh_orig = batch['mesh_unposed']
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_posed_full = mesh_pred_posed_full + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
mesh_pred_posed_32 = mesh_pred_posed_32 + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
mesh_pred_posed_low = mesh_pred_posed_low + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
e_loss = tf.reduce_mean(edge_loss(mesh_pred_full, mesh_orig, batch['mesh_mask']))
c_loss = tf.reduce_mean(collision_penalty(mesh_pred_posed_full, batch['mesh_body_posed'], batch['mesh_mask']))
@@ -156,16 +156,16 @@ def train_step(batch):
ms_ssim = tf.image.ssim_multiscale(pred_full + 1, tf.transpose(batch['uv_unposed'], [0,2,3,1]) + 1, max_val=3)
kl = kl_loss(mean_full, logvar_full)
e_loss_32 = tf.reduce_mean(edge_loss(mesh_pred_32, mesh_orig, batch['mesh_mask']))
c_loss_32 = tf.reduce_mean(collision_penalty(mesh_pred_posed_32, batch['mesh_body_posed'], batch['mesh_mask']))
l1_loss_32 = tf.reduce_sum(tf.reduce_sum((tf.math.abs(tf.transpose(batch['uv_unposed_32'], [0,2,3,1]) - pred_32)), axis=-1), axis=[1, 2])
l2_loss_32 = 1e3 * tf.reduce_mean(tf.reduce_sum(((tf.transpose(batch['uv_unposed_32'], [0,2,3,1]) - pred_32) ** 2), axis=-1), axis=[1, 2])
ms_ssim_32 = tf.image.ssim(pred_32 + 1, tf.transpose(batch['uv_unposed_32'], [0,2,3,1]) + 1, max_val=3)
kl_32 = kl_loss(mean_full, logvar_full)
e_loss_low = tf.reduce_mean(edge_loss(mesh_pred_low, mesh_orig, batch['mesh_mask']))
c_loss_low = tf.reduce_mean(collision_penalty(mesh_pred_posed_low, batch['mesh_body_posed'], batch['mesh_mask']))
l1_loss_low = tf.reduce_sum(tf.reduce_sum((tf.math.abs(tf.transpose(batch['uv_unposed' + resolution_modifier], [0,2,3,1]) - pred_low)), axis=-1), axis=[1, 2])
l2_loss_low = 1e3 * tf.reduce_mean(tf.reduce_sum(((tf.transpose(batch['uv_unposed' + resolution_modifier], [0,2,3,1]) - pred_low) ** 2), axis=-1), axis=[1, 2])
ms_ssim_low = tf.image.ssim(pred_low + 1, tf.transpose(batch['uv_unposed' + resolution_modifier], [0,2,3,1]) + 1, max_val=3)
kl_low = kl_loss(mean_full, logvar_full)
reconstr_loss = l2_loss + l2_loss_32
reconstr_loss = l2_loss + l2_loss_low
reconstr_loss = tf.reduce_mean(reconstr_loss)
loss = reconstr_loss + balancing_coeff * (kl + kl_32)
loss = reconstr_loss + balancing_coeff * (kl + kl_low)
ms_ssim = tf.reduce_mean(ms_ssim)
l1_loss = tf.reduce_mean(l1_loss)
@@ -173,25 +173,24 @@ def train_step(batch):
mean = tf.reduce_mean(mean_full)
logvar = tf.reduce_mean(logvar_full)
ms_ssim_32 = tf.reduce_mean(ms_ssim_32)
l1_loss_32 = tf.reduce_mean(l1_loss_32)
l2_loss_32 = tf.reduce_mean(l2_loss_32)
mean_32 = tf.reduce_mean(mean_32)
logvar_32 = tf.reduce_mean(logvar_32)
ms_ssim_low = tf.reduce_mean(ms_ssim_low)
l1_loss_low = tf.reduce_mean(l1_loss_low)
l2_loss_low = tf.reduce_mean(l2_loss_low)
mean_low = tf.reduce_mean(mean_low)
logvar_low = tf.reduce_mean(logvar_low)
mesh_orig_2 = uv2mesh(batch['uv_unposed'])
metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred_full) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
metric_32 = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred_32) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
metric_low = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred_low) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
metric_2 = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig_2 - mesh_pred_full) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
gradients = tape.gradient(loss, model.trainable_variables)
optimizer.apply_gradients(zip(gradients, model.trainable_variables))
return { 'train/loss': loss, 'train/edge_loss': e_loss, 'train/collision_loss': c_loss, 'train/l1_loss': l1_loss, 'train/euclid_error': metric, 'train/ms_ssim': ms_ssim,
'train/euclid_error_reconst': metric_2, 'train/reconstr_loss': reconstr_loss, 'train/mean': mean, 'train/logvar': logvar, 'train/kl_loss': kl,
'train/var': np.e ** logvar, 'train/reg_coeff': reg_coeff, 'train/l2_loss': l2_loss,
'train/edge_loss_32': e_loss_32, 'train/collision_loss_32': c_loss_32, 'train/l1_loss_32': l1_loss_32, 'train/euclid_error_32': metric_32, 'train/ms_ssim_32': ms_ssim_32,
'train/mean_32': mean_32, 'train/logvar_32': logvar_32, 'train/kl_loss_32': kl_32,
'train/var_32': np.e ** logvar_32, 'train/l2_loss_32': l2_loss_32 }
'train/edge_loss' + resolution_modifier: e_loss_low, 'train/collision_loss' + resolution_modifier: c_loss_low, 'train/l1_loss' + resolution_modifier: l1_loss_low, 'train/euclid_error' + resolution_modifier: metric_low, 'train/ms_ssim' + resolution_modifier: ms_ssim_low,
'train/mean' + resolution_modifier: mean_low, 'train/logvar' + resolution_modifier: logvar_low, 'train/kl_loss' + resolution_modifier: kl_low,
'train/var' + resolution_modifier: np.e ** logvar_low, 'train/l2_loss' + resolution_modifier: l2_loss_low }
@tf.function
@@ -235,26 +234,26 @@ def valid_step(batch):
def plot_everything(batch: dict, type: str):
uv_curvature = tf.one_hot(batch['uv_curvature'], 7)
uv_curvature_32 = tf.one_hot(batch['uv_curvature_32'], 7)
pred_full, mean_full, logvar_full, pred_32, mean_32, logvar_32, = model([batch['uv_unposed'], batch['uv_static'], batch['uv_body_posed'], uv_curvature,
batch['uv_unposed_32'], batch['uv_static_32'], batch['uv_body_posed_32'], uv_curvature_32])
uv_curvature_low = tf.one_hot(batch['uv_curvature' + resolution_modifier], 7)
pred_full, mean_full, logvar_full, pred_low, mean_low, logvar_low, = model([batch['uv_unposed'], batch['uv_static'], batch['uv_body_posed'], uv_curvature,
batch['uv_unposed' + resolution_modifier], batch['uv_static' + resolution_modifier], batch['uv_body_posed' + resolution_modifier], uv_curvature_low])
mesh_pred_full = uv2mesh(pred_full)
mesh_pred_32 = uv2mesh(pred_32)
mesh_pred_low = uv2mesh(pred_low)
mesh_orig = batch['mesh_unposed']
orig_img = tf.transpose(batch['uv_unposed'], [0,2,3,1])
uv_static_img = tf.transpose(batch['uv_static'], [0,2,3,1])
uv_body_posed_img = tf.transpose(batch['uv_body_posed'], [0,2,3,1])
pred_img = pred_full
pred_32_up = tf.image.resize(pred_32, (512, 256), tf.image.ResizeMethod.LANCZOS5)
img = tf.concat((uv_static_img, uv_body_posed_img, orig_img, pred_img, pred_32_up), axis=2)
pred_low_up = tf.image.resize(pred_low, (512, 256), tf.image.ResizeMethod.LANCZOS5)
img = tf.concat((uv_static_img, uv_body_posed_img, orig_img, pred_img, pred_low_up), axis=2)
imgs = [wandb.Image((img[i] + 1) / 2.0) for i in range(4)]
F = np.load("custom_utils/smpl_faces.npy")
mask = batch['mesh_mask'].numpy().astype(bool)
garment_unposed, faces = maskFacesBatch(mesh_pred_full.numpy(), F, mask)
garment_unposed_32, faces = maskFacesBatch(mesh_pred_32.numpy(), F, mask)
garment_unposed_low, faces = maskFacesBatch(mesh_pred_low.numpy(), F, mask)
gt = [mesh_orig[i].numpy()[mask[i], :] for i in range(pred_full.shape[0])]
body = batch['mesh_body_posed'].numpy()
@@ -269,7 +268,7 @@ def plot_everything(batch: dict, type: str):
collision_faces = [np.concatenate((F, faces[i] + 14475), axis=0) for i in range(len(garment_posed))]
collision_color = [np.concatenate((np.ones_like(body[i], dtype=np.int32)*100, np.ones_like(garment_posed[i], dtype=np.int32)*230), axis=0) for i in range(len(garment_posed))]
figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], garment_unposed_32[i], faces[i], collision[i], collision_faces[i], collision_color[i]) for i in range(4) }
figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], garment_unposed_low[i], faces[i], collision[i], collision_faces[i], collision_color[i]) for i in range(4) }
mean_hist = wandb.Histogram(sequence=mean_full.numpy().mean(axis=0))
logvar_hist = wandb.Histogram(sequence=logvar_full.numpy().mean(axis=0))
@@ -277,8 +276,6 @@ def plot_everything(batch: dict, type: str):
return { **figs, **{ type + '/images': imgs, type + '/mean_hist': mean_hist, type + '/logvar_hist': logvar_hist } }
def sample(folder):
# run = wandb.init(project='vae_plots', name=folder.split('/')[-1])
load_model(model,folder)
@@ -400,6 +397,7 @@ def sample(folder):
print()
if __name__ == '__main__':
init_wandb()
allow_memory_growth()
@@ -408,6 +406,8 @@ if __name__ == '__main__':
args = vars(parser.parse_args())
batch_size = 4
low_resolution = 128
resolution_modifier = '_' + str(low_resolution)
smpl = SMPL()
@@ -416,31 +416,30 @@ if __name__ == '__main__':
'pose_shape': (72 + 11,),
# 'uv_posed': (3, 512, 256,),
'uv_body_posed': (3, 512, 256,),
'uv_body_posed_32': (3, 32, 16,),
'uv_body_posed' + resolution_modifier: (3, low_resolution, low_resolution//2,),
'mesh_body_posed': (14475, 3,),
'mesh_posed': (14475, 3,),
'mesh_unposed': (14475, 3,),
'uv_unposed': (3, 512, 256,),
'uv_unposed_32': (3, 32, 16,),
'uv_unposed' + resolution_modifier: (3, low_resolution, low_resolution//2,),
'uv_curvature': (512, 256),
'uv_curvature_32': (32, 16),
'uv_curvature' + resolution_modifier: (low_resolution, low_resolution//2),
}
signature_static = { 'uv_static': (3, 512, 256,),
'uv_static_32': (3, 32, 16,),
'uv_static' + resolution_modifier: (3, low_resolution, low_resolution//2,),
# 'mesh_static': (14475, 3,),
'mesh_mask': (14475,),
'uv_mask': (512, 256,),
'uv_shaped_body': (3, 512, 256,),
# 'uv_shaped_body': (3, 512, 256,),
}
dataset_train = factory.get_dataset(folder='/home/workspace/local-data/train_100', batch_size=batch_size, signature=signature_dynamic, use_filled=True, resolutions=[512, 32])
static_dataset_train = StaticDataset(folder='/home/workspace/local-data/train_100', signature=signature_static, use_filled=True, resolutions=[512, 32])
dataset_train = factory.get_dataset(folder='/home/workspace/local-data/train_100', batch_size=batch_size, signature=signature_dynamic, use_filled=True, resolutions=[512, low_resolution])
static_dataset_train = StaticDataset(folder='/home/workspace/local-data/train_100', signature=signature_static, use_filled=True, resolutions=[512, low_resolution])
dataset_valid = factory.get_dataset(folder='/home/workspace/local-data/jumpsuit_20/valid', batch_size=batch_size, signature=signature_dynamic)
static_dataset_valid = StaticDataset(folder='/home/workspace/local-data/jumpsuit_20/valid', signature=signature_static)
model = Pyramid(latent_dim=128)
model = Pyramid(latent_dim=128, low_res=low_resolution)
# lr_schedule = tf.keras.optimizers.schedules.ExponentialDecay(0.0001, decay_steps=30000, decay_rate=0.1, staircase=False)
optimizer = tf.optimizers.Adam(learning_rate=0.0001)