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

activate all levels

Browse Source
This commit is contained in:
luni
2023-03-15 22:20:33 +01:00
parent e108460c48
commit 1373b363b5
2 changed files with 99 additions and 89 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cvae_pyramid.py
+96 -86
View File
@@ -222,20 +222,104 @@ def train_step(batch):
out_levels = model([levels_input, conds], training=True)
if config['use_skinning']:
mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
mesh_orig = batch['mesh_unposed']
else:
mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
mesh_orig = batch['mesh_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]
for i, res in enumerate(config['pyramid']['resolutions']):
# i = -1
res = config['pyramid']['resolutions'][i] if i != len(config['pyramid']['resolutions']) - 1 else 512
res_modifier = '_' + str(res) if res != 512 else ''
pred, mean, logvar = out_levels[i]
if config['use_skinning']:
uv_orig = batch['uv_unposed' + res_modifier]
else:
uv_orig = batch['uv_posed' + res_modifier]
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
# is the output already masked?
e_loss = tf.reduce_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 = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio)
l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1) * batch['uv_mask' + res_modifier], 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] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, axis=-1), axis=-1))
n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'])
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
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'])
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,
loss = reconstr_loss_total + balancing_coeff * kl_total
gradients = tape.gradient(loss, model.trainable_variables)
optimizer.apply_gradients(zip(gradients, model.trainable_variables))
return { **{ 'train/loss': loss, 'train/reconstr_loss_total': reconstr_loss_total, 'train/kl_total': kl_total }, **output }
@tf.function
def valid_step(batch):
levels_input, conds = group_inputs_for_levels(batch, config)
out_levels = model([levels_input, conds], training=False)
if config['use_skinning']:
mesh_orig = batch['mesh_unposed']
else:
mesh_orig = batch['mesh_posed']
output = dict()
reconstr_loss_total = 0
kl_total = 0
for i, res in enumerate(config['pyramid']['resolutions']):
# i = -1
res = config['pyramid']['resolutions'][i] if i != len(config['pyramid']['resolutions']) - 1 else 512
res_modifier = '_' + str(res) if res != 512 else ''
pred, mean, logvar = out_levels[i]
if config['use_skinning']:
uv_orig = batch['uv_unposed' + res_modifier]
else:
uv_orig = batch['uv_posed' + res_modifier]
mesh_pred = uv2mesh(pred)
if config['use_skinning']:
@@ -247,13 +331,12 @@ def train_step(batch):
mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
else:
mesh_pred_posed = mesh_pred
# is the output already masked?
e_loss = tf.reduce_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 = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio)
l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1) * batch['uv_mask' + res_modifier], 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] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, axis=-1), axis=-1))
@@ -277,83 +360,10 @@ def train_step(batch):
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/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,
loss = reconstr_loss_total + balancing_coeff * kl_total
gradients = tape.gradient(loss, model.trainable_variables)
optimizer.apply_gradients(zip(gradients, model.trainable_variables))
return { **{ 'train/loss': loss, 'train/reconstr_loss_total': reconstr_loss_total, 'train/kl_total': kl_total }, **output }
@tf.function
def valid_step(batch):
levels_input, conds = group_inputs_for_levels(batch, config)
out_levels = model([levels_input, conds], training=False)
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 = 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
# is the output already masked?
e_loss = tf.reduce_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 = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio)
l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - 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] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, axis=-1), axis=-1))
n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'])
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
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'])
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,
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,
loss = reconstr_loss_total + balancing_coeff * kl_total
@@ -871,8 +881,8 @@ if __name__ == '__main__':
# load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
# model.upscale_enhancer.trainable = False
for i in range(len(model.levels)-1):
model.levels[i].trainable = False
# for i in range(len(model.levels)-1):
# model.levels[i].trainable = False
# load_model(model.cond_encoder, config['pyramid']['pretrained_pyramid'])
# load_model(model.levels[0], config['pyramid']['pretrained_pyramid'])
models/pyramid_model_optimized.py
+1 -1
View File
@@ -416,8 +416,8 @@ class PyramidNew(tf.keras.Model):
pred = pred + levels_input[0][2] # uv_body_posed_32
if 1 != len(self.levels):
pred = self.levels[0].enhance(pred, levels_input[0][-2], training=training) # levels_input[i][-2]=uv_mask_res
pred = tf.image.resize(pred, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.BILINEAR)
out_levels.append([pred, mean, logvar])
pred = tf.image.resize(pred, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.BILINEAR)
pred = pred * levels_input[1][-2][:,:,:,tf.newaxis]
else:
# pred = self.enhance(pred, levels_input[0][-2], training=training)