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
+24 -14
View File
@@ -222,20 +222,25 @@ def train_step(batch):
out_levels = model([levels_input, conds], training=True) out_levels = model([levels_input, conds], training=True)
if config['use_skinning']: if config['use_skinning']:
mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed'] mesh_orig = batch['mesh_unposed']
else: else:
mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed'] mesh_orig = batch['mesh_posed']
output = dict() output = dict()
reconstr_loss_total = 0 reconstr_loss_total = 0
kl_total = 0 kl_total = 0
#for i, res in enumerate(config['pyramid']['resolutions']): for i, res in enumerate(config['pyramid']['resolutions']):
i = -1 # i = -1
res = config['pyramid']['resolutions'][-1] res = config['pyramid']['resolutions'][i] if i != len(config['pyramid']['resolutions']) - 1 else 512
res_modifier = '_' + str(res) if res != 512 else '' res_modifier = '_' + str(res) if res != 512 else ''
pred, mean, logvar = out_levels[i] 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) mesh_pred = uv2mesh(pred)
if config['use_skinning']: if config['use_skinning']:
@@ -253,7 +258,7 @@ def train_step(batch):
e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask'])) 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 = 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) 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_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)) # 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)) 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))
@@ -296,20 +301,25 @@ def valid_step(batch):
if config['use_skinning']: if config['use_skinning']:
mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed'] mesh_orig = batch['mesh_unposed']
else: else:
mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed'] mesh_orig = batch['mesh_posed']
output = dict() output = dict()
reconstr_loss_total = 0 reconstr_loss_total = 0
kl_total = 0 kl_total = 0
#for i, res in enumerate(config['pyramid']['resolutions']): for i, res in enumerate(config['pyramid']['resolutions']):
i = -1 # i = -1
res = config['pyramid']['resolutions'][-1] res = config['pyramid']['resolutions'][i] if i != len(config['pyramid']['resolutions']) - 1 else 512
res_modifier = '_' + str(res) if res != 512 else '' res_modifier = '_' + str(res) if res != 512 else ''
pred, mean, logvar = out_levels[i] 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) mesh_pred = uv2mesh(pred)
if config['use_skinning']: if config['use_skinning']:
@@ -326,7 +336,7 @@ def valid_step(batch):
e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask'])) 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 = 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) 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_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)) # 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)) 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))
@@ -871,8 +881,8 @@ if __name__ == '__main__':
# load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer']) # load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
# model.upscale_enhancer.trainable = False # model.upscale_enhancer.trainable = False
for i in range(len(model.levels)-1): # for i in range(len(model.levels)-1):
model.levels[i].trainable = False # model.levels[i].trainable = False
# load_model(model.cond_encoder, config['pyramid']['pretrained_pyramid']) # load_model(model.cond_encoder, config['pyramid']['pretrained_pyramid'])
# load_model(model.levels[0], 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 pred = pred + levels_input[0][2] # uv_body_posed_32
if 1 != len(self.levels): 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 = 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]) 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] pred = pred * levels_input[1][-2][:,:,:,tf.newaxis]
else: else:
# pred = self.enhance(pred, levels_input[0][-2], training=training) # pred = self.enhance(pred, levels_input[0][-2], training=training)