update cvae_low version

configs/config_cvae.py

@@ -1,7 +1,7 @@
 from configs.config_base import config
 
-config['gpu'] = '3'
+config['gpu'] = '0'
-config['name'] = 'cvae_19'
+config['name'] = 'cvae_19_2'
 config['notes'] = '\
 offsets over average unposed garment. remove global orientation (in posed body input and in pose_shape parameters. \
 retrained body encoder with deoriented bodies \
@@ -11,8 +11,16 @@ remove shape from unposed garment\
 training on 100 garments with offsets over the average of these\
 fixed autoencoders!!!!!!!!!\
 cvae only loads encoders instead AEs\
+with edge and collision loss\
 '
 
+# config['resolution'] = 32
+
+
+if config['resolution'] != 512:
+  config['notes'] += '\
+using custom enhancer for upscaling, using not filled versions\
+'
     
 config['lr'] = 0.0001
 config['starting_balancing_coeff'] = 0.0001
@@ -31,7 +39,19 @@ config['signature_static'] = { 'uv_static': (512, 256, 3),
                               'uv_mask': (512, 256,),
                               }
 
+if config['resolution'] != 512:
+  res_modifier = '_' + str(config['resolution'])
+  config['signature_dynamic']['uv_body_posed' + res_modifier] = (config['resolution'], config['resolution']//2, 3)
+  config['signature_dynamic']['uv_unposed' + res_modifier] = (config['resolution'], config['resolution']//2, 3)
+  config['signature_dynamic']['uv_curvature' + res_modifier] = (config['resolution'], config['resolution']//2)
+  config['signature_static']['uv_static' + res_modifier] = (config['resolution'], config['resolution']//2, 3)
+  config['signature_static']['uv_mask' + res_modifier] = (config['resolution'], config['resolution']//2)
+
+if config['resolution'] == 512:
   config['avg_garment_path'] = 'custom_data/train_100_no_shape_avg_uv.npy'
+else:
+  config['avg_garment_path'] = ''
+
 config['static_model'] = 'checkpoints/ae_static_7_2_x'
 config['body_model'] = 'checkpoints/ae_body_9_x'
 config['curvature_model'] = 'checkpoints/ae_curv_9_x'

cvae.py

@@ -87,21 +87,23 @@ def train_step(batch):
         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)
 
-        e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
+        e_loss = 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_loss = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
         l1_loss = tf.reduce_sum(tf.reduce_sum((tf.math.abs(batch['uv_unposed'] - pred)), axis=-1) * batch['uv_mask'], axis=[1, 2])
         l2_loss = 1e3 * tf.reduce_mean(tf.reduce_sum(((batch['uv_unposed'] - pred) ** 2), axis=-1) * batch['uv_mask'], axis=[1, 2])
         # ms_ssim = tf.image.ssim_multiscale(tf.transpose(pred, [0,2,3,1]) + 1, tf.transpose(batch['uv_unposed'], [0,2,3,1]) + 1, max_val=2)
         ms_ssim = 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))
         # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale((tf.transpose(pred, [0,2,3,1]) + 1) * batch['uv_mask'][:,:,:,tf.newaxis], (tf.transpose(batch['uv_unposed'], [0,2,3,1]) + 1) * batch['uv_mask'][:,:,:,tf.newaxis], max_val=2))
 
-        reconstr_loss = l2_loss
+        reconstr_loss = l2_loss + e_loss + c_loss
         reconstr_loss = tf.reduce_mean(reconstr_loss)
         kl = kl_loss(mean, logvar)
         loss = reconstr_loss + balancing_coeff * kl
         ms_ssim = tf.reduce_mean(ms_ssim)
         l1_loss = tf.reduce_mean(l1_loss)
         l2_loss = tf.reduce_mean(l2_loss)
+        e_loss = tf.reduce_mean(e_loss)
+        c_loss = tf.reduce_mean(c_loss)
         mean = tf.reduce_mean(mean)
         logvar = tf.reduce_mean(logvar)
 

cvae_low.py

@@ -1,5 +1,6 @@
 import os
-os.environ["CUDA_VISIBLE_DEVICES"] = "1"
+from configs.config_cvae import config
+os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
 
 gpus = tf.config.experimental.list_physical_devices('GPU')
@@ -29,86 +30,29 @@ from tf_utils import check_tf_version, allow_memory_growth, split_gpu_for_testin
 from losses import d_logistic, d_logistic_r1_reg, g_logistic_non_saturating, g_logistic_ns_pathreg, edge_loss, uv_mask_loss, bend_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
+from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d
 from dataset import DatasetFactory, StaticDataset
 from custom_utils.smpl import SMPL
-from models.cvae_model import CVAE#, CVAE128, CVAE32
+from models.cvae_model import CVAE
 from models.upscaler import UpscalerBasic as Upscaler
 
 
-name='cvae_low_4_2_d32'
 def init_wandb():
-    run = wandb.init(project='vae', name=name,
+    run = wandb.init(project='vae', name=config['name'], notes=config['notes'])
-            notes='learn offsets. smaller flattened latent vectors. with 25-85k pretraining. smaller batchsize. fixed balancing of reconst and kl loss for baseline. \
-new implementation for kl loss. no lr schedule. 25 jumpsuits, average reconst_loss before calculation, linearly increasing balancing, up to 1 from 0.1. \
-offsets over average unposed garment. remove global orientation (in posed body input and in pose_shape parameters. \
-retrained body encoder with deoriented bodies \
-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 , absolute, not offsets\
-using custom enhancer for upscaling, using not filled versions\
-calculating loss at full res')
     artifact = wandb.Artifact('code', type='code')
-    artifact.add_file('cvae.py')
+    artifact.add_file('cvae_low.py')
     artifact.add_file('models/cvae_model.py')
-    artifact.add_file('dataset.py')
     artifact.add_file('losses.py')
+    artifact.add_file('configs/config_base.py')
+    artifact.add_file('configs/config_cvae.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)
 
-def plot_3d(mesh_gt, mesh_pred_unposed, faces, collision, collision_faces, collision_color):
-    mesh_pred_unposed[:,2] += 1
-    collision[:,2] += 2
-    fig = go.Figure(data=[
-        go.Mesh3d(
-            # 8 vertices of a cube
-            x=mesh_gt[:,0],
-            y=mesh_gt[:,2],
-            z=mesh_gt[:,1],
-            # i, j and k give the vertices of triangles
-            i = faces[:,0],
-            j = faces[:,1],
-            k = faces[:,2]
-        ),
-        go.Mesh3d(
-            # 8 vertices of a cube
-            x=mesh_pred_unposed[:,0],
-            y=mesh_pred_unposed[:,2],
-            z=mesh_pred_unposed[:,1],
-            # i, j and k give the vertices of triangles
-            i = faces[:,0],
-            j = faces[:,1],
-            k = faces[:,2],
-        ),
-        go.Mesh3d(
-            # 8 vertices of a cube
-            x=collision[:,0],
-            y=collision[:,2],
-            z=collision[:,1],
-            # i, j and k give the vertices of triangles
-            i = collision_faces[:,0],
-            j = collision_faces[:,1],
-            k = collision_faces[:,2],
-            vertexcolor=collision_color
-        )
-    ])
-
-    fig.update_layout(scene_aspectmode='manual',
-                    scene_aspectratio=dict(x=1, y=2, z=1))
-    fig.update_layout(
-        scene = dict(
-            xaxis = dict(nticks=4, range=[-1,1],),
-                        yaxis = dict(nticks=4, range=[-1,3],),
-                        zaxis = dict(nticks=4, range=[-1,1],),)
-                        )
-
-    return fig
-
-
-
 
 def log_normal_pdf(sample, mean, logvar, raxis=1):
     log2pi = tf.math.log(2. * np.pi)
@@ -131,11 +75,10 @@ def train_step(batch):
         uv_curvature_low = tf.one_hot(batch['uv_curvature' + res_modifier], 7)
         pred, mean, logvar, z = model([batch['uv_unposed' + res_modifier], batch['uv_static' + res_modifier], batch['uv_body_posed' + res_modifier], uv_curvature_low,
                                        batch['uv_mask' + res_modifier], batch['uv_static'], batch['uv_body_posed'], uv_curvature, batch['uv_mask']], use_mask=True)
-        # pred = pred * batch['uv_mask' + res_modifier][:,:,:,tf.newaxis]
 
         pred_enhanced = enhance(upscale_enhancer, pred, batch['uv_mask' + res_modifier], training=False)
         pred_full_res = tf.image.resize(pred_enhanced, size=(512, 256), method=tf.image.ResizeMethod.LANCZOS5)
-        mesh_pred = uv2mesh(pred_enhanced)
+        mesh_pred = uv2mesh(pred_full_res)
         mesh_orig = batch['mesh_unposed']
 
         shape = batch['pose_shape'][:, 72:]
@@ -153,7 +96,7 @@ def train_step(batch):
             ms_ssim = tf.image.ssim(pred + 1, batch['uv_unposed' + res_modifier] + 1, max_val=3) 
             ms_ssim_full = tf.image.ssim(pred_full_res + 1, batch['uv_unposed'] + 1, max_val=3) 
         else:
-            ms_ssim = tf.image.ssim_multiscale(pred + 1, batch['uv_unposed' + res_modifier] + 1, max_val=3, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)) 
+            ms_ssim = tf.image.ssim_multiscale(pred + 1, batch['uv_unposed' + res_modifier] + 1, max_val=3, power_factors=(0.5, 0.3, 0.1, 0.1)) 
 
         reconstr_loss = l2_loss_full
         reconstr_loss = tf.reduce_mean(reconstr_loss)
@@ -167,18 +110,12 @@ def train_step(batch):
         mean = tf.reduce_mean(mean)
         logvar = tf.reduce_mean(logvar)
 
-    # mesh_orig_2 = uv2mesh(batch['uv_unposed' + res_modifier])
     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'])
-    # metric_2 = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig_2 - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
-    euclid_posed = 0 # tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_skinned - batch['mesh_posed']) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
     gradients = tape.gradient(loss, model.trainable_variables)
-    # gradients = [tf.clip_by_norm(g, 1.0) for g in gradients]
-    # gradients = [tf.clip_by_value(g, -1.0, 1.0) for g in gradients]
     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/l2_loss_full_res': l2_loss_full, 'train/ms_ssim_full_res': ms_ssim_full,
-             'train/euclid_error_posed': euclid_posed, 'train/reconstr_loss': reconstr_loss,
+             '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 }
         
@@ -226,8 +163,8 @@ def valid_step(batch):
 def plot_everything(batch: dict, type: str):
     uv_curvature = tf.one_hot(batch['uv_curvature'], 7)
     uv_curvature_low = tf.one_hot(batch['uv_curvature' + res_modifier], 7)
-    pred, mean, logvar, z = model([batch['uv_unposed' + res_modifier], batch['uv_static' + res_modifier], batch['uv_body_posed' + res_modifier], uv_curvature_low, batch['uv_static'], batch['uv_body_posed'], uv_curvature])
+    pred, mean, logvar, z = model([batch['uv_unposed' + res_modifier], batch['uv_static' + res_modifier], batch['uv_body_posed' + res_modifier], uv_curvature_low,
-    # pred = pred * batch['uv_mask' + res_modifier][:,:,:,tf.newaxis]
+                                    batch['uv_mask' + res_modifier], batch['uv_static'], batch['uv_body_posed'], uv_curvature, batch['uv_mask']], use_mask=True)
     
     pred = enhance(upscale_enhancer, pred, batch['uv_mask' + res_modifier], training=False)
     mesh_pred = uv2mesh(pred).numpy()
@@ -433,64 +370,31 @@ if __name__ == '__main__':
         res_modifier = '_' + str(resolution)
 
     factory = DatasetFactory()
-    signature_dynamic = { 'id': (),
-                          'pose_shape': (72 + 11,),
-                        #   'uv_posed': (512, 256, 3),
-                          'uv_body_posed': (512, 256, 3),
-                          'uv_body_posed' + res_modifier: (resolution, resolution//2, 3),
-                          'mesh_body_posed': (14475, 3,),
-                          'mesh_posed': (14475, 3,),
-                          'mesh_unposed': (14475, 3,),
-                          'uv_unposed': (512, 256, 3),
-                          'uv_unposed' + res_modifier: (resolution, resolution//2, 3),
-                          'uv_curvature': (512, 256,),
-                          'uv_curvature' + res_modifier: (resolution, resolution//2),
-                        }
-    signature_static = { 'uv_static': (512, 256, 3),
-                         'uv_static' + res_modifier: (resolution, resolution//2, 3),
-                        #  'mesh_static': (14475, 3,),
-                         'mesh_mask': (14475,),
-                         'uv_mask' + res_modifier: (resolution, resolution//2,),
-                         'uv_mask': (512, 256,),
-                        }
 
-    dataset_train = factory.get_dataset(folder='/home/workspace/local-data/train_100', batch_size=batch_size, signature=signature_dynamic, use_filled=False, resolutions=[512, resolution])
+    dataset_train = factory.get_dataset(folder=config['train_dir'], batch_size=config['batch_size'], signature=config['signature_dynamic'], use_filled=config['use_filled'], resolutions=[512, config['resolution']])
-    static_dataset_train = StaticDataset(folder='/home/workspace/local-data/train_100', signature=signature_static, use_filled=False, resolutions=[512, resolution])
+    static_dataset_train = StaticDataset(folder=config['train_dir'], signature=config['signature_static'], use_filled=config['use_filled'], resolutions=[512, config['resolution']])
-    dataset_valid = factory.get_dataset(folder='/home/workspace/local-data/jumpsuit_20/valid', batch_size=batch_size, signature=signature_dynamic)
+    dataset_valid = factory.get_dataset(folder=config['valid_dir'], batch_size=config['batch_size'], signature=config['signature_dynamic'])
-    static_dataset_valid = StaticDataset(folder='/home/workspace/local-data/jumpsuit_20/valid', signature=signature_static)
+    static_dataset_valid = StaticDataset(folder=config['valid_dir'], signature=config['signature_static'])
 
-
+    model = CVAE(config)
-    model = CVAE(#avg_garment_path='custom_data/train_100_no_shape_avg_uv.npy',
-                 size=resolution,
-                 latent_dim=128, static_model='checkpoints/ae_static_6_copy',
-                 body_model='checkpoints/ae_body_8_copy',
-                 curvature_model='checkpoints/ae_curvature_7_copy',
-                 freeze_encoders=True,
-                 encoder_res=512)
 
     upscale_enhancer = get_upscale_enhancer('checkpoints/up_2_3', res=resolution)
 
-
+    optimizer = tf.optimizers.Adam(learning_rate=config['lr'])
-    # lr_schedule = tf.keras.optimizers.schedules.ExponentialDecay(0.0001, decay_steps=30000, decay_rate=0.1, staircase=False)
+    balancing_coeff = config['starting_balancing_coeff']
-    optimizer = tf.optimizers.Adam(learning_rate=0.0001)
-    balancing_coeff = 0.0001
     reg_coeff = 1
-    folder = 'models/ae_logs/'
     valid_iterator = iter(dataset_valid)
     gamma = 1
     balancing_activated_step = 0
-    # avg_jumpsuit = np.load('custom_data/jumpsuit_20_avg_uv.npy')
-
 
     # sample('checkpoints/cvae_13')
 
-
     ckpt = tf.train.Checkpoint(model=model)
-    manager = tf.train.CheckpointManager(ckpt, 'checkpoints/' + name, max_to_keep=3)
+    manager = tf.train.CheckpointManager(ckpt, 'checkpoints/' + config['name'], max_to_keep=3)
 
     step = 0
     for batch in dataset_train:
-        batch = static_dataset_train.expand_batch(batch_to_dict(batch, signature_dynamic))
+        batch = static_dataset_train.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
 
         train_loss = train_step(batch)
 
@@ -514,8 +418,6 @@ if __name__ == '__main__':
                 balancing_activated_step = step
             balancing_coeff = balancing_coeff + 1 / 15000
 
-        # gamma = 0.99 * gamma + 0.01 * train_loss['train/reconstr_loss']        
-
         to_log = { **to_log, **{ 'train/balancing_coeff': balancing_coeff, 'train/gamma': gamma } }
         
         wandb.log(to_log, step = step)