helper

aaa_helpers.txt

@@ -1,11 +1,5 @@
-nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_64_e2e_r3" > nohup/review/pyr_abl_32_64_e2e_r3.out 2>&1 &
-nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_64_e2e_r3_pre" > nohup/review/pyr_abl_32_64_e2e_r3_pre.out 2>&1 &
-nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_64_e2e_r3_fine" > nohup/review/pyr_abl_32_64_e2e_r3_fine.out 2>&1 &
-nohup python evaluate_ae_pyramid.py --name evaluate_pyr_abl_32_64_e2e_r3 > nohup/evaluate/pyr_abl_32_64_e2e_r3.out 2>&1 &
-nohup python calculate_error.py --name error_pyr_abl_32_64_e2e_r3 > nohup/error/pyr_abl_32_64_e2e_r3.out 2>&1 &
-
-
 one final convolutional layer for smoothing, on the final coordinates
+nohup python calculate_error.py --name error_al_all_150k > nohup/error/post_al_all_150k.out 2>&1 &
 
 skirts!!!!
 pyramid next week

calculate_error.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_pyr_32 import config
+from configs.config_abl_all_post import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 # import tensorflow as tf
@@ -59,13 +59,13 @@ if __name__ == '__main__':
     folder = config['test_dir']
 
     checkpoint_name = config['name']
-    iteration = '200000'
+    iteration = ''
 
     F = np.load("custom_utils/smpl_faces" + skirt_modifier + ".npy").astype(np.int32)
     garment_type_table = np.load('custom_data/garment_type_table_test.npy', allow_pickle=True).item()
 
 
-    output_folder = '/home/workspace/data/results/' + checkpoint_name + '-' + iteration
+    output_folder = '/home/workspace/data/results/post/' + checkpoint_name + '-' + iteration
 
 
     faces_folder = '/home/workspace/data/results/support/faces' + ('_skirt' if config['is_skirt'] else '')

configs/config_abl_all_post.py

@@ -19,7 +19,7 @@ config['only_curvatures'] =           False
 ablation_count = [config['use_skinning'], config['remove_global_orientation'], config['use_curvature'], config['use_extra_losses'], config['use_offsets']].count(False)
 assert ablation_count == 1 or ablation_count == 0
 
-config['gpu'] = '1'
+config['gpu'] = '4'
 config['name'] = 'al_all_post'
 config['notes'] = ''
 

configs/config_abl_pyr_32.py

@@ -1,9 +1,8 @@
 config = dict()
 
 config['gpu'] = '0'
-config['name'] = 'pyr_abl_32_64_e2e_r3_fine_2'
+config['name'] = 'pyr_abl_32'
 config['notes'] = ''
-config['tags'] = ['review_3']
 
 # DON'T FORGET TO RESET SSIM LOSS USAGE
 # DON'T FORGET TO CHECK MODEL LOADING
@@ -22,12 +21,9 @@ config['use_offsets'] =               False
 
 
 config['pyramid'] = dict()
-config['pyramid']['resolutions'] = [32, 64]
+config['pyramid']['resolutions'] = [32]
 config['pyramid']['pretrained_pyramid'] = ''
-config['pyramid']['final_upscale_enhancer'] = 'checkpoints/64_512_2'
-
-config['pretrained_model'] = 'checkpoints/pyr_abl_32_64_e2e_r3_fine'
-config['pretrained_model_iteration'] = ''
+config['pyramid']['final_upscale_enhancer'] = 'checkpoints/32_512_4'
 
 config['train_dir'] = '/home/workspace/local-data/train'
 config['valid_dir'] = '/home/workspace/local-data/valid'
@@ -44,7 +40,7 @@ config['smpl_res'] = 14475
 if config['is_cape']:
   config['smpl_res'] = 3638
 
-config['lr'] = 0.00001
+config['lr'] = 0.0001
 config['starting_balancing_coeff'] = 0.0001
 config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
 config['avg_garment_path'] = ''
@@ -68,7 +64,7 @@ config['pyramid']['latent_dim'] = config['latent_dim']
 config['pyramid']['add_noise'] = True
 config['pyramid']['noise_amount'] = 0.025
 
-config['pyramid']['loss_weights'] = [2,1,1,1,1]
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
 
 for res in config['pyramid']['resolutions']:
   if res != 512:
@@ -153,7 +149,7 @@ for res in config['pyramid']['resolutions']:
     level['decoder_depths'] = [9, 9]
     level['decoder_dims'] = [256, 256]
     level['avg_garment_path'] = ''
-    level['upscale_enhancer'] = 'checkpoints/32_512_4'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer'] = ''#'checkpoints/up_3_d32_64_2'
     level['upscale_enhancer_freeze'] = True
     config['pyramid']['levels'].append(level)
   else:

configs/config_abl_pyr_32_skirt.py

@@ -1,8 +1,8 @@
 config = dict()
 
 config['gpu'] = '3'
-config['name'] = 'pyr_abl_32_skirt_r1'
-config['notes'] = ''
+config['name'] = 'pyr_abl_32_skirt_2'
+config['notes'] = 'continued from pyr_abl_32_skirt-180k'
 
 # DON'T FORGET TO RESET SSIM LOSS USAGE
 # DON'T FORGET TO CHECK MODEL LOADING
@@ -24,10 +24,7 @@ config['pyramid']['resolutions'] = [32]
 config['pyramid']['pretrained_pyramid'] = ''
 config['pyramid']['final_upscale_enhancer'] = 'checkpoints/32_512_skirt'
 
-config['pretrained_model'] = ''
-config['pretrained_model_iteration'] = ''
-
-config['train_dir'] = '/home/workspace/data/dataset/local-cache/train_skirt'
+config['train_dir'] = '/home/workspace/local-data/train_skirt'
 config['valid_dir'] = '/home/workspace/local-data/valid_skirt'
 config['test_dir'] = '/home/workspace/data/dataset/test_skirt_ready_2'
 config['batch_size'] = 4
@@ -38,7 +35,7 @@ config['pyramid']['static_model'] = 'checkpoints/static_1_skirt'
 config['pyramid']['body_model'] = 'checkpoints/body_1_skirt_2_2'
 config['pyramid']['curvature_model'] = 'checkpoints/curv_1_skirt'
 
-config['dataset_in_memory'] = True
+config['dataset_in_memory'] = False
 config['resolution'] = None
 config['latent_dim'] = 128
 
@@ -68,7 +65,6 @@ config['signature_static'] = { 'uv_static': (512, 256, 3),
 config['pyramid']['is_label'] = False
 config['pyramid']['latent_dim'] = config['latent_dim']
 config['pyramid']['add_noise'] = True
-config['pyramid']['noise_amount'] = 0.001
 
 config['pyramid']['loss_weights'] = [1,1,1,1,1]
 

custom_utils/custom_utils.py

@@ -45,7 +45,7 @@ class UV2Mesh(tf.keras.Model):
         if uv.shape[1] == 3:
             uv = tf.transpose(uv, [0,2,3,1])
         if uv.shape[1] != 512:
-            uv = tf.image.resize(uv, (512, 256), tf.image.ResizeMethod.BILINEAR)
+            uv = tf.image.resize(uv, (512, 256), tf.image.ResizeMethod.LANCZOS5)
             
         batch_size = uv.shape[0]
 

cvae_pyramid.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_pyr_32 import config
+from configs.post.config_abl_pyr_64_128_5 import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
@@ -41,7 +41,7 @@ from losses import collision_loss as collision_penalty
 from custom_utils.custom_utils import batch_to_dict, load_model
 from dataset import DatasetFactory, StaticDataset
 from custom_utils.smpl import SMPL
-from models.pyramid_model_optimized import Pyramid
+from models.pyramid_model_optimized import PyramidNew as Pyramid
 from postprocessing import fix_collision
 
 
@@ -59,11 +59,9 @@ def init_wandb():
     artifact.add_file('models/cond_encoder.py')
     artifact.add_file('dataset.py')
     artifact.add_file('convnext/models/convnext_tf.py')
-    config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs')]
+    config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.post.')]
     for config_file_name in config_file_names:
-        file_name = '/'.join(config_file_name.split('.')) + '.py'
-        if os.path.exists(file_name):
-            artifact.add_file(file_name)
+        artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
     run.log_artifact(artifact)
 
 uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
@@ -217,100 +215,19 @@ def train_step(batch):
     with tf.GradientTape() as tape:
         out_levels = model([levels_input, conds], training=True)
 
-        mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
+        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]
-            if res != 512:
-                if i == len(config['pyramid']['resolutions']) - 1:
-                    res_modifier = ''
-                else:
-                    res_modifier = '_' + str(res)
-            else:
-                res_modifier = ''
-
-            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(((batch['uv_unposed' + res_modifier] - 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, **{ '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)
-
-    mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
-
-    output = dict()
-    reconstr_loss_total = 0
-    kl_total = 0
-
-    for i, res in enumerate(config['pyramid']['resolutions']):
-        # i = -1
-        # res = config['pyramid']['resolutions'][-1]
-        if res != 512:
-            if i == len(config['pyramid']['resolutions']) - 1:
-                res_modifier = ''
-            else:
-                res_modifier = '_' + str(res)
-        else:
-            res_modifier = ''
-
+        #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)
@@ -324,12 +241,13 @@ def valid_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(((batch['uv_unposed' + res_modifier] - 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), 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))
@@ -342,10 +260,10 @@ def valid_step(batch):
                 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']
         
-        # 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)
@@ -353,10 +271,83 @@ def valid_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, **{ '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, **{ '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,
 
     loss = reconstr_loss_total + balancing_coeff * kl_total
 
@@ -799,7 +790,7 @@ if __name__ == '__main__':
     # generate_results()
 
     ckpt = tf.train.Checkpoint(model=model)
-    manager = tf.train.CheckpointManager(ckpt, 'checkpoints/' + config['name'], max_to_keep=20)
+    manager = tf.train.CheckpointManager(ckpt, 'checkpoints/post/' + config['name'], max_to_keep=20)
 
     # load_model(model, 'checkpoints/pyr_abl_32_skirt', iteration='180000')
 
@@ -807,33 +798,30 @@ if __name__ == '__main__':
         # assert len(config['pyramid']['resolutions']) == 1
         load_model(model, config['pretrained_model'], iteration=config['pretrained_model_iteration'])
 
-    model.static_enc.trainable = False
-    model.body_enc.trainable = False
-    model.curv_enc.trainable = False
+    if len(config['pyramid']['resolutions']) == 1:
+        model.static_enc.trainable = False
+        model.body_enc.trainable = False
+        model.curv_enc.trainable = False
+    else:
+        load_model(model, config['pyramid']['pretrained_pyramid'], iteration=(config['pyramid']['pretrained_pyramid_iteration'] if 'pretrained_pyramid_iteration' in config.keys() else ''))
+        model.static_enc.trainable = False
+        model.body_enc.trainable = False
+        model.curv_enc.trainable = False
 
-    # model.trainable = False
-    # model.cond_encoder_2.trainable = True
-    # if len(config['pyramid']['resolutions']) == 1:
-    # else:
-    #     load_model(model, config['pyramid']['pretrained_pyramid'], iteration=(config['pyramid']['pretrained_pyramid_iteration'] if 'pretrained_pyramid_iteration' in config.keys() else ''))
-    #     model.static_enc.trainable = False
-    #     model.body_enc.trainable = False
-    #     model.curv_enc.trainable = False
-    #     model.cond_encoder.trainable = False
 
     # load_model(model.levels[0].upscale_enhancer, config['pyramid']['levels'][0]['upscale_enhancer'])
     # model.levels[0].upscale_enhancer.trainable = False
 
 
-    for i in range(len(model.levels)-1):
+    for i in range(len(model.levels)):
         load_model(model.levels[i].upscale_enhancer, config['pyramid']['levels'][i]['upscale_enhancer'])
         model.levels[i].upscale_enhancer.trainable = False
-    if config['pyramid']['resolutions'][-1] != 512:
-        load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
-        model.upscale_enhancer.trainable = False
+    # if config['pyramid']['resolutions'][-1] != 512:
+    #     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'])

docker/Dockerfile

@@ -2,9 +2,41 @@ FROM tensorflow/tensorflow:2.9.0-gpu
 
 RUN apt-get update
 RUN apt-get upgrade -y
+
+# Add the current user to the image
+ARG USER_NAME=lhunor
+ARG USER_ID=11017
+ARG GROUP_NAME=guest
+ARG GROUP_ID=11000
+
+# Update the system and install required packages
+RUN apt-get update && apt-get upgrade -y && apt-get install -y sudo git
+
+# Create a new group with the same GID as the host
+RUN groupadd --gid $GROUP_ID $GROUP_NAME
+
+# Create a new user with the same UID and GID as the host
+RUN useradd --uid $USER_ID --gid $GROUP_ID --shell /bin/bash --create-home $USER_NAME
+
+# don't require password with sudo, for convenience
+# not the safest thing to do, but hopefully okay inside the container
+RUN echo '%sudo ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers
+
+# Add the new user to the sudo group
+RUN usermod -aG sudo $USER_NAME
+
+# Set the default user to the new user
+USER $USER_NAME
+
+WORKDIR //home-net
+
 RUN apt-get install git ffmpeg libsm6 libxext6 libopenexr-dev zip unzip htop nano -y
 RUN pip install numpy matplotlib opencv-python wandb OpenEXR tensorflow-graphics scipy plotly pandas tensorboardX opencv-python cmapy
 
+# defining the volumes that will be mounted
+VOLUME [ "/data-net" ]
+VOLUME [ "/data-local" ]
+VOLUME [ "/home-net" ]
 
-WORKDIR /home/workspace/data
-# RUN wandb login
+# Start the container with a bash shell
+CMD ["/bin/bash"]

evaluate_ae_pyramid.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_pyr_32 import config
+from configs.config_abl_2_pyr_32_64_128_256_512 import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
@@ -97,7 +97,7 @@ if __name__ == '__main__':
     ids = [id.split('_')[0] for id in ids]
     ids = set(ids)
 
-    iteration = '200000'
+    iteration = '50000'
 
     load_model(model, 'checkpoints/' + checkpoint_name, iteration=iteration)
     # load_model(model, 'checkpoints/' + 'abl_all_120k')

models/cvae_model.py

@@ -43,7 +43,7 @@ class CVAE(tf.keras.Model):
         self.cond_encoder = tf.keras.Sequential([tf.keras.layers.Dense(512, activation='relu'),
                                                  tf.keras.layers.Dense(256, activation='relu'),
                                                  tf.keras.layers.Dense(128, activation='relu'),
-                                                #  tf.keras.layers.Lambda(lambda x: x / 1000),
+                                                 tf.keras.layers.Lambda(lambda x: x / 1000),
                                                  tf.keras.layers.Dense(config['latent_dim'], activation='tanh')])
 
         self.encoder = VariationalEncoder(config['cvae']['latent_dim'], config['cvae']['encoder_depths'], config['cvae']['encoder_dims'], kernel_size=config['cvae']['kernel_size'])

models/pyramid_level.py

@@ -92,7 +92,7 @@ class PyramidLevel(tf.keras.Model):
         
         # x = x * uv_mask_high[:,:,:,tf.newaxis]
 
-        return x, z, mean, logvar
+        return x, mean, logvar
 
 
 

models/pyramid_model_optimized.py

@@ -78,11 +78,6 @@ class Pyramid(tf.keras.Model):
             load_model(self.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
             self.upscale_enhancer.trainable = False
 
-        self.cond_encoder_2 = tf.keras.Sequential([tf.keras.layers.Dense(512, activation='relu'),
-                                                 tf.keras.layers.Dense(256, activation='relu'),
-                                                 tf.keras.layers.Dense(128, activation='relu'),
-                                                 tf.keras.layers.Dense(config['pyramid']['latent_dim'], activation='tanh'),])
-
     def enhance(self, low, mask, training):
         x = self.upscale_enhancer([low, mask], training=training)
         return x
@@ -95,54 +90,44 @@ class Pyramid(tf.keras.Model):
         z_cond = tf.concat([z_static, z_body, z_curv], axis=-1)
         z_cond = self.cond_encoder(z_cond, training=training)
 
-        return z_cond, z_static, z_body, z_curv
-
-    def encode_conds_2(self, z, z_static, z_body, z_curv, training):
-        z_cond = tf.concat([z, z_static, z_body, z_curv], axis=-1)
-        z_cond = self.cond_encoder_2(z_cond, training=training)
-
         return z_cond
 
     def call(self, inputs, training):
         levels_input, conds = inputs
         uv_static, uv_body, uv_curv = conds[0], conds[1], conds[2]
 
-        z_cond, z_static, z_body, z_curv = self.encode_conds(uv_static, uv_body, uv_curv, training)
+        z_cond = self.encode_conds(uv_static, uv_body, uv_curv, training)
 
         if self.add_noise == True and training == True:
             z_cond = z_cond + (tf.random.uniform(z_cond.shape, maxval=self.noise_amount * 2) - self.noise_amount)
 
         out_levels = []
-        pred, z, mean, logvar = self.levels[0](levels_input[0], z_cond, training=training)
+        pred, mean, logvar = self.levels[0](levels_input[0], z_cond, training=training)
         if self.use_offsets:
             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.LANCZOS5)
             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)
-            pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.BILINEAR)
+            pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.LANCZOS5)
             pred = pred * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask
             out_levels.append([pred, mean, logvar])
 
         for i in range(1, len(self.levels)):
-            input = levels_input[i]
-            input[0] = pred # use previous level output as input for next level
-            z_cond_2 = self.encode_conds_2(z, z_static, z_body, z_curv, training=training)
-
-            pred_level, z, mean, logvar = self.levels[i](input, z_cond_2, training=training)
+            pred_level, mean, logvar = self.levels[i](levels_input[i], z_cond, training=training)
             pred = pred + pred_level
             if i != len(self.levels) - 1:
                 pred = self.levels[i].enhance(pred, levels_input[i][-2], training=training)
                 out_levels.append([pred, mean, logvar])
-                pred = tf.image.resize(pred, (self.levels[i+1].size, self.levels[i+1].size//2), tf.image.ResizeMethod.BILINEAR)
+                pred = tf.image.resize(pred, (self.levels[i+1].size, self.levels[i+1].size//2), tf.image.ResizeMethod.LANCZOS5)
                 pred = pred * levels_input[i+1][-2][:,:,:,tf.newaxis]
             else:
                 if self.upscale_enhancer is not None:
                     pred = self.enhance(pred, levels_input[-1][-2], training=training)
-                    pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.BILINEAR)
+                    pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.LANCZOS5)
                 pred = pred * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask
                 out_levels.append([pred, mean, logvar])