resnet condition encoders

aaa_helpers.txt

@@ -1,7 +1,7 @@
 nohup python cvae.py --name="lhunor_weights_test_6" > nohup/iccv/weights_test_6.out 2>&1 &
 nohup python evaluate_ae.py --name iccv_weights_test_6 > nohup/iccv/evaluate_iccv_weights_test_6.out 2>&1 &
 nohup python calculate_error.py --name iccv_weights_test_6 > nohup/iccv/error_iccv_weights_test_6.out 2>&1 &
-nohup python auto_encoder_static.py --name="lhunor_ae_static_iccv_resnet_1" > nohup/iccv/ae_static_iccv_resnet_1.out 2>&1 &
+nohup python auto_encoder_static.py --name="lhunor_ae_static_iccv_resnet_1" > nohup/iccv/encoders/ae_static_iccv_resnet_1.out 2>&1 &
 
 
 one final convolutional layer for smoothing, on the final coordinates

auto_encoder_body.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.review.config_ae_body import config
+from configs.iccv.config_ae_body import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -31,10 +31,11 @@ from losses import edge_loss, uv_mask_loss
 from dataset import DatasetFactory, StaticDataset
 from custom_utils.custom_utils import batch_to_dict, plot_3d
 from models.cond_encoder import AutoEncoderNew as AutoEncoder
+from custom_utils.custom_utils import Accumulator
 
 
 def init_wandb():
-    run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/home/workspace/local-data/temp', tags=config['tags'])
+    run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/tmp', tags=config['tags'])
     artifact = wandb.Artifact('code', type='code')
     artifact.add_file('auto_encoder_body.py')
     artifact.add_file('losses.py')
@@ -42,9 +43,11 @@ 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.review.')]
+    config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.')]
     for config_file_name in config_file_names:
-        artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
+        file_name = '/'.join(config_file_name.split('.')) + '.py'
+        if os.path.exists(file_name):
+            artifact.add_file(file_name)
     run.log_artifact(artifact)
 
 uv2mesh = UV2Mesh(res=256, is_smpl_orig=config['is_cape'], is_skirt=config['is_skirt'])
@@ -60,7 +63,8 @@ def train_step(batch):
 
         e_loss = 1e-2 * tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, tf.ones((pred.shape[0], 3638 if config['is_cape'] else 14475))))
         l1_loss = tf.reduce_mean(tf.reduce_sum(((tf.math.abs(batch['uv_body_posed' + resolution_modifier] - pred))), axis=1))
-        ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 1, batch['uv_body_posed' + resolution_modifier] + 1, max_val=2, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
+        # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 1, batch['uv_body_posed' + resolution_modifier] + 1, max_val=3, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
+        ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_body_posed' + resolution_modifier] + 1, max_val=3))
 
         loss = 1e3 * (1 - ms_ssim)
 
@@ -80,7 +84,8 @@ def valid_step(batch):
 
     e_loss = 1e-2 * tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, tf.ones((pred.shape[0], 3638 if config['is_cape'] else 14475))))
     l1_loss = tf.reduce_mean(tf.reduce_sum(((tf.math.abs(batch['uv_body_posed' + resolution_modifier] - pred))), axis=1))
-    ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 1, batch['uv_body_posed' + resolution_modifier] + 1, max_val=2, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
+    # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 1, batch['uv_body_posed' + resolution_modifier] + 1, max_val=3, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
+    ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_body_posed' + resolution_modifier] + 1, max_val=3))
 
     loss = 1e3 * (1 - ms_ssim)
 
@@ -124,24 +129,27 @@ def train():
     for batch in dataset_train:
         batch = static_dataset_train.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
         train_loss = train_step(batch)
+        train_accumulator.update(train_loss)
 
-        data_valid = valid_iterator.get_next()
+        if step % 50 == 0:
-        data_valid = static_dataset_valid.expand_batch(batch_to_dict(data_valid, config['signature_dynamic']))
+            data_valid = valid_iterator.get_next()
-        valid_loss = valid_step(data_valid)
+            data_valid = static_dataset_valid.expand_batch(batch_to_dict(data_valid, config['signature_dynamic']))
+            valid_loss = valid_step(data_valid)
+            valid_accumulator.update(valid_loss)
 
-        to_log = { **train_loss, **valid_loss, **{ 'current_step': step} }
+        if step % 1000 == 0 or (step < 1000 and step % 100 == 0):
-        if step % 5000 == 0 or (step < 5000 and step % 500 == 0):
+            to_log = dict({ **train_loss, **valid_loss, **{ 'current_step': step } })
-            train_figs = plot_everything(batch, 'train')
+            if step % 5000 == 0 or (step < 5000 and step % 1000 == 0):
-            valid_figs = plot_everything(data_valid, 'valid')
+                train_figs = plot_everything(batch, 'train')
-            to_log = { **to_log, **train_figs, **valid_figs }
+                valid_figs = plot_everything(data_valid, 'valid')
-        if step == 0:
+                to_log = { **to_log, **train_figs, **valid_figs }
-            to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
+            if step == 0:
+                to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
+                
+            wandb.log(to_log, step=step)
+            train_accumulator.reset()
+            valid_accumulator.reset()
 
-        if step % 1000 == 0:    
-            wandb.log(to_log, step=step, commit=True)
-        else:
-            wandb.log(to_log, step=step, commit=False)
-            
         if step % 10000 == 0:
             manager_enc.save(checkpoint_number=step)
             manager_dec.save(checkpoint_number=step)
@@ -207,5 +215,7 @@ if __name__ == '__main__':
     manager_enc = tf.train.CheckpointManager(ckpt_enc, 'checkpoints/post/' + config['name'] + '_enc', max_to_keep=20)
     ckpt_dec = tf.train.Checkpoint(model=model.decoder)
     manager_dec = tf.train.CheckpointManager(ckpt_dec, 'checkpoints/post/' + config['name'] + '_dec', max_to_keep=20)
+    train_accumulator = Accumulator()
+    valid_accumulator = Accumulator()
 
     train()

auto_encoder_curv.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.review.config_ae_curv import config
+from configs.iccv.config_ae_curv import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -32,12 +32,13 @@ from tf_utils import check_tf_version, allow_memory_growth
 from dataset import DatasetFactory, StaticDataset
 from custom_utils.custom_utils import batch_to_dict
 from models.cond_encoder import AutoEncoderNew as AutoEncoder
+from custom_utils.custom_utils import Accumulator
 
 
 testing = False
 def init_wandb():
     if not testing:
-        run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/home/workspace/local-data/temp', tags=config['tags'])
+        run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/tmp', tags=config['tags'])
         artifact = wandb.Artifact('code', type='code')
         artifact.add_file('auto_encoder_curv.py')
         artifact.add_file('losses.py')
@@ -45,9 +46,11 @@ 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.review.')]
+        config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.')]
         for config_file_name in config_file_names:
-            artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
+            file_name = '/'.join(config_file_name.split('.')) + '.py'
+            if os.path.exists(file_name):
+                artifact.add_file(file_name)
         run.log_artifact(artifact)
 
 uv2mesh = UV2MeshLabel(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
@@ -164,24 +167,26 @@ def train():
         batch = static_dataset_train.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
 
         train_loss = train_step(batch)
+        train_accumulator.update(train_loss)
 
-        data_valid = valid_iterator.get_next()
+        if step % 50 == 0:
-        data_valid = static_dataset_valid.expand_batch(batch_to_dict(data_valid, config['signature_dynamic']))
+            data_valid = valid_iterator.get_next()
-        valid_loss = valid_step(data_valid)
+            data_valid = static_dataset_valid.expand_batch(batch_to_dict(data_valid, config['signature_dynamic']))
+            valid_loss = valid_step(data_valid)
+            valid_accumulator.update(valid_loss)
 
-        to_log = { **train_loss, **valid_loss }
+        if step % 1000 == 0 or (step < 1000 and step % 100 == 0):
-        if step % 5000 == 0 or (step < 5000 and step % 500 == 0):
+            to_log = dict({ **train_loss, **valid_loss, **{ 'current_step': step } })
-            train_figs = plot_everything(batch, 'train')
+            if step % 5000 == 0 or (step < 5000 and step % 1000 == 0):
-            valid_figs = plot_everything(data_valid, 'valid')
+                train_figs = plot_everything(batch, 'train')
-            to_log = { **to_log, **train_figs, **valid_figs }
+                valid_figs = plot_everything(data_valid, 'valid')
-        if step == 0:
+                to_log = { **to_log, **train_figs, **valid_figs }
-            to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
+            if step == 0:
- 
+                to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
-        if step % 1000 == 0:    
+                
-            wandb.log(to_log, step=step, commit=True)
+            wandb.log(to_log, step=step)
-        else:
+            train_accumulator.reset()
-            wandb.log(to_log, step=step, commit=False)  
+            valid_accumulator.reset()
-        # print(step)
 
         if step % 10000 == 0:
             manager_enc.save(checkpoint_number=step)
@@ -257,6 +262,8 @@ if __name__ == '__main__':
     manager_enc = tf.train.CheckpointManager(ckpt_enc, 'checkpoints/post/' + config['name'] + '_enc', max_to_keep=20)
     ckpt_dec = tf.train.Checkpoint(model=model.decoder)
     manager_dec = tf.train.CheckpointManager(ckpt_dec, 'checkpoints/post/' + config['name'] + '_dec', max_to_keep=20)
+    train_accumulator = Accumulator()
+    valid_accumulator = Accumulator()
 
     if testing:
         test()

auto_encoder_static.py

@@ -34,6 +34,7 @@ from tf_utils import check_tf_version, allow_memory_growth
 from dataset import DatasetFactory, StaticDataset
 from custom_utils.custom_utils import batch_to_dict, plot_3d
 from models.cond_encoder import AutoEncoderNew as AutoEncoder
+from custom_utils.custom_utils import Accumulator
 
 
 def init_wandb():
@@ -46,9 +47,11 @@ 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.review.')]
+    config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.')]
     for config_file_name in config_file_names:
-        artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
+        file_name = '/'.join(config_file_name.split('.')) + '.py'
+        if os.path.exists(file_name):
+            artifact.add_file(file_name)
     run.log_artifact(artifact)
 
 uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
@@ -65,11 +68,14 @@ def train_step(batch):
 
         e_loss = 1e-2 * tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
         l1_loss = tf.reduce_mean(tf.reduce_sum((tf.math.abs(batch['uv_static'] - pred)), axis=1))
-        ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 1, batch['uv_static'] + 1, max_val=2, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
+        # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 1, batch['uv_static'] + 1, max_val=3, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
+        ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_static'] + 1, max_val=3))
         loss = 1e3 * (1 - ms_ssim)
+        # loss = l1_loss
 
     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'])
     gradients = tape.gradient(loss, model.trainable_variables)
+    gradients = [(tf.clip_by_norm(grad, clip_norm=2.0)) for grad in gradients]
     optimizer.apply_gradients(zip(gradients, model.trainable_variables))
     return { 'train/loss': loss, 'train/edge_loss': e_loss, 'train/l1_loss': l1_loss, 'train/euclid_error': metric, 'train/ms_ssim': ms_ssim, }
         
@@ -84,8 +90,10 @@ def valid_step(batch):
 
     e_loss = 1e-2 * tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
     l1_loss = tf.reduce_mean(tf.reduce_sum((tf.math.abs(batch['uv_static'] - pred)), axis=1))
-    ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 1, batch['uv_static'] + 1, max_val=2, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
+    # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 1, batch['uv_static'] + 1, max_val=3, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
-    loss = 1e3 * (1 - ms_ssim)
+    ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_static'] + 1, max_val=3))
+    loss = 1e3 * (1 - ms_ssim) 
+    # loss = l1_loss
 
     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'])
     return { 'valid/loss': loss, 'valid/edge_loss': e_loss, 'valid/l1_loss': l1_loss, 'valid/euclid_error': metric, 'valid/ms_ssim': ms_ssim, }
@@ -126,21 +134,26 @@ def train():
     for batch in dataset_train:
         batch = static_dataset_train.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
         train_loss = train_step(batch)
+        train_accumulator.update(train_loss)
 
-        data_valid = valid_iterator.get_next()
+        if step % 50 == 0:
-        data_valid = static_dataset_valid.expand_batch(batch_to_dict(data_valid, config['signature_dynamic']))
+            data_valid = valid_iterator.get_next()
-        valid_loss = valid_step(data_valid)
+            data_valid = static_dataset_valid.expand_batch(batch_to_dict(data_valid, config['signature_dynamic']))
+            valid_loss = valid_step(data_valid)
+            valid_accumulator.update(valid_loss)
 
-        to_log = dict({ **train_loss, **valid_loss, **{ 'current_step': step } })
+        if step % 1000 == 0 or (step < 1000 and step % 100 == 0):
-        if step % 5000 == 0 or (step < 5000 and step % 500 == 0):
+            to_log = dict({ **train_loss, **valid_loss, **{ 'current_step': step } })
-            train_figs = plot_everything(batch, 'train')
+            if step % 5000 == 0 or (step < 5000 and step % 1000 == 0):
-            valid_figs = plot_everything(data_valid, 'valid')
+                train_figs = plot_everything(batch, 'train')
-            to_log = { **to_log, **train_figs, **valid_figs }
+                valid_figs = plot_everything(data_valid, 'valid')
-        if step == 0:
+                to_log = { **to_log, **train_figs, **valid_figs }
-            to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
+            if step == 0:
-
+                to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
-
+                
-        wandb.log(to_log, step=step)
+            wandb.log(to_log, step=step)
+            train_accumulator.reset()
+            valid_accumulator.reset()
 
         if step % 10000 == 0:
             manager_enc.save(checkpoint_number=step)
@@ -184,17 +197,6 @@ def test():
 
     print()
 
-
-class MyLRSchedule(tf.keras.optimizers.schedules.LearningRateSchedule):
-
-  def __init__(self, initial_learning_rate):
-    self.initial_learning_rate = initial_learning_rate
-
-  def __call__(self, step):
-    if step < 1000:
-        return self.initial_learning_rate / 10.0
-    else:
-        return self.initial_learning_rate
   
 
 if __name__ == '__main__':
@@ -242,6 +244,8 @@ if __name__ == '__main__':
 
     model : AutoEncoder = AutoEncoder(config['cond_ae'])
     optimizer = tf.optimizers.Adam(learning_rate=config['lr'])
+    train_accumulator = Accumulator()
+    valid_accumulator = Accumulator()
 
     if config['pretrained_model'] != '':
         load_model(model.encoder, config['pretrained_model'] + '_enc')

configs/iccv/config_ae_body.py

@@ -23,19 +23,16 @@ config['cond_ae']['is_label'] = False
 config['cond_ae']['upscale_output'] = False
 config['cond_ae']['latent_dim'] = config['latent_dim']
 config['cond_ae']['kernel_size'] = 7
-config['cond_ae']['bottleneck_size'] = 16
+config['cond_ae']['bottleneck_size'] = 16 * 2
-config['cond_ae']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae']['layer_params'] = [3, 7, 15, 7, 3]
-config['cond_ae']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae']['bottleneck_size']]
-config['cond_ae']['decoder_depths'] = config['cond_ae']['encoder_depths']
-config['cond_ae']['decoder_dims'] = config['cond_ae']['encoder_dims']
 config['cond_ae']['activation'] = 'tanh'
 
 
-config['gpu'] = '4'
+config['gpu'] = '3'
 config['lr'] = 0.0001
-config['name'] = 'body_r7_3'
+config['name'] = 'body_resnet_1'
-config['notes'] = 'resnet18' 
+config['notes'] = '' 
-config['tags'] = ['review_7']
+config['tags'] = ['iccv', 'resnet']
 
 config['cond_ae']['upscale_output'] = False
 config['pretrained_model'] = ''

configs/iccv/config_ae_curv.py

@@ -23,19 +23,17 @@ config['cond_ae']['is_label'] = True
 config['cond_ae']['upscale_output'] = False
 config['cond_ae']['latent_dim'] = config['latent_dim']
 config['cond_ae']['kernel_size'] = 7
-config['cond_ae']['bottleneck_size'] = 40
+config['cond_ae']['bottleneck_size'] = 40 * 2
-config['cond_ae']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae']['layer_params'] = [3, 7, 15, 7, 3]
-config['cond_ae']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae']['bottleneck_size']]
-config['cond_ae']['decoder_depths'] = config['cond_ae']['encoder_depths']
-config['cond_ae']['decoder_dims'] = config['cond_ae']['encoder_dims']
 config['cond_ae']['activation'] = 'tanh'
 
 
-config['gpu'] = '3'
+
+config['gpu'] = '2'
 config['lr'] = 0.001
-config['name'] = 'curv_r7_3'
+config['name'] = 'curv_resnet_1'
-config['notes'] = 'resnet18' 
+config['notes'] = '' 
-config['tags'] = ['review_7']
+config['tags'] = ['iccv', 'resnet']
 
 config['cond_ae']['upscale_output'] = False
 config['pretrained_model'] = ''

configs/iccv/config_ae_static.py

@@ -23,17 +23,17 @@ config['cond_ae']['is_label'] = False
 config['cond_ae']['upscale_output'] = False
 config['cond_ae']['latent_dim'] = config['latent_dim']
 config['cond_ae']['kernel_size'] = 7
-config['cond_ae']['bottleneck_size'] = 8*4 # 8*4
+config['cond_ae']['bottleneck_size'] = 8*2 # 8*4
-config['cond_ae']['layer_params'] = [3, 4, 23, 4, 3]
+# config['cond_ae']['layer_params'] = [3, 4, 23, 4, 3]
-# config['cond_ae']['layer_params'] = [3, 4, 23, 3, 3]
+config['cond_ae']['layer_params'] = [3, 7, 15, 7, 3]
-config['cond_ae']['activation'] = 'linear'
+config['cond_ae']['activation'] = 'tanh'
 
 
-config['gpu'] = '5'
+config['gpu'] = '1'
-config['lr'] = 0.0001
+config['lr'] = 3e-4
 config['name'] = 'static_resnet_1'
-config['notes'] = 'resnet101 based, one more block'
+config['notes'] = ''
-config['tags'] = ['iccv', 'resnet']
+config['tags'] = ['iccv', 'resnet', 'static']
 
     
 

custom_utils/custom_utils.py

@@ -432,4 +432,28 @@ def group_inputs_for_levels(batch, config):
             uv_orig = batch['uv_posed' + res_modifier]
         levels_input.append([uv_orig, batch['uv_static' + res_modifier], batch['uv_body_posed' + res_modifier], batch['uv_curvature' + res_modifier], batch['uv_mask' + res_modifier], batch['uv_mask']])
     conds = [batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature']]
-    return levels_input, conds
+    return levels_input, conds
+
+
+
+
+
+class Accumulator():
+    def __init__(self):
+        self.dict = dict()
+
+    def update(self, dict):
+        for key in dict.keys():
+            if key in self.dict.keys():
+                self.dict[key].append(dict[key])
+            else:
+                self.dict[key] = [dict[key]]
+
+    def get(self):
+        result = dict()
+        for key in self.dict.keys():
+            result[key] = np.mean(self.dict[key])
+        return result
+
+    def reset(self):
+        self.dict = dict()

models/base.py

@@ -166,7 +166,7 @@ class AEEncoderNew(tf.keras.Model):
     def __init__(self, layer_params, features, activation='tanh'):
         super(AEEncoderNew, self).__init__()
 
-        self.encoder = resnet_18(layer_params, features)
+        self.encoder = resnet_101(layer_params, features)
         self.act = tf.keras.layers.Activation(activation)
 
 
@@ -193,9 +193,9 @@ class DecoderNew(tf.keras.Model):
         self.is_label = is_label
 
         if not is_label:
-            self.decoder = resnet_18(layer_params, features, reversed=True, is_cvae=is_cvae)
+            self.decoder = resnet_101(layer_params, features, reversed=True, is_cvae=is_cvae)
         else:
-            self.decoder = resnet_18(layer_params, features, reversed=True, labels=6, is_cvae=is_cvae)
+            self.decoder = resnet_101(layer_params, features, reversed=True, labels=6, is_cvae=is_cvae)
             
 
     def call(self, inputs, training):

models/resnet.py

@@ -133,7 +133,7 @@ class ResNetTypeI(tf.keras.Model):
         self.labels = labels
 
         if not reversed:
-            self.conv1 = tf.keras.layers.Conv2D(filters=64,
+            self.conv1 = tf.keras.layers.Conv2D(filters=32,
                                                 kernel_size=(7, 7),
                                                 strides=2,
                                                 padding="same")
@@ -149,19 +149,19 @@ class ResNetTypeI(tf.keras.Model):
             self.bn1 = tf.keras.layers.BatchNormalization()
             self.pool1 = tf.keras.layers.UpSampling2D()
 
-        self.layer1 = make_basic_block_layer(filter_num=64,
+        self.layer1 = make_basic_block_layer(filter_num=32,
                                              blocks=layer_params[0],
                                              stride=1 if not reversed else 2,
                                              upsample=reversed)
-        self.layer2 = make_basic_block_layer(filter_num=64,
+        self.layer2 = make_basic_block_layer(filter_num=32,
                                              blocks=layer_params[1],
                                              stride=2,
                                              upsample=reversed)
-        self.layer3 = make_basic_block_layer(filter_num=64,
+        self.layer3 = make_basic_block_layer(filter_num=32,
                                              blocks=layer_params[2],
                                              stride=2,
                                              upsample=reversed)
-        self.layer4 = make_basic_block_layer(filter_num=128,
+        self.layer4 = make_basic_block_layer(filter_num=64,
                                              blocks=layer_params[3],
                                              stride=2,
                                              upsample=reversed)
@@ -207,7 +207,7 @@ class ResNetTypeII(tf.keras.Model):
         self.labels = labels
 
         if not reversed:
-            self.conv1 = tf.keras.layers.Conv2D(filters=64,
+            self.conv1 = tf.keras.layers.Conv2D(filters=32,
                                                 kernel_size=(7, 7),
                                                 strides=2,
                                                 padding="same")
@@ -223,19 +223,19 @@ class ResNetTypeII(tf.keras.Model):
             self.bn1 = tf.keras.layers.BatchNormalization()
             self.pool1 = tf.keras.layers.UpSampling2D()
 
-        self.layer1 = make_bottleneck_layer(filter_num=64,
+        self.layer1 = make_bottleneck_layer(filter_num=32,
                                             blocks=layer_params[0],
                                             stride=1 if not reversed else 2,
                                             upsample=reversed)
-        self.layer2 = make_bottleneck_layer(filter_num=128,
+        self.layer2 = make_bottleneck_layer(filter_num=64,
                                             blocks=layer_params[1],
                                             stride=2,
                                             upsample=reversed)
-        self.layer3 = make_bottleneck_layer(filter_num=256,
+        self.layer3 = make_bottleneck_layer(filter_num=64,
                                             blocks=layer_params[2],
                                             stride=2,
                                             upsample=reversed)
-        self.layer4 = make_bottleneck_layer(filter_num=512,
+        self.layer4 = make_bottleneck_layer(filter_num=128,
                                             blocks=layer_params[3],
                                             stride=2,
                                             upsample=reversed)