helper

aaa_helpers.txt

@@ -1,4 +1,5 @@
 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

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

@@ -1,7 +1,7 @@
 config = dict()
 
 config['gpu'] = '0'
-config['name'] = 'pyr_abl_32_r1'
+config['name'] = 'pyr_abl_32'
 config['notes'] = ''
 
 # DON'T FORGET TO RESET SSIM LOSS USAGE

configs/config_abl_pyr_32_skirt.py

@@ -1,8 +1,8 @@
 config = dict()
 
 config['gpu'] = '3'
-config['name'] = 'pyr_abl_32_skirt_r1'
+config['name'] = 'pyr_abl_32_skirt_2'
-config['notes'] = ''
+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['train_dir'] = '/home/workspace/local-data/train_skirt'
-config['pretrained_model_iteration'] = ''
-
-config['train_dir'] = '/home/workspace/data/dataset/local-cache/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]
 

cvae_pyramid.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_pyr_32_skirt 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'
+        artifact.add_file('/'.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'])
@@ -210,7 +208,7 @@ def plot_3d(mesh_gt, mesh_pred_unposed_levels, faces, mesh_posed, collision, col
     return fig
 
 
-# @tf.function
+@tf.function
 def train_step(batch):
     levels_input, conds = group_inputs_for_levels(batch, config)
 
@@ -263,8 +261,8 @@ def train_step(batch):
         else:
             reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
 
-        # if config['use_norm_loss'] and step > 2000:
+        if config['use_norm_loss'] and step > 2000:
-        #     reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
+            reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
         
         kl_total += kl
 
@@ -336,8 +334,8 @@ def valid_step(batch):
     else:
         reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
     
-    # if config['use_norm_loss'] and step > 2000:
+    if config['use_norm_loss'] and step > 2000:
-    #     reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
+        reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
         
     kl_total += kl
 
@@ -733,7 +731,7 @@ def speed_step(levels_input, conds):
 
 
 if __name__ == '__main__':
-    # init_wandb()
+    init_wandb()
     parser = argparse.ArgumentParser(description='')
     parser.add_argument('--name', type=str, default='lhunor')
     args = vars(parser.parse_args())
@@ -792,7 +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')
 
@@ -809,18 +807,18 @@ if __name__ == '__main__':
         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:
+    # if config['pyramid']['resolutions'][-1] != 512:
-        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):
         model.levels[i].trainable = False

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
+# Start the container with a bash shell
-# RUN wandb login
+CMD ["/bin/bash"]

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'])