barely working decoder

aaa_helpers.txt

@@ -1,9 +1,16 @@
-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 &
-
-
 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 &
+nohup python auto_encoder_static.py --name="lhunor_static_iccv_1" > nohup/iccv/encoders/static_iccv_1.out 2>&1 &
+nohup python auto_encoder_static.py --name="lhunor_static_iccv_1_skirt" > nohup/iccv/encoders/static_iccv_1_skirt.out 2>&1 &
+nohup python auto_encoder_static.py --name="lhunor_static_iccv_1_cape_f" > nohup/iccv/encoders/static_iccv_1_cape_f.out 2>&1 &
+nohup python auto_encoder_static.py --name="lhunor_static_iccv_1_cape_m" > nohup/iccv/encoders/static_iccv_1_cape_m.out 2>&1 &
+nohup python auto_encoder_body.py --name="lhunor_body_iccv_1" > nohup/iccv/encoders/body_iccv_1.out 2>&1 &
+nohup python auto_encoder_body.py --name="lhunor_body_iccv_1_skirt" > nohup/iccv/encoders/body_iccv_1_skirt.out 2>&1 &
+nohup python auto_encoder_body.py --name="lhunor_body_iccv_1_skirt" > nohup/iccv/encoders/body_iccv_1_skirt.out 2>&1 &
+nohup python auto_encoder_curv.py --name="lhunor_curv_iccv_1 " > nohup/iccv/encoders/curv_iccv_1.out 2>&1 &
+nohup python auto_encoder_curv.py --name="lhunor_curv_iccv_1_skirt" > nohup/iccv/encoders/curv_iccv_1_skirt.out 2>&1 &
+nohup python auto_encoder_curv.py --name="lhunor_curv_iccv_1_cape_f" > nohup/iccv/encoders/curv_iccv_1_cape_f.out 2>&1 &
+nohup python cvae.py --name="lhunor_cvae_iccv_gnn_decoder_1" > nohup/iccv/cvae_iccv_gnn_decoder_1.out 2>&1 &
 
 skirts!!!!
 pyramid next week

auto_encoder_body.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_ae_body_post import config
+from configs.iccv.config_ae_body_cape_f 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')
+    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')
@@ -44,7 +45,9 @@ def init_wandb():
     artifact.add_file('convnext/models/convnext_tf.py')
     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'])
@@ -124,20 +127,26 @@ 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()
         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 % 10 == 0):
-        if step % 5000 == 0 or (step < 5000 and step % 500 == 0):
+            to_log = dict({ **train_loss, **valid_loss, **{ 'current_step': step } })
+            if step % 5000 == 0 or (step < 5000 and step % 1000 == 0):
                 train_figs = plot_everything(batch, 'train')
                 valid_figs = plot_everything(data_valid, 'valid')
                 to_log = { **to_log, **train_figs, **valid_figs }
             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 % 10000 == 0:
             manager_enc.save(checkpoint_number=step)
@@ -150,7 +159,6 @@ def train():
 
 if __name__ == '__main__':
     init_wandb()
-    allow_memory_growth()
     parser = argparse.ArgumentParser(description='')
     parser.add_argument('--name', type=str)
     args = vars(parser.parse_args())
@@ -196,13 +204,15 @@ if __name__ == '__main__':
 
     model = AutoEncoder(config['cond_ae'])
     optimizer = tf.optimizers.Adam(learning_rate=config['lr'])
+    train_accumulator = Accumulator()
+    valid_accumulator = Accumulator()
 
     # load_model(model.encoder, 'checkpoints/body_1_skirt_2_enc')
     # load_model(model.decoder, 'checkpoints/body_1_skirt_2_dec')
 
     ckpt_enc = tf.train.Checkpoint(model=model.encoder)
-    manager_enc = tf.train.CheckpointManager(ckpt_enc, 'checkpoints/post/' + config['name'] + '_enc', max_to_keep=20)
+    manager_enc = tf.train.CheckpointManager(ckpt_enc, 'checkpoints/iccv/' + 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)
+    manager_dec = tf.train.CheckpointManager(ckpt_dec, 'checkpoints/iccv/' + config['name'] + '_dec', max_to_keep=20)
 
     train()

auto_encoder_curv.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_ae_curv_post import config
+from configs.iccv.config_ae_curv_cape_f 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/')
+        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')
@@ -47,7 +48,9 @@ def init_wandb():
         artifact.add_file('convnext/models/convnext_tf.py')
         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'])
@@ -164,21 +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()
         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 % 10 == 0):
-        if step % 5000 == 0 or (step < 5000 and step % 500 == 0):
+            to_log = dict({ **train_loss, **valid_loss, **{ 'current_step': step } })
+            if step % 5000 == 0 or (step < 5000 and step % 1000 == 0):
                 train_figs = plot_everything(batch, 'train')
                 valid_figs = plot_everything(data_valid, 'valid')
                 to_log = { **to_log, **train_figs, **valid_figs }
             if step == 0:
                 to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
 
+                
             wandb.log(to_log, step=step)
-        print(step)
+            train_accumulator.reset()
+            valid_accumulator.reset()
 
         if step % 10000 == 0:
             manager_enc.save(checkpoint_number=step)
@@ -249,11 +257,13 @@ if __name__ == '__main__':
 
     model = AutoEncoder(config['cond_ae'])
     optimizer = tf.optimizers.Adam(learning_rate=config['lr'])
+    train_accumulator = Accumulator()
+    valid_accumulator = Accumulator()
 
     ckpt_enc = tf.train.Checkpoint(model=model.encoder)
-    manager_enc = tf.train.CheckpointManager(ckpt_enc, 'checkpoints/post/' + config['name'] + '_enc', max_to_keep=20)
+    manager_enc = tf.train.CheckpointManager(ckpt_enc, 'checkpoints/iccv/' + 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)
+    manager_dec = tf.train.CheckpointManager(ckpt_dec, 'checkpoints/iccv/' + config['name'] + '_dec', max_to_keep=20)
 
     if testing:
         test()

auto_encoder_static.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_ae_static import config
+from configs.iccv.config_ae_static_cape_m import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -34,10 +34,11 @@ 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():
-    run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/home/workspace/local-data/temp')
+    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_static.py')
     artifact.add_file('losses.py')
@@ -47,7 +48,9 @@ def init_wandb():
     artifact.add_file('convnext/models/convnext_tf.py')
     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'])
@@ -125,13 +128,16 @@ 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()
         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)
 
+        if step % 1000 == 0 or (step < 1000 and step % 10 == 0):
             to_log = dict({ **train_loss, **valid_loss, **{ 'current_step': step } })
-        if step % 5000 == 0 or (step < 5000 and step % 500 == 0):
+            if step % 5000 == 0 or (step < 5000 and step % 1000 == 0):
                 train_figs = plot_everything(batch, 'train')
                 valid_figs = plot_everything(data_valid, 'valid')
                 to_log = { **to_log, **train_figs, **valid_figs }
@@ -140,6 +146,8 @@ def train():
 
                 
             wandb.log(to_log, step=step)
+            train_accumulator.reset()
+            valid_accumulator.reset()
 
         if step % 10000 == 0:
             manager_enc.save(checkpoint_number=step)
@@ -231,6 +239,9 @@ 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')
         load_model(model.decoder, config['pretrained_model'] + '_dec')

compare_models_saved.py

@@ -1,188 +0,0 @@
-import os
-import sys
-from configs.config_abl_all_post import config as config_a
-
-os.environ["CUDA_VISIBLE_DEVICES"] = '5'
-import tensorflow as tf
-
-gpus = tf.config.experimental.list_physical_devices('GPU')
-if gpus:
-    try:
-        # Currently, memory growth needs to be the same across GPUs
-        for gpu in gpus:
-            tf.config.experimental.set_memory_growth(gpu, True)
-        logical_gpus = tf.config.experimental.list_logical_devices('GPU')
-        print(len(gpus), "Physical GPUs,", len(logical_gpus), "Logical GPUs")
-    except RuntimeError as e:
-        # Memory growth must be set before GPUs have been initialized
-        print(e)
-
-import glob
-import time
-import argparse
-import wandb
-import tqdm
-import random
-import numpy as np
-import plotly.graph_objects as go
-import plotly.express as ex
-from PIL import Image
-from postprocessing import fix_collision
-
-if config_a['is_skirt']:
-    from losses import edge_loss_skirt as edge_loss
-else:
-    from losses import edge_loss
-
-
-
-from losses import collision_ratio, kl_loss #, concept_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, plot_3d, UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision
-from dataset import DatasetFactory, StaticDataset
-from custom_utils.smpl import SMPL
-from models.cvae_model import CVAE
-from custom_utils.supersmpl_io import writeOBJ
-from plotly.subplots import make_subplots
-
-
-# uv2mesh = UV2Mesh(res=256, is_skirt=config_a['is_skirt'], is_adaptive=False)
-
-
-
-def plot(mesh_gt, pred_a, pred_b, body, mask):
-    fig = make_subplots(rows=1, cols=3, start_cell="top-left", specs = [ [{ 'type': 'scene' } for _ in range(3)] ])
-    
-    _, faces_garment = _maskFaces(np.zeros((14475, 3), np.float32), F, mask)
-    faces = np.concatenate((F, faces_garment + 14475), axis=0)
-    mesh_gt = np.concatenate((body, mesh_gt[mask, :]), axis=0)
-    pred_a = np.concatenate((body, pred_a), axis=0)
-    pred_b = np.concatenate((body, pred_b), axis=0)
-    colors = np.concatenate((np.ones_like(body, dtype=np.int32)*100, np.ones_like(mesh_gt, dtype=np.int32)*230), axis=0)
-    # colors = np.ones_like(mesh_gt, dtype=np.int32)*230
-
-    fig.add_trace(go.Mesh3d(
-            x=mesh_gt[:,0],
-            y=mesh_gt[:,2],
-            z=mesh_gt[:,1],
-            i = faces[:,0],
-            j = faces[:,1],
-            k = faces[:,2],
-            text="Ground Truth",
-            vertexcolor=colors,
-        ),
-        row=1, col=1)
-
-    fig.add_trace(go.Mesh3d(
-            x=pred_a[:,0],
-            y=pred_a[:,2],
-            z=pred_a[:,1],
-            i = faces[:,0],
-            j = faces[:,1],
-            k = faces[:,2],
-            text="Pred A",
-            vertexcolor=colors,
-        ),
-        row=1, col=2)
-
-    fig.add_trace(go.Mesh3d(
-            x=pred_b[:,0],
-            y=pred_b[:,2],
-            z=pred_b[:,1],
-            i = faces[:,0],
-            j = faces[:,1],
-            k = faces[:,2],
-            text="Pred B",
-            vertexcolor=colors,
-        ),
-        row=1, col=3)
-
-
-
-    fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1), 
-                    scene2_aspectmode='manual', scene2_aspectratio=dict(x=1, y=1, z=1), 
-                    scene3_aspectmode='manual', scene3_aspectratio=dict(x=1, y=1, z=1), 
-                    )
-    helper = dict(xaxis = dict(nticks=4, range=[-1,1],),
-                yaxis = dict(nticks=4, range=[-1,1],),
-                zaxis = dict(nticks=4, range=[-1,1],),)
-    fig.update_layout(scene = helper,
-                        scene2 = helper,
-                        scene3 = helper,
-                        )
-
-    return fig
-
-
-
-if __name__ == '__main__':
-    run = wandb.init(project='plots', name=config_a['name'], notes=config_a['notes'], dir='/wandb')
-
-    parser = argparse.ArgumentParser(description='')
-    parser.add_argument('--name', type=str)
-    args = vars(parser.parse_args())
-
-    skirt_modifier = '_skirt' if config_a['is_skirt'] else ''
-
-    folder = config_a['test_dir']
-    # smpl = SMPL(use_one_hot=False)
-
-    F = np.load("custom_utils/smpl_faces" + skirt_modifier + ".npy").astype(np.int32)
-
-    iteration = ''
-
-    # load_model(model, 'checkpoints/' + 'abl_all_120k')
-
-
-    factory = DatasetFactory()
-    dataset_a = factory.get_dataset(folder=config_a['test_dir'], 
-                                       batch_size=config_a['batch_size'], 
-                                       signature=config_a['signature_dynamic'], 
-                                       resolutions=[config_a['resolution']], 
-                                       in_memory=False, 
-                                       do_repeat=False,
-                                       use_one_hot=config_a['use_one_hot'],
-                                       use_no_orient=config_a['remove_global_orientation'],
-                                       shuffle=False,
-                                       testing=True,
-                                    #    frames_file='frames_abl.txt',
-                                       )
-    static_dataset_a = StaticDataset(folder=config_a['test_dir'], 
-                                        signature=config_a['signature_static'], 
-                                        resolutions=[config_a['resolution']], 
-                                        in_memory=True)
-
-    iterator_a = iter(dataset_a)
-    
-
-    faces_folder = '/home/workspace/data/results/support/faces' + ('_skirt' if config_a['is_skirt'] else '')
-    ids = os.listdir(faces_folder)
-    ids = [id.split('.')[0] for id in ids]
-    faces = {id : np.load(faces_folder + '/' + id + '.npy') for id in ids }
-
-    results_folder = '/home/workspace/data/results/post'
-
-    count = 0
-    while True:
-        batch = iterator_a.get_next()
-
-        batch = static_dataset_a.expand_batch(batch_to_dict(batch, config_a['signature_dynamic']))
-
-        mask = batch['mesh_mask'].numpy().astype(bool)
-        gt = batch['mesh_posed'].numpy()
-        body = batch['mesh_body_posed'].numpy()
-
-        for i in range(mask.shape[0]):
-            id, frame_nr = batch['id'][i].numpy().decode("utf-8"), batch['frame_nr'][i].numpy().decode("utf-8")
-            pred_a = np.load(results_folder + '/al_all_post-/' + id + '_' + frame_nr + '.npy')
-            pred_b = np.load(results_folder + '/iccv_weights_test_6-/' + id + '_' + frame_nr + '.npy')
-            # pred_c = np.load(results_folder + '/iccv_weights_test_6-/' + id + '_' + frame_nr + '.npy')
-
-            fig = plot(gt[i], pred_a, pred_b, body[i], mask[i])
-
-            wandb.log({f'{id}_{frame_nr}': fig}, step = count)
-            count += 1
-
-            print(count)
-

configs/archive/config_abl_all_post.py

@@ -7,7 +7,7 @@ config = dict()
 # DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
 # DON'T FORGET TO CHECK AVG GARMENT USED
 
-config['use_skinning'] =              False # and deshaping
+config['use_skinning'] =              True # and deshaping
 config['remove_global_orientation'] = True
 config['use_curvature'] =             True
 config['use_extra_losses'] =          True # edge, collision, 3d mesh
@@ -19,9 +19,9 @@ 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'] = '5'
+config['gpu'] = '4'
-config['name'] = 'iccv_weights_test_8'
+config['name'] = 'al_all_post'
-config['notes'] = 'smaller weight loss coeff, 1e-6, convolutional weight learning, changed convnext reverse'
+config['notes'] = ''
 
 config['avg_garment_path'] = 'custom_data/train_no_shape_avg_uv.npy' #custom_data/train_no_shape_avg_uv.npy # train_no_shape_avg_uv  train_no_shape_one_hot_avg_uv
 if config['use_skinning']:
@@ -86,15 +86,14 @@ config['use_one_hot'] = False
 config['cvae'] = dict()
 config['cvae']['is_label'] = False
 config['cvae']['add_noise'] = True
-config['cvae']['noise_amount'] = 0.00001
+config['cvae']['noise_amount'] = 0.001
 
 config['cvae']['kernel_size'] = 7
 config['cvae']['encoder_depths'] = [3, 3, 3, 9, 3]
 config['cvae']['encoder_dims'] = [32, 64, 128, 256, 64]
-config['cvae']['decoder_depths'] = [3, 9, 3, 3, 3, 3]
+config['cvae']['decoder_depths'] = config['cvae']['encoder_depths']
-config['cvae']['decoder_dims'] = [3, 32, 128, 128, 256, 512]
+config['cvae']['decoder_dims'] = config['cvae']['encoder_dims']
-config['cvae']['decoder_weights_depths'] = [3, 9, 3, 3, 3]
+
-config['cvae']['decoder_weights_dims'] = [24, 32, 64, 128, 256]
 
 config['cond_ae_static'] = dict()
 config['cond_ae_static']['is_label'] = False