luni/cvpr
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

started training pyramid

Browse Source
This commit is contained in:
luni
2023-02-26 22:25:50 +00:00
parent a678724711
commit 64ecb900f5
8 changed files with 314 additions and 79 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cvae_pyramid.py
+29 -21
View File
@@ -1,6 +1,6 @@
import os
import sys
from configs.post.config_abl_pyr_64_128_5 import config
from configs.iccv.config_abl_pyr_32 import config
os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
import tensorflow as tf
@@ -43,10 +43,11 @@ from dataset import DatasetFactory, StaticDataset
from custom_utils.smpl import SMPL
from models.pyramid_model_optimized import PyramidNew as Pyramid
from postprocessing import fix_collision
from custom_utils.custom_utils import Accumulator
def init_wandb():
run = wandb.init(project='ablation', name=config['name'], notes=config['notes'], dir='/wandb', tags=config['tags'])
run = wandb.init(project='iccv', name=config['name'], notes=config['notes'], dir='/tmp', tags=config['tags'])
artifact = wandb.Artifact('code', type='code')
artifact.add_file('cvae_pyramid.py')
@@ -61,11 +62,14 @@ 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.post.')]
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'])
def plot_3d(mesh_gt, mesh_pred_unposed_levels, faces, mesh_posed, collision, collision_faces, collision_color):
fig = make_subplots(rows=1, cols=1+len(mesh_pred_unposed_levels)+1+1, start_cell="top-left", specs = [ [{ 'type': 'scene' } for _ in range(1+len(mesh_pred_unposed_levels)+1+1)] ])
@@ -791,6 +795,8 @@ if __name__ == '__main__':
ckpt = tf.train.Checkpoint(model=model)
manager = tf.train.CheckpointManager(ckpt, 'checkpoints/post/' + config['name'], max_to_keep=20)
train_accumulator = Accumulator()
valid_accumulator = Accumulator()
# load_model(model, 'checkpoints/pyr_abl_32_skirt', iteration='180000')
@@ -846,31 +852,33 @@ if __name__ == '__main__':
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)
if step % 50 == 0:
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 % 5000 == 0 or (step < 5000 and step % 500 == 0):
train_figs = plot_everything(batch, 'train')
valid_figs = plot_everything(data_valid, 'valid')
to_log = { **to_log, **train_figs, **valid_figs }
if step % 5000 == 0:
manager.save(checkpoint_number=step)
if step == 0:
to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
if train_loss['train/euclid_error'] < 0.004:
if train_loss['train/euclid_error'] < 0.015:
if balancing_activated_step == 0:
balancing_activated_step = step
balancing_coeff = balancing_coeff + 1 / 20000
if step % 1000 == 0 or (step < 1000 and step % 100 == 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)) } }
to_log = { **to_log, **{ 'train/balancing_coeff': balancing_coeff, 'train/gamma': gamma } }
wandb.log(to_log, step = step)
to_log = { **to_log, **{ 'train/balancing_coeff': balancing_coeff, 'train/gamma': gamma } }
wandb.log(to_log, step=step)
train_accumulator.reset()
valid_accumulator.reset()
print(step)