luni/cvpr_2023
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

working static ae training

Browse Source
This commit is contained in:
luni
2023-04-06 17:25:57 +00:00
parent 31c2194a4e
commit b4be8bf80d
5 changed files with 172 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
configs/ae_static.py
+3 -2
View File
@@ -2,11 +2,13 @@ from utils.convnext_utils import CNBlockConfig
config = dict()
config['gpu'] = '5'
config['gpu'] = '1'
config['name'] = 'static_torch_1'
config['notes'] = ' '
config['tags'] = ['torch', 'static']
config['pretrained_model'] = 'checkpoints/iccv/static_torch_1'
config['batch_size'] = 4
config['train_dir'] = '/data-local/127/train'
config['valid_dir'] = '/data-local/127/valid'
@@ -60,7 +62,6 @@ config['cond_ae']['activation'] = 'tanh'
config['lr'] = 0.0005
config['cond_ae']['upscale_output'] = False
config['pretrained_model'] = ''
config['signature'] = { 'id',
'frame_nr',
configs/ae_static_orig.py
+71
View File
@@ -0,0 +1,71 @@
from utils.convnext_utils import CNBlockConfig
config = dict()
config['gpu'] = '2'
config['name'] = 'static_torch_orig_1'
config['notes'] = ' '
config['tags'] = ['torch', 'static']
config['batch_size'] = 4
config['train_dir'] = '/data-local/127/train'
config['valid_dir'] = '/data-local/127/valid'
config['test_dir'] = '/data-net/dataset/test_ready'
config['train_frames'] = None
config['valid_frames'] = None
config['resolution'] = 512
config['is_skirt'] = False
config['dataset_in_memory'] = True
config['is_cape'] = False
config['remove_global_orientation'] = True
config['device'] = 'cuda'
config['smpl_res'] = 14475
if config['is_cape']:
config['smpl_res'] = 3638
config['latent_dim'] = 128
config['bottleneck_scale'] = 2
config['cond_ae'] = dict()
config['cond_ae']['device'] = config['device']
config['cond_ae']['is_label'] = False
config['cond_ae']['latent_dim'] = config['latent_dim']
config['cond_ae']['kernel_size'] = 7
config['cond_ae']['bottleneck_size'] = 8 * config['bottleneck_scale']
block_setting = [
CNBlockConfig(8, 16, 3),
CNBlockConfig(16, 32, 3),
CNBlockConfig(32, 64, 3),
CNBlockConfig(64, config['cond_ae']['bottleneck_size'], 27),
CNBlockConfig(config['cond_ae']['bottleneck_size'], None, 3),
]
block_setting_reverse = [
CNBlockConfig(config['cond_ae']['bottleneck_size'], 64, 3),
CNBlockConfig(64, 32, 27),
CNBlockConfig(32, 16, 3),
CNBlockConfig(16, 8, 3),
CNBlockConfig(8, 3, 3),
# CNBlockConfig(3, 3, 3),
]
config['cond_ae']['encoder_block_settings'] = block_setting
config['cond_ae']['decoder_block_settings'] = block_setting_reverse
config['cond_ae']['activation'] = 'tanh'
config['lr'] = 0.0005
config['cond_ae']['upscale_output'] = False
config['pretrained_model'] = ''
config['signature'] = { 'id',
'frame_nr',
'uv_static',
'mesh_static',
'mesh_mask',
'uv_mask',
}
configs/ae_static_orig_2.py
+71
View File
@@ -0,0 +1,71 @@
from utils.convnext_utils import CNBlockConfig
config = dict()
config['gpu'] = '3'
config['name'] = 'static_torch_orig_2'
config['notes'] = ' '
config['tags'] = ['torch', 'static']
config['batch_size'] = 4
config['train_dir'] = '/data-local/127/train'
config['valid_dir'] = '/data-local/127/valid'
config['test_dir'] = '/data-net/dataset/test_ready'
config['train_frames'] = None
config['valid_frames'] = None
config['resolution'] = 512
config['is_skirt'] = False
config['dataset_in_memory'] = True
config['is_cape'] = False
config['remove_global_orientation'] = True
config['device'] = 'cuda'
config['smpl_res'] = 14475
if config['is_cape']:
config['smpl_res'] = 3638
config['latent_dim'] = 128
config['bottleneck_scale'] = 2
config['cond_ae'] = dict()
config['cond_ae']['device'] = config['device']
config['cond_ae']['is_label'] = False
config['cond_ae']['latent_dim'] = config['latent_dim']
config['cond_ae']['kernel_size'] = 7
config['cond_ae']['bottleneck_size'] = 8 * config['bottleneck_scale']
block_setting = [
CNBlockConfig(8, 16, 3),
CNBlockConfig(16, 32, 3),
CNBlockConfig(32, 64, 3),
CNBlockConfig(64, config['cond_ae']['bottleneck_size'], 9),
CNBlockConfig(config['cond_ae']['bottleneck_size'], None, 3),
]
block_setting_reverse = [
CNBlockConfig(config['cond_ae']['bottleneck_size'], 64, 3),
CNBlockConfig(64, 32, 9),
CNBlockConfig(32, 16, 3),
CNBlockConfig(16, 8, 3),
CNBlockConfig(8, 3, 3),
# CNBlockConfig(3, 3, 3),
]
config['cond_ae']['encoder_block_settings'] = block_setting
config['cond_ae']['decoder_block_settings'] = block_setting_reverse
config['cond_ae']['activation'] = 'tanh'
config['lr'] = 0.0005
config['cond_ae']['upscale_output'] = False
config['pretrained_model'] = ''
config['signature'] = { 'id',
'frame_nr',
'uv_static',
'mesh_static',
'mesh_mask',
'uv_mask',
}
models/base.py
+2 -1
View File
@@ -69,7 +69,8 @@ class Decoder(nn.Module):
self.decoder = ConvNeXt(block_setting=block_setting, kernel_size=kernel_size, is_label=is_label, nr_of_labels=nr_of_classes, device=device, reversed=True)
self.softmax = nn.Softmax(dim=1)
if self.is_label:
self.softmax = nn.Softmax(dim=1)
def forward(self, inputs):
if len(inputs) == 2:
scripts/ae_static_train.py
+25 -22
View File
@@ -13,9 +13,8 @@ import wandb
import random
import numpy as np
import torch
from torch import nn
from torchmetrics import MultiScaleStructuralSimilarityIndexMeasure as MSSSIM
from custom_utils.custom_utils import UV2Mesh, get_summary_html, load_model, maskFacesBatch, get_summary_str
# from torchmetrics import MultiScaleStructuralSimilarityIndexMeasure as MSSSIM
from custom_utils.custom_utils import UV2Mesh, get_summary_html, maskFacesBatch, get_summary_str
import plotly.graph_objects as go
import plotly.express as ex
import torch.optim as optim
@@ -26,15 +25,18 @@ else:
from losses.losses import edge_loss
from data.dataset import Dataset
from torch.utils.data import DataLoader
from custom_utils.custom_utils import batch_to_dict, plot_3d
# from torch.utils.data import DataLoader
from custom_utils.custom_utils import plot_3d
from models.cond_encoder import AutoEncoder
from utils.checkpoints import CheckpointSaver
from utils.checkpoints import CheckpointSaver, load_model
from custom_utils.custom_utils import Accumulator
from utils.utils import InfiniteDataLoader as DataLoader
from pytorch_msssim import MS_SSIM
def init_wandb():
run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/data-local/127/temp/wandb', tags=config['tags'])
run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/data-local/127/temp', tags=config['tags'])
artifact = wandb.Artifact('code', type='code')
artifact.add_file('scripts/ae_static_train.py')
artifact.add_file('losses/losses.py')
@@ -57,19 +59,21 @@ def train_step(batch):
model.train()
pred = model([batch['uv_static'], batch['uv_mask']])
mesh_pred = uv2mesh(pred)
mesh_orig = batch['mesh_static']
e_loss = 1e-2 * torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
l1_loss = torch.mean(torch.sum((torch.abs(batch['uv_static'] - pred)), axis=1))
ms_ssim = torch.mean(_MSSSIM(pred + 1, batch['uv_static'] + 1))
loss = 1e3 * (1 - ms_ssim)
# loss = l1_loss
optimizer.zero_grad()
loss.backward()
optimizer.step()
metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred.detach()) ** 2, axis=-1))) / torch.sum(batch['mesh_mask'])
model.eval()
with torch.inference_mode():
mesh_pred = uv2mesh(pred)
mesh_orig = batch['mesh_static']
l1_loss = torch.mean(torch.sum((torch.abs(batch['uv_static'] - pred)), axis=1))
e_loss = 1e-2 * torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred.detach()) ** 2, axis=-1))) / torch.sum(batch['mesh_mask'])
return { 'train/loss': loss, 'train/edge_loss': e_loss, 'train/l1_loss': l1_loss, 'train/euclid_error': metric, 'train/ms_ssim': ms_ssim, }
@@ -151,8 +155,6 @@ def train():
ckpt_saver_enc(model.encoder, step, optimizer)
ckpt_saver_dec(model.decoder, step, optimizer)
print(step)
step += 1
@@ -170,24 +172,25 @@ if __name__ == '__main__':
skirt_modifier = '_skirt' if config['is_skirt'] else ''
# dataset = Dataset('/data-local/127/train', config['signature'], resolutions=[512], device=device, frames_file='frames_jumpsuit.txt')
dataset_train = Dataset(config['train_dir'], config['signature'], device=config['device'], frames_file=config['train_frames'])
dataset_valid = Dataset(config['valid_dir'], config['signature'], device=config['device'], frames_file=config['valid_frames'])
train_dataloader = DataLoader(dataset_train, batch_size=4, drop_last=True, shuffle=False)
valid_dataloader = DataLoader(dataset_valid, batch_size=4, drop_last=True, shuffle=False)
dataset_train = Dataset(config['train_dir'], config['signature'], device=config['device'], frames_file=config['train_frames'], use_cache=config['dataset_in_memory'])
dataset_valid = Dataset(config['valid_dir'], config['signature'], device=config['device'], frames_file=config['valid_frames'], use_cache=config['dataset_in_memory'])
train_dataloader = DataLoader(dataset_train, batch_size=4, drop_last=True, shuffle=True, )
valid_dataloader = DataLoader(dataset_valid, batch_size=4, drop_last=True, shuffle=True)
train_accumulator = Accumulator()
valid_accumulator = Accumulator()
model : AutoEncoder = AutoEncoder(config['cond_ae'])
optimizer = optim.Adam(model.parameters(), lr=config['lr'])
_MSSSIM = MSSSIM(data_range=2).to(config['device'])
# _MSSSIM = MSSSIM(data_range=2).to(config['device'])
_MSSSIM = MS_SSIM(data_range=2, size_average=True, channel=3)
if config['pretrained_model'] != '':
load_model(model.encoder, config['pretrained_model'] + '_enc')
load_model(model.decoder, config['pretrained_model'] + '_dec')
ckpt_saver_enc = CheckpointSaver('checkpoints/iccv/' + config['name'] + '_enc', top_n=20)
ckpt_saver_dec = CheckpointSaver('checkpoints/iccv/' + config['name'] + '_dec', top_n=20)
ckpt_saver_enc = CheckpointSaver('checkpoints/iccv/' + config['name'] + '_enc', top_n=5)
ckpt_saver_dec = CheckpointSaver('checkpoints/iccv/' + config['name'] + '_dec', top_n=5)
run_name = config['name']
print(f'started training: {run_name}')