ae body training

configs/ae_body_1.py

@@ -0,0 +1,72 @@
+from utils.convnext_utils import CNBlockConfig
+
+config = dict()
+
+config['gpu'] = '1'
+config['name'] = 'body_torch_1'
+config['notes'] = ' ' 
+config['tags'] = ['torch', 'body'] 
+
+config['pretrained_model'] = ''
+
+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'] = False
+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'] = 16 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 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'] = 0.0001
+config['cond_ae']['upscale_output'] = False
+
+config['signature'] = { 'id',
+                        'frame_nr',
+                        'pose_shape',
+                        'uv_body_posed',
+                        'mesh_mask',
+                        'mesh_body_posed',
+                        }

models/base.py

@@ -1,6 +1,6 @@
 import torch
 from torch import nn
-from models.convnext import ConvNeXt, CNBlock, CNBlockConfig
+from models.convnext_orig import ConvNeXt, CNBlock, CNBlockConfig
 from typing import Any, Callable, List, Optional, Sequence
 
 

scripts/ae_body_train.py

@@ -0,0 +1,203 @@
+import os
+import sys
+sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/..')
+
+from configs.ae_body_1 import config
+os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID"
+os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
+
+
+import time
+import argparse
+import wandb
+import random
+import numpy as np
+import torch
+import cv2
+# 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
+
+if config['is_skirt']:
+    from losses.losses import edge_loss_skirt as edge_loss
+else:
+    from losses.losses import edge_loss
+
+from data.dataset import Dataset
+# 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, 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', tags=config['tags'])
+    artifact = wandb.Artifact('code', type='code')
+    artifact.add_file('scripts/ae_body_train.py')
+    artifact.add_file('losses/losses.py')
+    artifact.add_file('models/base.py')
+    artifact.add_file('models/cond_encoder.py')
+    artifact.add_file('models/convnext.py')
+    artifact.add_file('data/dataset.py')
+    config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.')]
+    for config_file_name in config_file_names:
+        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 train_step(batch):
+    model.train()
+    pred = model([batch['uv_body_posed'], uv_mask_body])
+
+    ms_ssim = torch.mean(_MSSSIM(pred + 1, batch['uv_body_posed'] + 1))
+    loss = 1e3 * (1 - ms_ssim)
+
+    optimizer.zero_grad()
+    loss.backward()
+    optimizer.step()
+
+    model.eval()
+    with torch.inference_mode():
+        mesh_pred = uv2mesh(pred)
+        mesh_orig = batch['mesh_body_posed']
+        l1_loss = torch.mean(torch.sum((torch.abs(batch['uv_body_posed'] - pred)), axis=1))
+        e_loss = 1e-2 * torch.mean(edge_loss(mesh_pred, mesh_orig, torch.ones((pred.shape[0], 3638 if config['is_cape'] else 14475), device=pred.get_device())))
+        metric = torch.mean(torch.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred) ** 2, axis=-1)))
+    
+    return { 'train/loss': loss, 'train/edge_loss': e_loss, 'train/l1_loss': l1_loss, 'train/euclid_error': metric, 'train/ms_ssim': ms_ssim, }
+        
+
+def valid_step(batch):
+    model.eval()
+
+    with torch.inference_mode():
+        pred = model([batch['uv_body_posed'], uv_mask_body])
+
+        mesh_pred = uv2mesh(pred)
+        mesh_orig = batch['mesh_body_posed']
+
+        e_loss = 1e-2 * torch.mean(edge_loss(mesh_pred, mesh_orig, torch.ones((pred.shape[0], 3638 if config['is_cape'] else 14475), device=pred.get_device())))
+        l1_loss = torch.mean(torch.sum((torch.abs(batch['uv_body_posed'] - pred)), axis=1))
+        ms_ssim = torch.mean(_MSSSIM(pred + 1, batch['uv_body_posed'] + 1))
+        loss = 1e3 * (1 - ms_ssim)
+
+        metric = torch.mean(torch.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred) ** 2, axis=-1)))
+    
+    return { 'valid/loss': loss, 'valid/edge_loss': e_loss, 'valid/l1_loss': l1_loss, 'valid/euclid_error': metric, 'valid/ms_ssim': ms_ssim, }
+       
+
+def plot_everything(batch: dict, type: str):
+    model.eval()
+    pred = model([batch['uv_body_posed'], uv_mask_body]).detach()
+    
+    mesh_pred = uv2mesh(pred)
+    mesh_orig = batch['mesh_body_posed']
+    
+    orig_img = torch.permute(batch['uv_body_posed'], [0,2,3,1])
+    pred_img = torch.permute(pred, [0,2,3,1])
+    img = torch.concat((orig_img, pred_img), axis=2)
+    imgs = [wandb.Image((img[i].cpu().numpy() + 1) / 2.0) for i in range(4)]
+
+    F = np.load("smpl/smpl_faces" + skirt_modifier + ("_orig" if config['is_cape'] else "") + ".npy")
+    garment_unposed, faces = mesh_pred.cpu().numpy(), F
+    gt = [mesh_orig[i].cpu().numpy() for i in range(pred.shape[0])]
+    
+    body = uv2mesh(batch['uv_body_posed']).cpu().numpy()
+    garment_posed = garment_unposed
+    collision = [np.concatenate((body[i], garment_posed[i]), axis=0) for i in range(len(garment_posed))]
+    collision_faces = [np.concatenate((F, faces + (3638 if config['is_cape'] else 14475)), axis=0) for i in range(len(garment_posed))]
+    collision_color = [np.concatenate((np.ones_like(body[i], dtype=np.int32)*100, np.ones_like(garment_posed[i], dtype=np.int32)*230), axis=0) for i in range(len(garment_posed))]
+
+    figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], faces, collision[i], collision_faces[i], collision_color[i]) for i in range(4) }
+    
+    return { **figs, **{ type + '/images': imgs } }
+
+
+def train():
+    valid_iterator = iter(valid_dataloader)
+
+    step = 0
+    for batch in train_dataloader:
+        train_loss = train_step(batch)
+        train_accumulator.update(train_loss)
+
+        if step % 25 == 0:
+            data_valid = next(valid_iterator)
+            valid_loss = valid_step(data_valid)
+            valid_accumulator.update(valid_loss)
+
+        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)) } }
+
+            wandb.log(to_log, step=step)
+            train_accumulator.reset()
+            valid_accumulator.reset()
+            print(step)
+
+        if step % 10000 == 0:
+            ckpt_saver_enc(model.encoder, step, optimizer)
+            ckpt_saver_dec(model.decoder, step, optimizer)
+
+        step += 1
+
+
+if __name__ == '__main__':
+    init_wandb()
+    # device = "cuda" if torch.cuda.is_available() else "cpu"
+
+    parser = argparse.ArgumentParser(description='')
+    parser.add_argument('--name', type=str)
+    args = vars(parser.parse_args())
+    
+    resolution_modifier = ''
+    if config['resolution'] != 512:
+        resolution_modifier = '_' + str(config['resolution'])
+    skirt_modifier = '_skirt' if config['is_skirt'] else ''
+
+    uv_mask_body = np.load('custom_utils/mask_256x512' + ('_skirt' if config['is_skirt'] else '') + '.npy')
+    uv_mask_body = cv2.dilate(uv_mask_body.astype(np.float32), cv2.getStructuringElement(cv2.MORPH_RECT, (2 * 2 + 1, 2 * 2 + 1), (2, 2)), iterations=2)
+    uv_mask_body = torch.from_numpy(uv_mask_body).float().to(config['device'])
+
+    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 = 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=5)
+    ckpt_saver_dec = CheckpointSaver('checkpoints/iccv/' + config['name'] + '_dec', top_n=5)
+
+    run_name = config['name']
+    print(f'started training: {run_name}')
+    train()
+
+
+