diff --git a/scripts/cvae_norm.py b/scripts/cvae_norm.py index 2a305dc..e1cf73e 100644 --- a/scripts/cvae_norm.py +++ b/scripts/cvae_norm.py @@ -12,7 +12,7 @@ args = vars(parser.parse_args()) if args['debug']: - from configs.iccvw.cvae_norm_1 import config + from configs.iccvw.cvae_norm_5 import config else: config_module = importlib.import_module(args['config']) config = config_module.config @@ -28,6 +28,7 @@ import wandb import tqdm import random import numpy as np +import kaleido import plotly.graph_objects as go import plotly.express as ex from PIL import Image @@ -93,7 +94,7 @@ def train_step(batch): kl = kl_loss(mean, logvar) reconstr_loss = l2_loss + l2_mesh_loss + (1 - ms_ssim) - loss = reconstr_loss + g_balancing_coeff * kl + loss: torch.Tensor = reconstr_loss + g_balancing_coeff * kl optimizer.zero_grad() loss.backward() @@ -164,125 +165,6 @@ def plot_everything(batch: dict, type: str): return { **{ type + '/images': imgs, type + '/mean_hist': mean_hist, type + '/logvar_hist': logvar_hist } } -def sample(folder): - # run = wandb.init(project='vae_plots', name=folder.split('/')[-1]) - load_model(model,folder) - count = 0 - for batch in dataset_train: - batch = static_dataset_train.expand_batch(batch_to_dict(batch, config['signature_dynamic'])) - uv_normals = tf.one_hot(batch['uv_normals'], 7) - nr_of_samples=2 - - pred = model.sample_single(batch['uv_static'][0], batch['uv_body_posed'][0], uv_normals[0], batch['uv_mask'][0], nr_of_samples=nr_of_samples) - pose, shape = batch['pose_shape'][0, :72], batch['pose_shape'][0, 72:] - pose, shape = tf.tile(pose[tf.newaxis,:], [nr_of_samples,1]), tf.tile(shape[tf.newaxis,:], [nr_of_samples,1]) - - mesh_pred = uv2mesh(pred) - mesh_posed = smpl.run_garment(pose, shape, mesh_pred).numpy() - mesh_orig = batch['mesh_posed'][0].numpy() - mesh_orig_reposed = smpl.run_garment(pose[:1], shape[:1], batch['mesh_unposed'][:1]).numpy()[0] - - body = batch['mesh_body_posed'][0].numpy() - body_color = np.ones_like(body, dtype=np.int32)*100 - - F = np.load("custom_utils/smpl_faces.npy") - mask = batch['mesh_mask'].numpy().astype(bool)[0] - _, faces = _maskFaces(np.ones((config['smpl_res'], 3)), F, mask) - - pred_zero = model.sample_single(batch['uv_static'][0], batch['uv_body_posed'][0], uv_normals[0], batch['uv_mask'][0], nr_of_samples=nr_of_samples, zero_latent=True) - mesh_pred_zero = uv2mesh(pred_zero) - mesh_posed_zero = smpl.run_garment(pose, shape, mesh_pred_zero).numpy() - - - meshes = [] - meshes.append(go.Mesh3d( - # 8 vertices of a cube - x=mesh_orig_reposed[mask,0], - y=mesh_orig_reposed[mask,2], - z=mesh_orig_reposed[mask,1], - # i, j and k give the vertices of triangles - i = faces[:,0], - j = faces[:,1], - k = faces[:,2] - )) - - for i in range(nr_of_samples): - x = mesh_posed[i][mask, :].copy() - # x[:, 2] += 1 * (i + 1) - x[:, 2] += 1 - meshes.append(go.Mesh3d( - # 8 vertices of a cube - x=x[:,0], - y=x[:,2], - z=x[:,1], - # i, j and k give the vertices of triangles - i = faces[:,0], - j = faces[:,1], - k = faces[:,2] - )) - - - for i in range(nr_of_samples): - x = mesh_posed_zero[i][mask, :].copy() - # x[:, 2] += 1 * (i + 1) - x[:, 2] += 2 - meshes.append(go.Mesh3d( - # 8 vertices of a cube - x=x[:,0], - y=x[:,2], - z=x[:,1], - # i, j and k give the vertices of triangles - i = faces[:,0], - j = faces[:,1], - k = faces[:,2] - )) - - # for i in range(5): - # x = body.copy() - # x[:, 2] += 1 * i - # meshes.append(go.Mesh3d( - # # 8 vertices of a cube - # x=x[:,0], - # y=x[:,2], - # z=x[:,1], - # # i, j and k give the vertices of triangles - # i = F[:,0], - # j = F[:,1], - # k = F[:,2], - # vertexcolor=body_color - # )) - - - fig = go.Figure(data=meshes) - - fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=2, z=1)) - # fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=nr_of_samples-1, z=1)) - fig.update_layout( - scene = dict( - xaxis = dict(nticks=4, range=[-1,1],), - # yaxis = dict(nticks=4, range=[-1,nr_of_samples+1],), - yaxis = dict(nticks=4, range=[-1,3],), - zaxis = dict(nticks=4, range=[-1,1],),) - ) - - # wandb.log({'plot_' + str(count): fig}) - fig.show() - - pred = pred.numpy() - frames = [Image.fromarray(((pred[i] + 1) * 128).astype(np.int8), mode='RGB') for i in range(pred.shape[0])] - frames[0].save("temp/garment_1.gif", format="GIF", append_images=frames[1:], - save_all=True, duration=500, loop=0) - - - if count > 10: - break - - print(count) - count += 1 - - print() - - def train(): global g_balancing_coeff @@ -314,7 +196,7 @@ def train(): print(step) if train_loss['train/euclid_error'] < config['balancing_activation_limit']: - g_balancing_coeff += 1 / 10000 + g_balancing_coeff += 1 / 2000 if step % 20000 == 0: ckpt_saver(model, step, optimizer, None) @@ -322,6 +204,49 @@ def train(): step += 1 + +def sample(): + model.eval() + load_model(model, f'checkpoints/iccvw/{config["name"]}') + count = 0 + + for batch in train_dataloader: + uv_static = batch['uv_static'] + uv_body_posed = batch['uv_body_posed'] + uv_mask = batch['uv_mask'] + + batch_size = uv_static.size(0) + + for i in range(batch_size): + uv_static_tiled = uv_static[i][None,:,:,:].repeat(4, 1, 1, 1) + uv_body_posed_tiled = uv_body_posed[i][None,:,:,:].repeat(4, 1, 1, 1) + uv_mask_tiled = uv_mask[i][None,:,:].repeat(4, 1, 1) + + with torch.inference_mode(): + pred = model.sample(uv_static_tiled, uv_body_posed_tiled, uv_mask_tiled) + + pred = pred * 1.4 + + pred = pred.cpu().numpy().transpose(0, 2, 3, 1) + pred = (pred + 1.4) / 2.8 + pred = pred * uv_mask_tiled[:,:,:,None].cpu().numpy() + gt = (batch['uv_normals'][i].cpu().numpy().transpose(1, 2, 0) + 1.4) / 2.8 * uv_mask_tiled[0,:,:,None].cpu().numpy() + img = np.concatenate(pred, axis=1) + img = np.concatenate([gt, img], axis=1) + # flip image along its shorter edge + img = img[::-1,:,:] + + fig = ex.imshow(img) + fig.update_layout(margin=dict(l=0, r=0, b=0, t=0, pad=0), width=img.shape[1], height=img.shape[0]) + fig.update_xaxes(visible=False) + fig.update_yaxes(visible=False) + fig.write_image(f'temp/normals/{batch["id"][i]}_{batch["frame_nr"][i].cpu().numpy()}_{batch["garment"][i]}.png') + count += 1 + + if count > 100: + break + + if __name__ == '__main__': if not args['debug']: init_wandb() @@ -338,6 +263,10 @@ if __name__ == '__main__': model = CVAENorm(config) + sample() + exit() + + optimizer = optim.Adam(model.parameters(), lr=config['lr']) _MSSSIM = MS_SSIM(data_range=2, size_average=True, channel=3) g_balancing_coeff = config['starting_balancing_coeff'] diff --git a/scripts/cvae_pyramid.py b/scripts/cvae_pyramid.py index f2b99fc..4b36b5c 100644 --- a/scripts/cvae_pyramid.py +++ b/scripts/cvae_pyramid.py @@ -11,7 +11,7 @@ parser.add_argument('--debug', action='store_true') args = vars(parser.parse_args()) if args['debug']: - from configs.iccvw.pyr_64_128_256_512_cape_f import config + from configs.iccvw.pyr_64_cape_f_skin import config else: config_module = importlib.import_module(args['config']) config = config_module.config diff --git a/scripts/cvae_pyramid_e2e.py b/scripts/cvae_pyramid_e2e.py new file mode 100644 index 0000000..a7d7215 --- /dev/null +++ b/scripts/cvae_pyramid_e2e.py @@ -0,0 +1,570 @@ +import os +import sys +sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/..') + +import importlib +import argparse +parser = argparse.ArgumentParser(description='') +parser.add_argument('--name', type=str) +parser.add_argument('--config', type=str) +parser.add_argument('--debug', action='store_true') +args = vars(parser.parse_args()) + +if args['debug']: + from configs.iccvw.pyr_64_128_256_512_cape_m_e2e import config +else: + config_module = importlib.import_module(args['config']) + config = config_module.config + +os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID" +os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu'] +if args['debug']: + os.environ["CUDA_LAUNCH_BLOCKING"] = '1' + +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 + +if config['is_skirt']: + from losses.losses import edge_loss_skirt as edge_loss +else: + from losses.losses import edge_loss + +import torch +import torch.nn as nn +import torch.optim as optim +import torch.nn.functional as F +from torchvision.transforms import Resize +from torchvision.transforms.functional import InterpolationMode +from data.dataset import Dataset +from utils.checkpoints import CheckpointSaver, load_model +from utils.utils import InfiniteDataLoader as DataLoader +from utils.utils import text_to_html +from utils.postprocess import fix_collision +from losses.losses import collision_loss, normal_loss, kl_loss +from pytorch_msssim import MS_SSIM +from custom_utils.custom_utils import UV2Mesh, Accumulator, plot_3d, get_summary_html, maskFacesBatch, get_summary_str, plot_3d_collision, group_inputs_for_levels +from smpl.smpl_torch import SMPL +from plotly.subplots import make_subplots +from models.pyramid_model import Pyramid + + +def init_wandb(): + wandb.login(host='https://wandb2.lnrweb.com', key='local-2a78b434e9bc51e9f12625f8321a9e3ee34af16d', relogin=True, force=True) + run = wandb.init(project='iccvw', name=config['name'], notes=config['notes'], dir='/data-local/127/temp', tags=config['tags']) + artifact = wandb.Artifact('code', type='code') + artifact.add_file('scripts/cvae_pyramid_e2e.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('models/pyramid_model.py') + artifact.add_file('models/pyramid_level.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 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)] ]) + + 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" + ), + row=1, col=1) + + for i, mesh in enumerate(mesh_pred_unposed_levels): + fig.add_trace(go.Mesh3d( + x=mesh[:,0], + y=mesh[:,2], + z=mesh[:,1], + i = faces[:,0], + j = faces[:,1], + k = faces[:,2], + text='Unposed level_' + str(i) + ), + row=1, col=i+2) + + fig.add_trace(go.Mesh3d( + x=mesh_posed[:,0], + y=mesh_posed[:,2], + z=mesh_posed[:,1], + i = faces[:,0], + j = faces[:,1], + k = faces[:,2], + text='Posed GT' + ), + row=1, col=1+len(mesh_pred_unposed_levels)+1) + + fig.add_trace(go.Mesh3d( + x=collision[:,0], + y=collision[:,2], + z=collision[:,1], + i = collision_faces[:,0], + j = collision_faces[:,1], + k = collision_faces[:,2], + vertexcolor=collision_color, + text='Posed output on body' + ), + row=1, col=1+len(mesh_pred_unposed_levels)+1+1) + + if len(mesh_pred_unposed_levels) == 1: + 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), + scene4_aspectmode='manual', scene4_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, + scene4 = helper, + ) + if len(mesh_pred_unposed_levels) == 2: + 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), + scene4_aspectmode='manual', scene4_aspectratio=dict(x=1, y=1, z=1), + scene5_aspectmode='manual', scene5_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, + scene4 = helper, + scene5 = helper, + ) + if len(mesh_pred_unposed_levels) == 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), + scene4_aspectmode='manual', scene4_aspectratio=dict(x=1, y=1, z=1), + scene5_aspectmode='manual', scene5_aspectratio=dict(x=1, y=1, z=1), + scene6_aspectmode='manual', scene6_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, + scene4 = helper, + scene5 = helper, + scene6 = helper, + ) + if len(mesh_pred_unposed_levels) == 4: + 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), + scene4_aspectmode='manual', scene4_aspectratio=dict(x=1, y=1, z=1), + scene5_aspectmode='manual', scene5_aspectratio=dict(x=1, y=1, z=1), + scene6_aspectmode='manual', scene6_aspectratio=dict(x=1, y=1, z=1,), + scene7_aspectmode='manual', scene7_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, + scene4 = helper, + scene5 = helper, + scene6 = helper, + scene7 = helper, + ) + if len(mesh_pred_unposed_levels) == 5: + 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), + scene4_aspectmode='manual', scene4_aspectratio=dict(x=1, y=1, z=1), + scene5_aspectmode='manual', scene5_aspectratio=dict(x=1, y=1, z=1), + scene6_aspectmode='manual', scene6_aspectratio=dict(x=1, y=1, z=1,), + scene7_aspectmode='manual', scene7_aspectratio=dict(x=1, y=1, z=1,), + scene8_aspectmode='manual', scene8_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, + scene4 = helper, + scene5 = helper, + scene6 = helper, + scene7 = helper, + scene8 = helper, + ) + return fig + + +def train_step(batch): + if config['is_cape']: + batch['mesh_fix'] = {'mesh_mask': batch['mesh_mask']} + + model.train() + # with torch.autocast(device_type='cuda', dtype=torch.float16, enabled=use_amp): + levels_input, conds = group_inputs_for_levels(batch, config) + + out_levels = model([levels_input, conds]) + + if config['use_skinning']: + mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed'] + else: + mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed'] + + output = dict() + reconstr_loss_total = 0 + kl_total = 0 + posed_or_not = 'unposed' if config['use_skinning'] else 'posed' + + for i, res in enumerate(config['pyramid']['resolutions']): + # i = -1 + res = config['pyramid']['resolutions'][i] + res_modifier = '_' + str(res) if res != 512 else '' + pred, mean, logvar = out_levels[i] + if res != 512: + pred = resizer(pred) * batch['uv_mask'][:,None,:,:] + + l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((uv_orig - pred) ** 2), dim=-1), dim=[1, 2])) # levels_input[i][0] = uv_orig + kl = kl_loss(mean, logvar) + + mesh_pred = uv2mesh(pred) + + if config['use_skinning']: + shape = batch['pose_shape'][:, 72:] + gender = torch.greater_equal(shape[:, 10] , 0.5).to(dtype=torch.int64) + shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])]) + + mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_fix']['mesh_mask'][:,:,None] + mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0] + else: + mesh_pred_posed = mesh_pred + + e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_fix']['mesh_mask'])) + c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_fix']['mesh_mask']) + c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio) + n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_fix']['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape']) + l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_fix']['mesh_mask'][:,:,None] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, dim=-1), dim=-1)) + + reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss) + if not config['is_cape']: + reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] + if config['use_norm_loss'] and step > 2000: + reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * n_loss * config['reg_loss_coeff'] + + kl_total += kl + loss: torch.Tensor = reconstr_loss_total + g_balancing_coeff * kl_total + + optimizer.zero_grad() + loss.backward() + optimizer.step() + + model.eval() + with torch.inference_mode(): + mean = torch.mean(mean) + logvar = torch.mean(logvar) + + ms_ssim = torch.mean(_MSSSIM(pred + 1, uv_orig + 1)) + metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_fix']['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred.detach()) ** 2, axis=-1))) / torch.sum(batch['mesh_fix']['mesh_mask']) + + output = { **output, **{ 'train/edge_loss' + res_modifier: e_loss, 'train/collision_loss' + res_modifier: c_loss,'train/euclid_error' + res_modifier: metric, + 'train/mean' + res_modifier: mean, 'train/logvar' + res_modifier: logvar, 'train/kl_loss' + res_modifier: kl, + 'train/var' + res_modifier: np.e ** logvar, 'train/l2_loss' + res_modifier: l2_loss, 'train/normal_loss': n_loss, + 'train/euclid_error': metric, 'train/l2_mesh_loss': l2_mesh_loss, 'train/ms_ssim' + res_modifier: ms_ssim, + 'train/collision_ratio': c_ratio } } # + + + return { **{ 'train/loss': loss, 'train/reconstr_loss_total': reconstr_loss_total, 'train/kl_total': kl_total }, **output } + + +def valid_step(batch): + if config['is_cape']: + batch['mesh_fix'] = {'mesh_mask': batch['mesh_mask']} + + model.eval() + with torch.inference_mode(): + levels_input, conds = group_inputs_for_levels(batch, config) + + out_levels = model([levels_input, conds]) + + if config['use_skinning']: + mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed'] + else: + mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed'] + + output = dict() + reconstr_loss_total = 0 + kl_total = 0 + + for i, res in enumerate(config['pyramid']['resolutions']): + # i = -1 + res = config['pyramid']['resolutions'][i] + res_modifier = '_' + str(res) if res != 512 else '' + pred, mean, logvar = out_levels[i] + if res != 512: + pred = resizer(pred) * batch['uv_mask'][:,None,:,:] + + mesh_pred = uv2mesh(pred) + + if config['use_skinning']: + shape = batch['pose_shape'][:, 72:] + gender = torch.greater_equal(shape[:, 10] , 0.5).to(dtype=torch.int64) + shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])]) + + mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_fix']['mesh_mask'][:,:,None] + mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0] + else: + mesh_pred_posed = mesh_pred + + e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_fix']['mesh_mask'])) + c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_fix']['mesh_mask']) + c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio) + l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_fix']['mesh_mask'][:,:,None] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, dim=-1), dim=-1)) + n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_fix']['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape']) + l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((uv_orig - pred) ** 2), dim=-1), dim=[1, 2])) + + kl = kl_loss(mean, logvar) + + if config['use_extra_losses']: + reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss) + if not config['is_cape']: + reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] + if config['use_norm_loss'] and step > 2000: + reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * n_loss * config['reg_loss_coeff'] + else: + reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss) + + kl_total += kl + loss = reconstr_loss_total + g_balancing_coeff * kl_total + + mean = torch.mean(mean) + logvar = torch.mean(logvar) + + ms_ssim = torch.mean(_MSSSIM(pred + 1, uv_orig + 1)) + metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_fix']['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / torch.sum(batch['mesh_fix']['mesh_mask']) + + output = { **output, **{ 'valid/edge_loss' + res_modifier: e_loss, 'valid/collision_loss' + res_modifier: c_loss,'valid/euclid_error' + res_modifier: metric, + 'valid/mean' + res_modifier: mean, 'valid/logvar' + res_modifier: logvar, 'valid/kl_loss' + res_modifier: kl, + 'valid/var' + res_modifier: np.e ** logvar, 'valid/l2_loss' + res_modifier: l2_loss, 'valid/normal_loss': n_loss, + 'valid/euclid_error': metric, 'valid/l2_mesh_loss': l2_mesh_loss, 'valid/ms_ssim' + res_modifier: ms_ssim, } } # + + + + return { **{ 'valid/loss': loss, 'valid/reconstr_loss_total': reconstr_loss_total, 'valid/kl_total': kl_total }, **output } + + +def plot_everything(batch: dict, type: str): + if config['is_cape']: + batch['mesh_fix'] = {'mesh_mask': batch['mesh_mask']} + + if config['use_skinning']: + mesh_orig, uv_orig = batch['mesh_unposed'].cpu().numpy(), batch['uv_unposed'] + else: + mesh_orig, uv_orig = batch['mesh_posed'].cpu().numpy(), batch['uv_posed'] + + model.eval() + with torch.inference_mode(): + levels_input = group_inputs_for_levels(batch, config) + output_levels = model(levels_input) + + mesh_pred_levels = [uv2mesh(output_levels[i][0]).cpu() for i in range(len(output_levels))] + mesh_orig_posed = batch['mesh_posed'].cpu() + body = batch['mesh_body_posed'].cpu().numpy() + + # mesh_pred = torch.cat((mesh_pred[:, :, 0:1], -mesh_pred[:, :, 2:3], mesh_pred[:, :, 1:2]), dim=2) + # mesh_pred_levels = [torch.cat((mesh_pred_levels[i][:, :, 0:1], -mesh_pred_levels[i][:, :, 2:3], mesh_pred_levels[i][:, :, 1:2]), dim=2).numpy() for i in range(len(mesh_pred_levels))] + # mesh_orig_posed = torch.cat((mesh_orig_posed[:, :, 0:1], -mesh_orig_posed[:, :, 2:3], mesh_orig_posed[:, :, 1:2]), dim=2).numpy() + + orig_img = (torch.permute(uv_orig, [0,2,3,1]) + 1) / 2 + uv_static_img = (torch.permute(batch['uv_static'], [0,2,3,1]) + 1) / 2 + uv_body_posed_img = (torch.permute(batch['uv_body_posed'], [0,2,3,1]) + 1) / 2 + uv_normals = (torch.permute(batch['uv_normals'], [0,2,3,1]) + 1.4) / 2.8 + pred_img = torch.concatenate([torch.permute(model.resizers[512](output_levels[i][0]), [0,2,3,1]) for i in range(len(output_levels))], dim=2) + # pred_img = (pred_img - pred_img.min(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis]) / (pred_img.max(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis] - pred_img.min(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis]) + pred_img = (pred_img - pred_img.flatten().reshape(pred_img.shape[0], -1).min(1)[0][:,None,None,None]) / (pred_img.flatten().reshape(pred_img.shape[0], -1).max(1)[0][:,None,None,None] - pred_img.flatten().reshape(pred_img.shape[0], -1).min(1)[0][:,None,None,None]) + + img = torch.concat((uv_static_img, uv_body_posed_img, uv_normals, orig_img, pred_img), dim=2) + imgs = [wandb.Image(img[i].cpu().numpy()) for i in range(4)] + + _F = np.load("smpl/smpl_faces" + skirt_modifier + ("_orig" if config['is_cape'] else "") + ".npy") + mask = batch['mesh_fix']['mesh_mask'].cpu().numpy().astype(bool) + if 'mesh_fix' in batch and not config['is_cape']: + faces = [np.load( (dataset_train if type == 'train' else dataset_valid).folder + "/mesh_fixed/" + batch['id'][i] + '_' + batch['garment'][i] + ".npz" )['faces'] for i in range(len(batch['id']))] + else: + _, faces = maskFacesBatch(np.ones_like(mesh_orig), _F, mask) + + if config['use_skinning']: + shape = batch['pose_shape'][:, 72:] + gender = torch.greater_equal(shape[:, 10] , 0.5).to(torch.long) + shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])]).cpu().numpy() + + gt = [mesh_orig[i][mask[i], :] + shape_offsets[i, mask[i], :] for i in range(mask.shape[0])] + + mesh_unposed_shaped_levels = [[] for _ in range(mask.shape[0])] + for i in range(len(output_levels)): + mesh_unposed_shaped = [mesh_pred_levels[i][j, mask[j], :] + shape_offsets[j, mask[j]] for j in range(mask.shape[0])] + for k in range(mask.shape[0]): + mesh_unposed_shaped_levels[k].append(mesh_unposed_shaped[k]) + + # full res version + mesh_unposed_shaped_full = np.zeros((mask.shape[0], config['smpl_res'], 3), dtype=np.float32) + for i in range(mask.shape[0]): + mesh_unposed_shaped_full[i, mask[i], :] = mesh_unposed_shaped[i] + mesh_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], torch.tensor(mesh_unposed_shaped_full, device=config['device']))[0].cpu().numpy() + + # rotate gt 180 degrees along z axis + # gt = [np.matmul(gt[i], np.array([[np.cos(np.pi), -np.sin(np.pi), 0], [np.sin(np.pi), np.cos(np.pi), 0], [0, 0, 1]])) for i in range(mask.shape[0])] + + # gt_full = np.zeros((mask.shape[0], config['smpl_res'], 3), dtype=np.float32) + # for i in range(mask.shape[0]): + # gt_full[i, mask[i], :] = gt[i] + # mesh_orig_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], torch.tensor(np.stack(gt_full, axis=0), device=config['device'], dtype=torch.float32))[0].cpu().numpy() + else: + mesh_posed = mesh_pred_levels[-1] + gt = [mesh_orig[i][mask[i], :] for i in range(mesh_posed.shape[0])] + mesh_unposed_shaped_levels = [[mesh_pred_levels[i][j, mask[j], :] for i in range(len(output_levels))] for j in range(mask.shape[0])] + + + gt_posed = [mesh_orig_posed[i, mask[i], :] for i in range(mask.shape[0])] + mesh_posed_fixed = fix_collision(torch.Tensor(mesh_posed).to('cuda'), torch.Tensor(body).to('cuda'), torch.Tensor(mask).to('cuda')).cpu().numpy() + + mesh_posed = [mesh_posed[j, mask[j], :] for j in range(mask.shape[0])] + + if config['is_cape']: + collision = mesh_posed + collision_faces = faces + collision_color = [np.ones_like(mesh_posed[i], dtype=np.int32)*230 for i in range(len(mesh_posed))] + else: + collision = [np.concatenate((body[i], mesh_posed[i]), axis=0) for i in range(len(mesh_posed))] + collision_faces = [np.concatenate((_F, faces[i] + config['smpl_res']), axis=0) for i in range(len(mesh_posed))] + collision_color = [np.concatenate((np.ones_like(body[i], dtype=np.int32)*100, np.ones_like(mesh_posed[i], dtype=np.int32)*230), axis=0) for i in range(len(mesh_posed))] + + figs = { type + "/garment_" + str(i): plot_3d(gt[i], mesh_unposed_shaped_levels[i], faces[i], gt_posed[i], collision[i], collision_faces[i], collision_color[i]) for i in range(4) } + + if config['is_cape']: + figs_coll = dict() + else: + garment_posed_fixed = [mesh_posed_fixed[i, mask[i], :] for i in range(body.shape[0])] + collision_fixed = [np.concatenate((body[i], garment_posed_fixed[i]), axis=0) for i in range(len(mesh_posed))] + gt_posed = [batch['mesh_posed'].cpu().numpy()[i, mask[i], :] for i in range(mask.shape[0])] + collision_gt = [np.concatenate((body[i], gt_posed[i]), axis=0) for i in range(len(gt_posed))] + figs_coll = { type + "/garment_" + str(i) + '_collision': plot_3d_collision(collision_gt[i], collision[i], collision_fixed[i], collision_faces[i], collision_color[i]) for i in range(4) } + + batch_id = batch['id'] + batch_frame_nr = batch['frame_nr'] + batch_garment = batch['garment'] + batch_info = [f'batch_info: id: {batch_id[i]}, frame_nr: {batch_frame_nr[i]}, garment: {batch_garment[i]}' for i in range(len(batch_id))] + batch_info = text_to_html(batch_info) + batch_info = wandb.Html(batch_info) + + return { **figs, **figs_coll, **{ type + '/images': imgs, }, **{ f'{type}/batch_info': batch_info }, } + + +def speed_step(levels_input, conds): + + return model.sample([levels_input, conds], training=False) + + + +def train(): + global g_balancing_coeff + global step + valid_iterator = iter(valid_dataloader) + + for batch in train_dataloader: + train_loss = train_step(batch) + train_accumulator.update(train_loss) + + 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)) } } + + if not args['debug']: + wandb.log(to_log, step=step) + train_accumulator.reset() + valid_accumulator.reset() + print(step) + + # if train_loss['train/euclid_error'] < config['balancing_activation_limit']: + # g_balancing_coeff += 1 / 50000 + + if step % 5000 == 0 and not args['debug']: + ckpt_saver(model, step, optimizer, None) + + step += 1 + + +if __name__ == '__main__': + if not args['debug']: + init_wandb() + + use_amp = True + smpl = SMPL(orig_smpl=config['is_cape'], path='smpl', device=config['device']) + skirt_modifier = '_skirt' if config['is_skirt'] else '' + dataset_resolutions = config['pyramid']['resolutions'].copy() + if 512 not in dataset_resolutions: + dataset_resolutions.append(512) + + dataset_train = Dataset(config['train_dir'], config['signature'], device=config['device'], frames_file=config['train_frames'], use_cache=config['dataset_in_memory'], resolutions=dataset_resolutions, is_cape=config['is_cape']) + dataset_valid = Dataset(config['valid_dir'], config['signature'], device=config['device'], frames_file=config['valid_frames'], use_cache=config['dataset_in_memory'], resolutions=dataset_resolutions, is_cape=config['is_cape']) + 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: Pyramid = Pyramid(config) + + # optimizer = optim.Adam(model.parameters(), lr=config['lr']) + optimizer = optim.Adam(model.parameters(), lr=config['lr']) + _MSSSIM = MS_SSIM(data_range=2, size_average=True, channel=3) + ckpt_saver = CheckpointSaver('checkpoints/iccvw/' + config['name'], top_n=50) + scaler = torch.cuda.amp.GradScaler(enabled=use_amp) + resizer = Resize(size=(512, 256), interpolation=InterpolationMode.BILINEAR).to(config['device']) + + g_balancing_coeff = config['starting_balancing_coeff'] + config['pyramid']['loss_weights'] = [1,2,3,4,5] + + step = 0 + if config['pretrained_model'] != '': + if 'ignore_saved_optimizer' in config.keys() and config['ignore_saved_optimizer']: + step = load_model(model, config['pretrained_model']) + else: + step = load_model(model, config['pretrained_model'], optimizer=optimizer, iteration=config['pretrained_model_iteration']) + + for param in model.static_enc.parameters(): param.requires_grad = False + for param in model.body_enc.parameters(): param.requires_grad = False + for param in model.norm_enc.parameters(): param.requires_grad = False + for i in range(len(model.levels)-1): + for param in model.levels[i].upscale_enhancer.parameters(): param.requires_grad = False + + train() \ No newline at end of file diff --git a/scripts/cvae_pyramid_fine.py b/scripts/cvae_pyramid_fine.py index 4ae3158..f1853a1 100644 --- a/scripts/cvae_pyramid_fine.py +++ b/scripts/cvae_pyramid_fine.py @@ -40,6 +40,8 @@ import torch import torch.nn as nn import torch.optim as optim import torch.nn.functional as F +from torchvision.transforms import Resize +from torchvision.transforms.functional import InterpolationMode from data.dataset import Dataset from utils.checkpoints import CheckpointSaver, load_model from utils.utils import InfiniteDataLoader as DataLoader @@ -57,7 +59,7 @@ def init_wandb(): wandb.login(host='https://wandb2.lnrweb.com', key='local-2a78b434e9bc51e9f12625f8321a9e3ee34af16d', relogin=True, force=True) run = wandb.init(project='iccvw', name=config['name'], notes=config['notes'], dir='/data-local/127/temp', tags=config['tags']) artifact = wandb.Artifact('code', type='code') - artifact.add_file('scripts/cvae_pyramid.py') + artifact.add_file('scripts/cvae_pyramid_fine.py') artifact.add_file('losses/losses.py') artifact.add_file('models/base.py') artifact.add_file('models/cond_encoder.py') @@ -241,8 +243,10 @@ def train_step(batch): res = config['pyramid']['resolutions'][i] res_modifier = '_' + str(res) if res != 512 else '' pred, mean, logvar = out_levels[i] + if res != 512: + pred = resizer(pred) * batch['uv_mask'][:,None,:,:] - l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((levels_input[i][0] - pred) ** 2), dim=-1), dim=[1, 2])) # levels_input[i][0] = uv_orig + l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((uv_orig - pred) ** 2), dim=-1), dim=[1, 2])) # levels_input[i][0] = uv_orig kl = kl_loss(mean, logvar) mesh_pred = uv2mesh(pred) @@ -281,7 +285,7 @@ def train_step(batch): mean = torch.mean(mean) logvar = torch.mean(logvar) - ms_ssim = torch.mean(_MSSSIM(pred + 1, levels_input[i][0] + 1)) + ms_ssim = torch.mean(_MSSSIM(pred + 1, uv_orig + 1)) metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_fix']['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred.detach()) ** 2, axis=-1))) / torch.sum(batch['mesh_fix']['mesh_mask']) output = { **output, **{ 'train/edge_loss' + res_modifier: e_loss, 'train/collision_loss' + res_modifier: c_loss,'train/euclid_error' + res_modifier: metric, @@ -318,6 +322,8 @@ def valid_step(batch): res = config['pyramid']['resolutions'][i] res_modifier = '_' + str(res) if res != 512 else '' pred, mean, logvar = out_levels[i] + if res != 512: + pred = resizer(pred) * batch['uv_mask'][:,None,:,:] mesh_pred = uv2mesh(pred) @@ -336,7 +342,7 @@ def valid_step(batch): c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio) l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_fix']['mesh_mask'][:,:,None] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, dim=-1), dim=-1)) n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_fix']['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape']) - l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((levels_input[i][0] - pred) ** 2), dim=-1), dim=[1, 2])) + l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((uv_orig - pred) ** 2), dim=-1), dim=[1, 2])) kl = kl_loss(mean, logvar) @@ -355,7 +361,7 @@ def valid_step(batch): mean = torch.mean(mean) logvar = torch.mean(logvar) - ms_ssim = torch.mean(_MSSSIM(pred + 1, levels_input[i][0] + 1)) + ms_ssim = torch.mean(_MSSSIM(pred + 1, uv_orig + 1)) metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_fix']['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / torch.sum(batch['mesh_fix']['mesh_mask']) output = { **output, **{ 'valid/edge_loss' + res_modifier: e_loss, 'valid/collision_loss' + res_modifier: c_loss,'valid/euclid_error' + res_modifier: metric, @@ -538,15 +544,18 @@ if __name__ == '__main__': model: Pyramid = Pyramid(config) - optimizer = optim.Adam(model.parameters(), lr=config['lr'] * 0.05) + # optimizer = optim.Adam(model.parameters(), lr=config['lr']) + optimizer = optim.Adam(model.parameters(), lr=config['lr'] * 0.1) _MSSSIM = MS_SSIM(data_range=2, size_average=True, channel=3) - ckpt_saver = CheckpointSaver('checkpoints/iccvw/' + config['name'] + '_fine_2', top_n=50) + ckpt_saver = CheckpointSaver('checkpoints/iccvw/' + config['name'], top_n=50) scaler = torch.cuda.amp.GradScaler(enabled=use_amp) + resizer = Resize(size=(512, 256), interpolation=InterpolationMode.BILINEAR).to(config['device']) g_balancing_coeff = config['starting_balancing_coeff'] - config['pyramid']['loss_weights'] = [1,3,5,10,25] + config['pyramid']['loss_weights'] = [1,2,3,4,5] - step = load_model(model, f'checkpoints/iccvw/{config["name"]}', iteration='25000') + step = 0 + load_model(model, config['pretrained_model'], iteration=config['pretrained_model_iteration']) for param in model.static_enc.parameters(): param.requires_grad = False for param in model.body_enc.parameters(): param.requires_grad = False diff --git a/scripts/generate_results.py b/scripts/generate_results.py index 4d0042c..7e7e6f4 100644 --- a/scripts/generate_results.py +++ b/scripts/generate_results.py @@ -13,10 +13,10 @@ parser.add_argument('-g', '--gpu', type=str) args = vars(parser.parse_args()) if args['debug']: - from configs.iccvw.pyr_64_128_cape_f_2 import config + from configs.iccvw.pyr_64_128_cape_f_2 import config_1 else: config_module = importlib.import_module(args['config']) - config = config_module.config + config_1 = config_module.config os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID" os.environ["CUDA_VISIBLE_DEVICES"] = args['gpu'] @@ -53,26 +53,26 @@ from models.pyramid_model import Pyramid from models.cvae_model import CVAE -uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape']) +uv2mesh = UV2Mesh(res=256, is_skirt=config_1['is_skirt'], is_smpl_orig=config_1['is_cape']) def step_pyramid(batch): model.eval() with torch.inference_mode(): - levels_input, conds = group_inputs_for_levels(batch, config) + levels_input, conds = group_inputs_for_levels(batch, config_1) out_levels = model([levels_input, conds]) pred, _, _ = out_levels[-1] mesh_pred = uv2mesh(pred) - if config['use_skinning']: + if config_1['use_skinning']: shape = batch['pose_shape'][:, 72:] gender = torch.greater_equal(shape[:, 10] , 0.5).to(dtype=torch.int64) shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])]) mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None] - if not config['is_cape']: + if not config_1['is_cape']: mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0] else: mesh_pred_posed = mesh_pred_shaped @@ -83,7 +83,7 @@ def step_pyramid(batch): def step(batch): - if config['use_skinning']: + if config_1['use_skinning']: uv_orig = batch['uv_unposed'] else: uv_orig = batch['uv_posed'] @@ -92,7 +92,7 @@ def step(batch): pred, _, _ = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_normals'], batch['uv_mask']]) mesh_pred = uv2mesh(pred) - if config['use_skinning']: + if config_1['use_skinning']: shape = batch['pose_shape'][:, 72:] gender = torch.greater_equal(shape[:, 10] , 0.5).to(torch.long) shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])]) @@ -141,33 +141,33 @@ def generate(): if __name__ == '__main__': - smpl = SMPL(orig_smpl=config['is_cape'], path='smpl', device=config['device']) - skirt_modifier = '_skirt' if config['is_skirt'] else '' + smpl = SMPL(orig_smpl=config_1['is_cape'], path='smpl', device=config_1['device']) + skirt_modifier = '_skirt' if config_1['is_skirt'] else '' dataset_resolutions = [] - if 'pyramid' in config: - dataset_resolutions = config['pyramid']['resolutions'].copy() + if 'pyramid' in config_1: + dataset_resolutions = config_1['pyramid']['resolutions'].copy() if 512 not in dataset_resolutions: dataset_resolutions.append(512) # remove all values from config['signature] that start with mesh_ - config['signature'] = set([x for x in config['signature'] if not x.startswith('mesh_')]) + config_1['signature'] = set([x for x in config_1['signature'] if not x.startswith('mesh_')]) - dataset_test = Dataset(config['test_dir'], config['signature'], device=config['device'], frames_file=config['test_frames'], use_cache=config['dataset_in_memory'], resolutions=dataset_resolutions, is_cape=config['is_cape']) + dataset_test = Dataset(config_1['test_dir'], config_1['signature'], device=config_1['device'], frames_file=config_1['test_frames'], use_cache=config_1['dataset_in_memory'], resolutions=dataset_resolutions, is_cape=config_1['is_cape']) # dataset_test = Dataset(config['test_dir'], config['signature'], device=config['device'], frames_file='frames_temp.txt', use_cache=config['dataset_in_memory'], resolutions=dataset_resolutions, is_cape=config['is_cape']) test_dataloader = DataLoader(dataset_test, batch_size=4, drop_last=True, shuffle=True, ) - is_pyramid = config['name'].startswith('pyr') + is_pyramid = config_1['name'].startswith('pyr') if is_pyramid: - model: Pyramid = Pyramid(config) + model: Pyramid = Pyramid(config_1) else: - model: CVAE = CVAE(config) + model: CVAE = CVAE(config_1) - it = load_model(model, 'checkpoints/iccvw/' + config['name'], iteration=args['iteration']) + it = load_model(model, 'checkpoints/iccvw/' + config_1['name'], iteration=args['iteration']) model.eval() # it = load_model(model, 'checkpoints/iccvw/' + config['name']) - name = config['name'] + '_' + str(it) + name = config_1['name'] + '_' + str(it) folder = '/data-local/127_2/results' out_folder = f'{folder}/{name}' diff --git a/scripts/generate_results_all.py b/scripts/generate_results_all.py new file mode 100644 index 0000000..853a3c6 --- /dev/null +++ b/scripts/generate_results_all.py @@ -0,0 +1,142 @@ +import os +import sys +sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/..') + +import importlib +import argparse +parser = argparse.ArgumentParser(description='') +parser.add_argument('--name', type=str) +parser.add_argument('--config', type=str) +parser.add_argument('--iteration', type=str, default='') +parser.add_argument('--debug', action='store_true') +parser.add_argument('-g', '--gpu', type=str, default='1') +args = vars(parser.parse_args()) + +if args['debug']: + from configs.iccvw.pyr_64_128_256_512_e2e import config as config_1 +else: + config_module = importlib.import_module(args['config']) + config_1 = config_module.config + +os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID" +os.environ["CUDA_VISIBLE_DEVICES"] = args['gpu'] +if args['debug']: + os.environ["CUDA_LAUNCH_BLOCKING"] = '1' + +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 + + +import torch +import torch.nn as nn +import torch.optim as optim +import torch.nn.functional as F +from tqdm import tqdm +from data.dataset import Dataset +from utils.checkpoints import CheckpointSaver, load_model +from torch.utils.data import DataLoader +from utils.utils import text_to_html +from utils.postprocess import fix_collision +from losses.losses import collision_loss, normal_loss, kl_loss +from pytorch_msssim import MS_SSIM +from custom_utils.custom_utils import UV2Mesh, Accumulator, plot_3d, get_summary_html, maskFacesBatch, get_summary_str, plot_3d_collision, group_inputs_for_levels +from smpl.smpl_torch import SMPL +from plotly.subplots import make_subplots +from models.pyramid_model import Pyramid +from models.cvae_model import CVAE + + +uv2mesh = UV2Mesh(res=256, is_skirt=config_1['is_skirt'], is_smpl_orig=config_1['is_cape']) + + +def step_pyramid(batch): + model.eval() + with torch.inference_mode(): + levels_input, conds = group_inputs_for_levels(batch, config_1) + + out = [] + out_levels = model([levels_input, conds]) + for i in range(len(out_levels)): + pred, _, _ = out_levels[i] + + mesh_pred = uv2mesh(pred) + + if config_1['use_skinning']: + shape = batch['pose_shape'][:, 72:] + gender = torch.greater_equal(shape[:, 10] , 0.5).to(dtype=torch.int64) + shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])]) + + mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None] + if not config_1['is_cape']: + mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0] + else: + mesh_pred_posed = mesh_pred_shaped + else: + mesh_pred_posed = mesh_pred + + out.append(mesh_pred_posed.cpu().numpy()) + + return out + + + +def generate(): + for batch in tqdm(test_dataloader): + with torch.inference_mode(): + mesh_pred = step_pyramid(batch) + + ids = batch['id'] + frame_nrs = batch['frame_nr'] + garments = batch['garment'] + + + for i in range(len(ids)): + np.savez_compressed(f'{out_folder}/{ids[i]}_{frame_nrs[i]}_{garments[i]}', { f'lvl{k}': mesh_pred[k][i] for k in range(len(config_1['pyramid']['resolutions'])) } ) + +#np.load(f'{out_folder}/00462_67_Jumpsuit.npz', allow_pickle=True)['arr_0'].item()['lvl3'] + + + +if __name__ == '__main__': + + smpl = SMPL(orig_smpl=config_1['is_cape'], path='smpl', device=config_1['device']) + skirt_modifier = '_skirt' if config_1['is_skirt'] else '' + dataset_resolutions = [] + if 'pyramid' in config_1: + dataset_resolutions = config_1['pyramid']['resolutions'].copy() + if 512 not in dataset_resolutions: + dataset_resolutions.append(512) + + # remove all values from config['signature] that start with mesh_ + config_1['signature'] = set([x for x in config_1['signature'] if not x.startswith('mesh_')]) + + dataset_test = Dataset(config_1['test_dir'], config_1['signature'], device=config_1['device'], frames_file=config_1['test_frames'], use_cache=config_1['dataset_in_memory'], resolutions=dataset_resolutions, is_cape=config_1['is_cape']) + # dataset_test = Dataset(config['test_dir'], config['signature'], device=config['device'], frames_file='frames_temp.txt', use_cache=config['dataset_in_memory'], resolutions=dataset_resolutions, is_cape=config['is_cape']) + test_dataloader = DataLoader(dataset_test, batch_size=4, drop_last=True, shuffle=True, ) + + is_pyramid = config_1['name'].startswith('pyr') + + if is_pyramid: + model: Pyramid = Pyramid(config_1) + else: + model: CVAE = CVAE(config_1) + + it = load_model(model, 'checkpoints/iccvw/' + config_1['name'], iteration=args['iteration']) + model.eval() + # it = load_model(model, 'checkpoints/iccvw/' + config['name']) + + name = config_1['name'] + '_' + str(it) + + folder = '/data-local/127_2/results' + out_folder = f'{folder}/{name}' + + os.makedirs(out_folder, exist_ok=True) + + generate() \ No newline at end of file diff --git a/scripts/get_error.py b/scripts/get_error.py index c03ae10..bf36b24 100644 --- a/scripts/get_error.py +++ b/scripts/get_error.py @@ -13,10 +13,10 @@ parser.add_argument('-g', '--gpu', type=str) args = vars(parser.parse_args()) if args['debug']: - from configs.iccvw.pyr_64_128_cape_f_2 import config + from configs.iccvw.pyr_64_128_cape_f_2 import config_1 else: config_module = importlib.import_module(args['config']) - config = config_module.config + config_1 = config_module.config import time @@ -57,21 +57,21 @@ def calculate(): if __name__ == '__main__': - skirt_modifier = '_skirt' if config['is_skirt'] else '' + skirt_modifier = '_skirt' if config_1['is_skirt'] else '' - name = config['name'] - if not config['is_cape']: - frames_file = config['test_frames'] - with open(os.path.join(config['test_dir'], frames_file), 'r') as f: + name = config_1['name'] + if not config_1['is_cape']: + frames_file = config_1['test_frames'] + with open(os.path.join(config_1['test_dir'], frames_file), 'r') as f: frames = f.readlines() frames = [Frame(frames.split()[0], int(frames.split()[1]), frames.split()[2]) for frames in frames] else: from data.dataset_cape import read_frames - frames = read_frames(config['test_dir'], shuffle=False, is_cape=True) + frames = read_frames(config_1['test_dir'], shuffle=False, is_cape=True) results_folder = '/data-local/127_2/results' if args['iteration'] == '': - folders = [f for f in os.listdir(results_folder) if os.path.isdir(os.path.join(results_folder, f)) and f.startswith(config['name'])] + folders = [f for f in os.listdir(results_folder) if os.path.isdir(os.path.join(results_folder, f)) and f.startswith(config_1['name'])] assert len(folders) == 1 name = folders[0] else: diff --git a/scripts/get_error_merged.py b/scripts/get_error_merged.py new file mode 100644 index 0000000..f26bf76 --- /dev/null +++ b/scripts/get_error_merged.py @@ -0,0 +1,109 @@ +import os +import sys +sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/..') + +import importlib +import argparse +parser = argparse.ArgumentParser(description='') +parser.add_argument('--name', type=str) +parser.add_argument('--config1', type=str) +parser.add_argument('--config2', type=str, default='') +parser.add_argument('--debug', action='store_true') +parser.add_argument('--iteration1', type=str, default='') +parser.add_argument('--iteration2', type=str, default='') +parser.add_argument('-g', '--gpu', type=str) +args = vars(parser.parse_args()) + + +if args['debug']: + from configs.iccvw.pyr_64_128_cape_f_2 import config_1 +else: + config_module = importlib.import_module(args['config1']) + config_1 = config_module.config + config_module = importlib.import_module(args['config2'] if args['config2'] != '' else args['config1'] + '_skirt') + config_2 = config_module.config + +import time +import argparse +import tqdm +import random +import numpy as np +import plotly.graph_objects as go +import plotly.express as ex +from data.utils import Frame + + + + +def calculate(name): + errors = dict() + errors_mean = dict() + + with open(f'{results_folder}/errors/{name}.csv', 'r') as f: + lines = f.readlines() + + for line in lines: + line = line.split(',') + category = line[2] + if category not in errors: + errors[category] = [] + errors[category].append(float(line[3])) + + for category in errors: + errors_mean[category] = np.mean(errors[category]) + + return errors_mean + + + +if __name__ == '__main__': + name = config_1['name'] + if not config_1['is_cape']: + frames_file = config_1['test_frames'] + with open(os.path.join(config_1['test_dir'], frames_file), 'r') as f: + frames = f.readlines() + frames = [Frame(frames.split()[0], int(frames.split()[1]), frames.split()[2]) for frames in frames] + else: + from data.dataset_cape import read_frames + frames = read_frames(config_1['test_dir'], shuffle=False, is_cape=True) + + results_folder = '/data-local/127_2/results' + if args['iteration1'] == '': + folders = [f for f in os.listdir(results_folder) if os.path.isdir(os.path.join(results_folder, f)) and f.startswith(config_1['name'])] + if not config_1['is_skirt']: + folders = [f for f in folders if f.find('skirt') == -1] + assert len(folders) == 1 + name = folders[0] + else: + name = f'{name}_{args["iteration1"]}' + + non_skirt = calculate(name) + + name = config_2['name'] + if not config_2['is_cape']: + frames_file = config_2['test_frames'] + with open(os.path.join(config_2['test_dir'], frames_file), 'r') as f: + frames = f.readlines() + frames = [Frame(frames.split()[0], int(frames.split()[1]), frames.split()[2]) for frames in frames] + else: + from data.dataset_cape import read_frames + frames = read_frames(config_2['test_dir'], shuffle=False, is_cape=True) + + results_folder = '/data-local/127_2/results' + if args['iteration2'] == '': + folders = [f for f in os.listdir(results_folder) if os.path.isdir(os.path.join(results_folder, f)) and f.startswith(config_2['name'])] + if not config_2['is_skirt']: + folders = [f for f in folders if f.find('skirt') == -1] + assert len(folders) == 1 + name = folders[0] + else: + name = f'{name}_{args["iteration2"]}' + + skirt = calculate(name) + + all = {**non_skirt, **skirt} + + print(all) + mean = np.mean(list(all.values())) + + print(f'Final error: {mean}') diff --git a/scripts/get_final_cape.py b/scripts/get_final_cape.py new file mode 100644 index 0000000..edcdb2b --- /dev/null +++ b/scripts/get_final_cape.py @@ -0,0 +1,188 @@ +import os +import sys +sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/..') + +import importlib +import argparse +parser = argparse.ArgumentParser(description='') +parser.add_argument('--name', type=str) +parser.add_argument('--config', type=str) +parser.add_argument('--iteration', type=str, default='') +parser.add_argument('--debug', action='store_true') +parser.add_argument('-g', '--gpu', type=str, default='1') +args = vars(parser.parse_args()) + +if args['debug']: + from configs.iccvw.pyr_64_128_256_512_cape_f_e2e import config as config_1 +else: + config_module = importlib.import_module(args['config']) + config_1 = config_module.config + +os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID" +os.environ["CUDA_VISIBLE_DEVICES"] = args['gpu'] +if args['debug']: + os.environ["CUDA_LAUNCH_BLOCKING"] = '1' + +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 + + +import torch +import torch.nn as nn +import torch.optim as optim +import torch.nn.functional as F +from tqdm import tqdm +from data.dataset import Dataset +from utils.checkpoints import CheckpointSaver, load_model +from torch.utils.data import DataLoader +from utils.utils import text_to_html +from utils.postprocess import fix_collision +from losses.losses import collision_loss, normal_loss, kl_loss +from pytorch_msssim import MS_SSIM +from custom_utils.custom_utils import UV2Mesh, Accumulator, plot_3d, get_summary_html, maskFacesBatch, get_summary_str, plot_3d_collision, group_inputs_for_levels +from smpl.smpl_torch import SMPL +from plotly.subplots import make_subplots +from models.pyramid_model import Pyramid +from models.cvae_model import CVAE +from data.utils import Frame + + +uv2mesh = UV2Mesh(res=256, is_skirt=config_1['is_skirt'], is_smpl_orig=config_1['is_cape']) + + +def step_pyramid(batch): + model.eval() + with torch.inference_mode(): + levels_input, conds = group_inputs_for_levels(batch, config_1) + + out = [] + + out_levels = model([levels_input, conds]) + for i in range(len(out_levels)): + pred, _, _ = out_levels[i] + + mesh_pred = uv2mesh(pred) + + if config_1['use_skinning']: + shape = batch['pose_shape'][:, 72:] + gender = torch.greater_equal(shape[:, 10] , 0.5).to(dtype=torch.int64) + shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])]) + + mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None] + if not config_1['is_cape']: + mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0] + else: + mesh_pred_posed = mesh_pred_shaped + else: + mesh_pred_posed = mesh_pred + + out.append(mesh_pred_posed) + + return out + +from smpl.smpl_torch import SMPL +smpl = SMPL(path='smpl', orig_smpl=True, device='cpu') +clothing_verts_idx = np.load(os.path.join('custom_data', 'clothing_verts_idx.npy')) +cape_mask = np.zeros((6890), bool) +cape_mask[clothing_verts_idx] = True + +def get_error(pred, frame: Frame): + gt = np.load(f'{config_1["test_dir"]}/mesh_unposed_no_shape/{frame.id}.{frame.frame_nr}.npz')['mesh_unposed_no_shape'] + pose_shape = np.load(f'{config_1["test_dir"]}/pose_shape/{frame.id}.{frame.frame_nr}.npy').astype(np.float32) + pose, shape = pose_shape[:72], pose_shape[72:] + gender = int(shape[10] >= 0.5) + shape_offsets = torch.tensordot(torch.from_numpy(shape[:10][None, :]), smpl.shapedirs[gender].to('cpu'), dims=[[1], [2]])[0,smpl.to_keep,:].numpy() + + gt_shaped = gt + shape_offsets + + min_body = np.load(os.path.join('/data-local/127_2/cape_processed', 'minimal_body_shape', frame.id.split('_')[0], frame.id.split('_')[0] + '_minimal.npy')) + offsets_pred = pred[cape_mask[smpl.to_keep],:] - min_body[clothing_verts_idx,:] + offsets_orig = gt_shaped[cape_mask[smpl.to_keep],:] - min_body[clothing_verts_idx,:] + + error = np.linalg.norm(offsets_pred - offsets_orig, axis=1).mean() + return error + + +def generate(): + errors = {0: [], 1: [], 2: [], 3: []} + for batch in tqdm(test_dataloader): + with torch.inference_mode(): + mesh_pred = step_pyramid(batch) + + + ids = batch['id'] + frame_nrs = batch['frame_nr'] + garments = batch['garment'] + + for i in range(len(mesh_pred)): + frame = Frame(ids[i], frame_nrs[i], garments[i]) + for j in range(4): + error = get_error(mesh_pred[j][i].cpu().numpy(), frame) + errors[j].append(error) + + # print(errors) + for j in range(4): + print(f'Level {j}: {np.mean(errors[j])}') + + + # import plotly.graph_objects as go + # mesh_pred = mesh_pred.cpu().numpy() + # mask = batch['mesh_mask'].cpu().numpy() + # i = 3 + # fig = go.Figure(data=[go.Scatter3d(x=mesh_pred[i,mask[i],0], y=mesh_pred[i,mask[i],2], z=mesh_pred[i,mask[i],1], mode='markers', marker=dict(size=1))]) + # fig.update_layout(scene_aspectmode='cube') + # fig.show() + + # import plotly.graph_objects as go + # mesh_pred = mesh_pred.cpu().numpy() + # i = 3 + # fig = go.Figure(data=[go.Scatter3d(x=mesh_pred[i,:,0], y=mesh_pred[i,:,2], z=mesh_pred[i,:,1], mode='markers', marker=dict(size=1))]) + # fig.update_layout(scene_aspectmode='cube') + # fig.update_layout(scene=dict(xaxis=dict(range=[-1,1]), yaxis=dict(range=[-1,1]), zaxis=dict(range=[-1,1]))) + # fig.show() + + + + + + +if __name__ == '__main__': + + smpl = SMPL(orig_smpl=config_1['is_cape'], path='smpl', device=config_1['device']) + skirt_modifier = '_skirt' if config_1['is_skirt'] else '' + dataset_resolutions = [] + if 'pyramid' in config_1: + dataset_resolutions = config_1['pyramid']['resolutions'].copy() + if 512 not in dataset_resolutions: + dataset_resolutions.append(512) + + # remove all values from config['signature] that start with mesh_ + config_1['signature'] = set([x for x in config_1['signature'] if not x.startswith('mesh_')]) + + dataset_test = Dataset(config_1['test_dir'], config_1['signature'], device=config_1['device'], frames_file=config_1['test_frames'], use_cache=config_1['dataset_in_memory'], resolutions=dataset_resolutions, is_cape=config_1['is_cape']) + # dataset_test = Dataset(config['test_dir'], config['signature'], device=config['device'], frames_file='frames_temp.txt', use_cache=config['dataset_in_memory'], resolutions=dataset_resolutions, is_cape=config['is_cape']) + test_dataloader = DataLoader(dataset_test, batch_size=4, drop_last=True, shuffle=True, ) + + is_pyramid = config_1['name'].startswith('pyr') + + model: Pyramid = Pyramid(config_1) + + it = load_model(model, 'checkpoints/iccvw/' + config_1['name'], iteration=args['iteration']) + model.eval() + # it = load_model(model, 'checkpoints/iccvw/' + config['name']) + + name = config_1['name'] + '_' + str(it) + + folder = '/data-local/127_2/results' + out_folder = f'{folder}/{name}' + + os.makedirs(out_folder, exist_ok=True) + + generate() \ No newline at end of file