From 2f77e2af18f45825ddbcc1ebd5d77dfb863d94aa Mon Sep 17 00:00:00 2001 From: Hunor Laczko Date: Thu, 13 Jul 2023 12:35:11 +0200 Subject: [PATCH] plot ablation --- scripts/plot_ablation.py | 161 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 161 insertions(+) create mode 100644 scripts/plot_ablation.py diff --git a/scripts/plot_ablation.py b/scripts/plot_ablation.py new file mode 100644 index 0000000..26df6dd --- /dev/null +++ b/scripts/plot_ablation.py @@ -0,0 +1,161 @@ +import os +import sys +sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/..') + +os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID" +os.environ["CUDA_VISIBLE_DEVICES"] = '3' + +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 torchvision.transforms import Resize +from torchvision.transforms.functional import InterpolationMode +from pathlib import Path +import importlib + +from data.utils import Frame +from data.dataset import read_frames_file +from utils.utils import save_stl +from utils.checkpoints import CheckpointSaver, load_model +from utils.postprocess import fix_collision +from losses.losses import collision_loss, normal_loss, kl_loss +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 data.dataset import Dataset +from utils.checkpoints import CheckpointSaver, load_model +from torch.utils.data import DataLoader +import trimesh as tm +from zipfile import ZipFile + +from configs.iccvw.pyr_64_128_256_512_abl import config as config_1 + + +uv2mesh = UV2Mesh(res=256, is_skirt=False, is_smpl_orig=config_1['is_cape']) +uv2mesh_skirt = UV2Mesh(res=256, is_skirt=True, is_smpl_orig=config_1['is_cape']) + + +def step_pyramid(model, batch, config): + with torch.inference_mode(): + levels_input, conds = group_inputs_for_levels(batch, config) + out_levels = model([levels_input, conds]) + pred, _, _ = out_levels[-1] + + mesh_pred = uv2mesh(pred) if not config['is_skirt'] else uv2mesh_skirt(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_mask'][:,:,None] + if not config['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 + + return mesh_pred_posed + + +def create_temp_frames(folder: str, frame: Frame): + with open(Path(folder) / 'frames_temp.txt', 'w') as f: + f.writelines([f'{frame}\n' for _ in range(4)]) + + +if __name__ == '__main__': + results_folder = Path('/data-local/127_2/results') + out_folder = Path('temp/ablation') + + smpl = SMPL(orig_smpl=config_1['is_cape'], path='smpl', device=config_1['device']) + dataset_resolutions = [] + dataset_resolutions = [64, 128, 256, 512] + + experiments = { + 'final': { 'nonskirt': ('pyr_64_128_256_512', 100000), 'skirt': ('pyr_64_128_256_512_skirt', 200000) }, + 'e2e': { 'nonskirt': ('pyr_64_128_256_512_e2e', 165000), 'skirt': ('pyr_64_128_256_512_skirt_e2e', 175000) }, + 'skin': { 'nonskirt': ('pyr_64_128_256_512_skin', 225000), 'skirt': ('pyr_64_128_256_512_skin_skirt', 200000) }, + 'norm': { 'nonskirt': ('pyr_64_128_256_512_norm', 200000), 'skirt': ('pyr_64_128_256_512_norm_skirt', 200000) }, + 'reg': { 'nonskirt': ('pyr_64_128_256_512_reg', 200000), 'skirt': ('pyr_64_128_256_512_reg_skirt', 200000) }, + } + + configs = dict() + models = dict() + + for experiment in experiments.keys(): + configs[experiment] = dict() + configs[experiment]['nonskirt'] = importlib.import_module('configs.iccvw.' + experiments[experiment]['nonskirt'][0]).config + configs[experiment]['skirt'] = importlib.import_module('configs.iccvw.' + experiments[experiment]['skirt'][0]).config + + models[experiment] = dict() + models[experiment]['nonskirt'] = Pyramid(configs[experiment]['nonskirt']) + models[experiment]['skirt'] = Pyramid(configs[experiment]['skirt']) + + load_model(models[experiment]['nonskirt'], 'checkpoints/iccvw/' + configs[experiment]['nonskirt']['name'], iteration=experiments[experiment]['nonskirt'][1]) + load_model(models[experiment]['skirt'], 'checkpoints/iccvw/' + configs[experiment]['skirt']['name'], iteration=experiments[experiment]['skirt'][1]) + + models[experiment]['nonskirt'].eval() + models[experiment]['skirt'].eval() + + + frames = ['00054_1_Dress', '00005_1_Jumpsuit'] + frames = [Frame(frame_str=frame) for frame in frames] + body_faces = smpl.f + + for frame in frames: + create_temp_frames(config_1['train_dir'], frame) + dataset = Dataset(config_1['train_dir'], config_1['signature'], device=config_1['device'], frames_file='frames_temp.txt', use_cache=True, resolutions=dataset_resolutions, is_cape=False) + dataloader = DataLoader(dataset, batch_size=4, drop_last=True, shuffle=True, ) + + model_picker = 'skirt' if frame.garment in ['Dress', 'Skirt'] else 'nonskirt' + + fix_data = np.load(Path(dataset.folder) / 'mesh_fixed' / f'{frame.id}_{frame.garment}.npz') + mask = fix_data['mask'] + faces = fix_data['faces'] + + batch = next(iter(dataloader)) + body = batch['mesh_body_posed'][0].cpu().numpy() + gt = batch['mesh_posed'][0].cpu().numpy() + + save_stl(out_folder / f'{frame}_gt.stl', gt[mask, :], faces) + save_stl(out_folder / f'{frame}_gt_body.stl', body, body_faces) + + for experiment in experiments.keys(): + + pred = step_pyramid(models[experiment][model_picker], batch, configs[experiment][model_picker]) + + mesh_posed_fixed = fix_collision(pred, batch['mesh_body_posed'], batch['mesh_mask']).cpu().numpy() + mesh_posed_fixed = mesh_posed_fixed[0, mask, :] + m = tm.Trimesh(mesh_posed_fixed, faces, process=False, validate=False) + tm.smoothing.filter_humphrey(m, iterations=2) + verts = m.vertices + + save_stl(out_folder / f'{frame}_{experiment}_body.stl', body, body_faces) + save_stl(out_folder / f'{frame}_{experiment}_mesh.stl', verts, faces) + + fig = go.Figure(data=[go.Mesh3d(x=verts[:,0], y=verts[:,2], z=verts[:,1], i=faces[:,0], j=faces[:,1], k=faces[:,2], color='lightpink', opacity=1), + go.Mesh3d(x=body[:,0], y=body[:,2], z=body[:,1], i=body_faces[:,0], j=body_faces[:,1], k=body_faces[:,2], color='gray', opacity=1) + ]) + fig.update_layout(scene=dict(aspectmode='cube')) + fig.update_layout(scene=dict(xaxis=dict(range=[-1, 1], ), yaxis=dict(range=[-1, 1], ), zaxis=dict(range=[-1, 1], ), ), ) + fig.update_layout(title_text=f'{frame} {experiment}') + fig.show() + pass + + pass + + + +