import imp import os import time import argparse import wandb import random import numpy as np import tensorflow as tf from custom_utils.custom_utils import UV2Mesh, maskFacesBatch import plotly.graph_objects as go import plotly.express as ex from tf_utils import check_tf_version, allow_memory_growth from losses import d_logistic, d_logistic_r1_reg, g_logistic_non_saturating, g_logistic_ns_pathreg, edge_loss, uv_mask_loss from dataset import DatasetFactory, StaticDataset from custom_utils.custom_utils import batch_to_dict from custom_utils.smpl import SMPL from models.ae_static_model import AutoEncoder name='ae_static_5' def init_wandb(): os.environ["CUDA_VISIBLE_DEVICES"] = "0" run = wandb.init(project='vae', name=name, notes='convnext + convnext, add dense with tanh at the end of reverse convnext, larger features. add lr scheduler. fft3d instead of rfft3d. \ fft2d per channel and separate for top and bottom. fft_loss, all data. added convnext block as bottleneck, same as before, added extra metric. \ . lowered learning rate because it goes to nan. shallow third stage. slower lr decay. with validation. higher lr rate.\ convnext first stage down/upscale by factor fo 2 instead of 4, and 5 stages instead of 4 so bottlneck same size\ flattened latent dim to 128\ trai on 100 garments') artifact = wandb.Artifact('code', type='code') artifact.add_file('auto_encoder_static.py') artifact.add_file('losses.py') artifact.add_file('dataset.py') artifact.add_file('convnext/models/convnext_tf.py') run.log_artifact(artifact) uv2mesh = UV2Mesh(res=256) def plot_3d(mesh_gt, mesh_pred_unposed, faces, collision, collision_faces, collision_color): mesh_pred_unposed[:,1] += 1 collision[:,1] += 2 fig = go.Figure(data=[ go.Mesh3d( # 8 vertices of a cube x=mesh_gt[:,0], y=mesh_gt[:,1], z=mesh_gt[:,2], # i, j and k give the vertices of triangles i = faces[:,0], j = faces[:,1], k = faces[:,2] ), go.Mesh3d( # 8 vertices of a cube x=mesh_pred_unposed[:,0], y=mesh_pred_unposed[:,1], z=mesh_pred_unposed[:,2], # i, j and k give the vertices of triangles i = faces[:,0], j = faces[:,1], k = faces[:,2], ), go.Mesh3d( # 8 vertices of a cube x=collision[:,0], y=collision[:,1], z=collision[:,2], # i, j and k give the vertices of triangles i = collision_faces[:,0], j = collision_faces[:,1], k = collision_faces[:,2], vertexcolor=collision_color ) ]) fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=2, z=1)) fig.update_layout( scene = dict( xaxis = dict(nticks=4, range=[-1,1],), yaxis = dict(nticks=4, range=[-1,3],), zaxis = dict(nticks=4, range=[-1,1],),) ) return fig @tf.function def train_step(batch): with tf.GradientTape() as tape: pred = model(batch['uv_static']) uv_mask = batch['uv_mask'] mesh_pred = uv2mesh(pred) mesh_orig = batch['mesh_static'] e_loss = 1e-2 * tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask'])) c_loss = 0 #1e-2 * tf.reduce_mean(collision_penalty(mesh_pred, batch['mesh_body_posed'], batch['mesh_mask'])) # l1_loss = tf.reduce_mean(tf.reduce_sum((tf.math.abs(batch['mesh_unposed'] - pred)), axis=-1) * batch['mesh_mask']) l1_loss = tf.reduce_mean(tf.reduce_sum((tf.math.abs(batch['uv_static'] - pred)), axis=1) * uv_mask) ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(tf.transpose(pred, [0,2,3,1]) * uv_mask[:,:,:,tf.newaxis] + 1, tf.transpose(batch['uv_static'], [0,2,3,1]) * uv_mask[:,:,:,tf.newaxis] + 1, max_val=2)) fft_loss = 0 #tf.reduce_mean(tf.reduce_sum(tf.math.abs(tf.signal.fft3d(tf.complex(pred, tf.zeros_like(pred))) - tf.signal.fft3d(tf.complex(batch['uv_static'], tf.zeros_like(batch['uv_static'])))), axis=[1,2,3])) loss = 1e3 * (1 - ms_ssim) mesh_orig_2 = uv2mesh(batch['uv_static']) # mesh_skinned = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred) metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask']) metric_2 = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig_2 - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask']) euclid_posed = 0 # tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_skinned - batch['mesh_posed']) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask']) gradients = tape.gradient(loss, model.trainable_variables) # gradients = [tf.clip_by_norm(g, 1.0) for g in gradients] # gradients = [tf.clip_by_value(g, -1.0, 1.0) for g in gradients] optimizer.apply_gradients(zip(gradients, model.trainable_variables)) return { 'train/loss': loss, 'train/edge_loss': e_loss, 'train/collision_loss': c_loss, 'train/l1_loss': l1_loss, 'train/euclid_error': metric, 'train/ms_ssim': ms_ssim, 'train/fft_loss': fft_loss, 'train/euclid_error_reconst': metric_2, 'train/euclid_error_posed': euclid_posed } @tf.function def valid_step(batch): pred = model(batch['uv_static']) uv_mask = batch['uv_mask'] mesh_pred = uv2mesh(pred) mesh_orig = batch['mesh_static'] e_loss = 1e-2 * tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask'])) c_loss = 0 l1_loss = tf.reduce_mean(tf.reduce_sum((tf.math.abs(batch['uv_static'] - pred)), axis=1) * uv_mask) ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(tf.transpose(pred, [0,2,3,1]) + 1, tf.transpose(batch['uv_static'], [0,2,3,1]) + 1, max_val=2)) fft_loss = 0 #tf.reduce_mean(tf.reduce_sum(tf.math.abs(tf.signal.fft3d(tf.complex(pred, tf.zeros_like(pred))) - tf.signal.fft3d(tf.complex(batch['uv_static'], tf.zeros_like(batch['uv_static'])))), axis=[1,2,3])) loss = 1e3 * (1 - ms_ssim) mesh_orig_2 = uv2mesh(batch['uv_static']) metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask']) metric_2 = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig_2 - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask']) return { 'valid/loss': loss, 'valid/edge_loss': e_loss, 'valid/collision_loss': c_loss, 'valid/l1_loss': l1_loss, 'valid/euclid_error': metric, 'valid/ms_ssim': ms_ssim, 'valid/fft_loss': fft_loss, 'valid/euclid_error_reconst': metric_2 } def plot_everything(batch: dict, type: str): pred = model(batch['uv_static']) mesh_pred = uv2mesh(pred) mesh_orig = batch['mesh_static'] orig_img = tf.transpose(batch['uv_static'], [0,2,3,1]) pred_img = tf.transpose(pred, [0,2,3,1]) img = tf.concat((orig_img, pred_img), axis=2) imgs = [wandb.Image((img[i] + 1) / 2.0) for i in range(4)] F = np.load("custom_utils/smpl_faces.npy") mask = batch['mesh_mask'].numpy().astype(bool) garment_unposed, faces = maskFacesBatch(mesh_pred.numpy(), F, mask) gt = [mesh_orig[i].numpy()[mask[i], :] for i in range(pred.shape[0])] body = gt garment_posed = mesh_pred collision = [np.concatenate((body[i], garment_posed[i]), axis=0) for i in range(len(garment_posed))] collision_faces = [np.concatenate((faces[i], faces[i] + np.sum(mask[i])), 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[i], collision[i], collision_faces[i], collision_color[i]) for i in range(4) } return { **figs, **{ type + '/images': imgs } } def train(): step = 0 for batch in dataset_train: batch = static_dataset_train.expand_batch(batch_to_dict(batch, signature_dynamic)) train_loss = train_step(batch) # data_valid = valid_iterator.get_next() # data_valid = static_dataset_valid.expand_batch(batch_to_dict(data_valid, signature_dynamic)) valid_loss = {}#valid_step(data_valid) if step % 1000 == 0: train_figs = plot_everything(batch, 'train') valid_figs = {}#plot_everything(data_valid, 'valid') wandb.log({ **train_loss, **valid_loss, **train_figs, **valid_figs }, step=step) else: wandb.log({ **train_loss, **valid_loss }, step=step) print(step) step += 1 if __name__ == '__main__': init_wandb() allow_memory_growth() parser = argparse.ArgumentParser(description='') parser.add_argument('--name', type=str) args = vars(parser.parse_args()) smpl = SMPL() resolution_modifier = '_32' resolutions = [32] factory = DatasetFactory() signature_dynamic = { 'id': (), # 'pose_shape': (72 + 11,), # 'uv_posed': (3, 512, 256,), # 'uv_body_posed': (3, 512, 256,), # 'mesh_body_posed': (14475, 3,), # 'mesh_posed': (14475, 3,), # 'mesh_unposed': (14475, 3,), # 'uv_unposed': (3, 512, 256,) } signature_static = { 'uv_static': (3, 512, 256,), 'mesh_static': (14475, 3,), 'mesh_mask': (14475,), 'uv_mask': (512, 256,), # 'uv_shaped_body': (3, 512, 256,), } dataset_train = factory.get_dataset(folder='/home/workspace/local-data/train_100', batch_size=8, signature=signature_dynamic) static_dataset_train = StaticDataset(folder='/home/workspace/local-data/train_100', signature=signature_static) dataset_valid = factory.get_dataset(folder='/home/workspace/local-data/jumpsuit_20/valid', batch_size=8, signature=signature_dynamic) static_dataset_valid = StaticDataset(folder='/home/workspace/local-data/jumpsuit_20/valid', signature=signature_static) model = AutoEncoder() lr_schedule = tf.keras.optimizers.schedules.ExponentialDecay(0.0005, decay_steps=30000, decay_rate=0.1, staircase=False) optimizer = tf.optimizers.Adam(learning_rate=lr_schedule) folder = 'models/ae_logs/' valid_iterator = iter(dataset_valid) ckpt = tf.train.Checkpoint(model=model) manager = tf.train.CheckpointManager(ckpt, 'checkpoints/' + name, max_to_keep=5) train()