diff --git a/auto_encoder_body.py b/auto_encoder_body.py index 2861e03..1fc01ee 100644 --- a/auto_encoder_body.py +++ b/auto_encoder_body.py @@ -1,4 +1,6 @@ import os +os.environ["CUDA_VISIBLE_DEVICES"] = "0" + import time import argparse import wandb @@ -7,27 +9,19 @@ import cv2 import numpy as np import tensorflow as tf from custom_utils.custom_utils import UV2Mesh, maskFacesBatch -from tensorboardX import SummaryWriter import plotly.graph_objects as go import plotly.express as ex -from utils import str_to_bool -from tf_utils import check_tf_version, allow_memory_growth, split_gpu_for_testing -from load_models import load_generator, load_discriminator -from losses import d_logistic, d_logistic_r1_reg, g_logistic_non_saturating, g_logistic_ns_pathreg, edge_loss, uv_mask_loss -# from losses import collision_penalty as collision_penalty -from losses import collision_loss as collision_penalty -from convnext.models.convnext_tf import ConvNeXt, ConvNeXtReverse, Block -from stylegan2_ae.generator import Generator -from custom_utils.graph_utils import Reconstructor_V4_Decoder as GNNDecoder -from custom_utils.graph_utils import Reconstructor_v2 as SimpleReconstructor +from tf_utils import check_tf_version, allow_memory_growth +from losses import 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_body_model import AutoEncoder -name='ae_body_7_2' + +name='ae_body_8' def init_wandb(): - os.environ["CUDA_VISIBLE_DEVICES"] = "4" 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. \ @@ -36,10 +30,12 @@ def init_wandb(): larger batch_size.\ flattened bottleneck with 128 latent_dim\ remove global orientation\ fixed gender issue with deoriented bodies, again, aaand again\ - trained on 100 garments') + trained on 100 garments\ + remove multiplications with garment uv mask') artifact = wandb.Artifact('code', type='code') artifact.add_file('auto_encoder_body.py') artifact.add_file('losses.py') + artifact.add_file('models/ae_body_model.py') artifact.add_file('dataset.py') artifact.add_file('convnext/models/convnext_tf.py') run.log_artifact(artifact) @@ -47,42 +43,6 @@ def init_wandb(): uv2mesh = UV2Mesh(res=256) -class DatasetSimple(tf.data.Dataset): - - def _generator(folder): - # Opening the file - folder = folder.decode("utf-8") - uv_folder = os.path.join(folder, 'uv_posed') - frames = os.listdir(uv_folder) - random.shuffle(frames) - - for frame in frames: - id, frame_nr = frame.split('.')[0].split('_') - mesh_mask = np.load(os.path.join(folder, 'mesh_mask', id + '.npy')); mesh_mask = mesh_mask.astype(np.float32) - uv_mask = np.load(os.path.join(folder, 'uv_mask', id + '.npz')); uv_mask=uv_mask['uv_mask']; uv_mask = uv_mask.astype(np.float32) - mesh_unposed = np.load(os.path.join(folder, 'mesh_unposed', id + '_' + frame_nr + '.npz')); mesh_unposed = mesh_unposed['mesh_unposed'] - uv_unposed = np.load(os.path.join(folder, 'uv_unposed', id + '_' + frame_nr + '.npz')); uv_unposed = uv_unposed['uv_unposed']; uv_unposed = np.transpose(uv_unposed, [2, 0, 1]) - - yield uv_unposed, mesh_unposed, uv_mask, mesh_mask - - def __new__(cls, folder, res=256): - return tf.data.Dataset.from_generator( - cls._generator, - output_signature = (tf.TensorSpec(shape = (3, res * 2, res,), dtype = tf.float32), - tf.TensorSpec(shape = (14475, 3,), dtype = tf.float32), - tf.TensorSpec(shape = (res * 2, res,), dtype = tf.float32), - tf.TensorSpec(shape = (14475,), dtype = tf.float32), ), - args=(folder, ) - ) - - - -def filter_resolutions_featuremaps(resolutions, featuremaps, res): - index = resolutions.index(res) - filtered_resolutions = resolutions[:index + 1] - filtered_featuremaps = featuremaps[:index + 1] - return filtered_resolutions, filtered_featuremaps - def plot_3d(mesh_gt, mesh_pred_unposed, faces, collision, collision_faces, collision_color): mesh_pred_unposed[:,1] += 1 @@ -133,149 +93,12 @@ def plot_3d(mesh_gt, mesh_pred_unposed, faces, collision, collision_faces, colli return fig -class Bottleneck(tf.keras.Model): - - def __init__(self, dim, latent_dim): - super(Bottleneck, self).__init__() - - self.bottleneck = tf.keras.Sequential( - [Block(dim=dim, drop_path=0, - layer_scale_init_value=1e-6, prefix=f'bottleneck{j}') for j in range(5)] - ) - self.flatten = tf.keras.layers.Flatten() - self.dense = tf.keras.layers.Dense(latent_dim) - - def call(self, inputs, training=None): - x = inputs - - x = self.bottleneck(x) - x = self.flatten(x) - x = self.dense(x) - - return x - - -class Decoder(tf.keras.Model): - - def __init__(self, bottleneck_size, latent_dim): - super(Decoder, self).__init__() - - self.dense = tf.keras.layers.Dense(4 * 2 * bottleneck_size) - self.reshape = tf.keras.layers.Reshape((4, 2, bottleneck_size)) - self.decoder = ConvNeXtReverse(depths=list(reversed([3, 3, 9, 3])), dims=list(reversed([bottleneck_size, 128, 64, 16]))) - - def call(self, inputs, training=None): - x = inputs - - x = self.dense(x) - x = self.reshape(x) - x = self.decoder(x) - - return x - - -class AutoEncoder(tf.keras.Model): - - def __init__(self): - super(AutoEncoder, self).__init__() - - - bottleneck_size = 512 - latent_dim = 128 - - self.encoder = ConvNeXt(depths=[3, 3, 9, 9, 3, 3], dims=[32, 64, 128, 256, 256, bottleneck_size], include_top=False) - self.bottleneck = Bottleneck(bottleneck_size, latent_dim) - self.decoder = Decoder(bottleneck_size, latent_dim) - - - def call(self, inputs, training=None): - x, _ = inputs - - x = tf.transpose(x, [0,2,3,1]) - x = self.encoder(x, training=training) - # x = self.pooling(x) - # x = self.reshape(x) - # x = self.flatten(x) - - x = self.bottleneck(x, training=training) - - x = self.decoder(x, training=training) - x = tf.image.resize(x, (512, 256), tf.image.ResizeMethod.LANCZOS5) - x = tf.transpose(x, [0,3,1,2]) - - # x = x * uv_mask[:,:, tf.newaxis] - x = x * uv_mask_body[tf.newaxis,tf.newaxis,:,:] - - return x - -def draw_cicle(shape,diamiter): - ''' - Input: - shape : tuple (height, width) - diameter : scalar - - Output: - np.array of shape that says True within a circle with diamiter = around center - ''' - assert len(shape) == 2 - TF = np.zeros(shape,dtype=bool) - center = np.array(TF.shape)/2.0 - - for iy in range(shape[0]): - for ix in range(shape[1]): - TF[iy,ix] = (iy- center[0])**2 + (ix - center[1])**2 < diamiter **2 - return (TF) - - -TFcircleIN = draw_cicle(shape=(256,256), diamiter=15) -TFcircleIN = np.ones((512,256,3), dtype=bool) * np.concatenate((TFcircleIN, TFcircleIN), axis=0)[:,:,np.newaxis] -TFcircleOUT = ~TFcircleIN - -def fft_loss_per_channel(pred, gt): - pred = tf.complex(pred, tf.zeros_like(pred)) - gt = tf.complex(gt, tf.zeros_like(gt)) - - fft_pred_top = tf.stack([tf.signal.fftshift(tf.signal.fft2d(pred[:,i,:256,:])) for i in range(3)], axis=-1) - fft_gt_top = tf.stack([tf.signal.fftshift(tf.signal.fft2d(gt[:,i,:256,:])) for i in range(3)], axis=-1) - - fft_pred_bottom = tf.stack([tf.signal.fftshift(tf.signal.fft2d(pred[:,i,256:,:])) for i in range(3)], axis=-1) - fft_gt_bottom = tf.stack([tf.signal.fftshift(tf.signal.fft2d(gt[:,i,256:,:])) for i in range(3)], axis=-1) - - fft_pred = tf.concat((fft_pred_top, fft_pred_bottom), axis=1) - fft_gt = tf.concat((fft_gt_top, fft_gt_bottom), axis=1) - - fft_pred_low = tf.where(TFcircleIN, fft_pred, tf.zeros_like(fft_pred)) - fft_gt_low = tf.where(TFcircleIN, fft_gt, tf.zeros_like(fft_gt)) - fft_pred_high = tf.where(TFcircleOUT, fft_pred, tf.zeros_like(fft_pred)) - fft_gt_high = tf.where(TFcircleOUT, fft_gt, tf.zeros_like(fft_gt)) - - low_loss = tf.reduce_mean(tf.reduce_sum(tf.math.abs(fft_pred_low - fft_gt_low), axis=[1,2,3])) - high_loss = tf.reduce_mean(tf.reduce_sum(tf.math.abs(fft_pred_high - fft_gt_high), axis=[1,2,3])) - total = tf.reduce_mean(tf.reduce_sum(tf.math.abs(fft_pred - fft_gt), axis=[1,2,3])) - - return total, low_loss, high_loss - - # ex.imshow(tf.math.real(gt[0,0,:256,:])).show() - # img = tf.signal.fftshift(fft_gt[0][0]) - # ex.imshow(tf.math.abs(tf.math.log(img))).show() - # low = tf.where(TFcircleIN, img, tf.zeros_like(img)) - # ex.imshow(tf.math.real(tf.signal.ifft2d(tf.signal.ifftshift(low)))).show() - # high = tf.where(TFcircleOUT, img, tf.zeros_like(img)) - # # ex.imshow(tf.math.abs(tf.math.log(high))).show() - # ex.imshow(tf.math.real(tf.signal.ifft2d(tf.signal.ifftshift(high)))).show() - - - - - print() - - @tf.function def train_step(batch): with tf.GradientTape() as tape: - pred = model([batch['uv_body_posed'], batch['uv_mask']]) + pred = model(batch['uv_body_posed']) # pred = (pred + zero_body) * batch['mesh_mask'][:,:,tf.newaxis] mesh_pred = uv2mesh(pred) @@ -283,14 +106,12 @@ def train_step(batch): mesh_orig = batch['mesh_body_posed'] - e_loss = 1e-2 * tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask'])) + e_loss = 1e-2 * tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, tf.ones_like(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_body_posed'] - pred)), axis=1) * batch['uv_mask']) - ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(tf.transpose(pred, [0,2,3,1]) + 1, tf.transpose(batch['uv_body_posed'], [0,2,3,1]) + 1, max_val=2)) - rfft_loss = 0 #tf.reduce_mean(tf.reduce_sum(tf.math.abs(tf.signal.rfft3d(pred) - tf.signal.rfft3d(batch['uv_unposed'])), axis=[1,2,3])) + l1_loss = tf.reduce_mean(tf.reduce_sum(((tf.math.abs(batch['uv_body_posed'] - pred) * uv_mask_body[tf.newaxis,tf.newaxis,:,:])), axis=1)) + ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(tf.transpose(pred * uv_mask_body[tf.newaxis,tf.newaxis,:,:], [0,2,3,1]) + 1, tf.transpose(batch['uv_body_posed'] * uv_mask_body[tf.newaxis,tf.newaxis,:,:], [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_body_posed'], tf.zeros_like(batch['uv_body_posed'])))), axis=[1,2,3])) - fft_loss_pc, fft_loss_pc_low, fft_loss_pc_high = 0,0,0 #fft_loss_per_channel(pred, batch['uv_unposed']) # loss = fft_loss_pc # + e_loss + c_loss loss = 1e3 * (1 - ms_ssim) @@ -304,11 +125,11 @@ def train_step(batch): # 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/rfft_loss': rfft_loss, 'train/fft_oc_low': fft_loss_pc_low, 'train/fft_pc_high': fft_loss_pc_high, - 'train/fft_loss_per_channel': fft_loss_pc, 'train/euclid_error_posed': euclid_posed } + 'train/fft_loss': fft_loss, 'train/euclid_error_reconst': metric_2, 'train/euclid_error_posed': euclid_posed } +# UPDATE! @tf.function def valid_step(batch): pred = model([batch['uv_body_posed'], batch['uv_mask']]) @@ -332,7 +153,7 @@ def valid_step(batch): def plot_everything(batch: dict, type: str): - pred = model([batch['uv_body_posed'], batch['uv_mask']]) + pred = model(batch['uv_body_posed']) mesh_pred = uv2mesh(pred) mesh_orig = batch['mesh_body_posed'] @@ -417,12 +238,12 @@ if __name__ == '__main__': signature_static = { #'uv_static': (3, 512, 256,), # 'mesh_static': (14475, 3,), 'mesh_mask': (14475,), - 'uv_mask': (512, 256,), + # 'uv_mask': (512, 256,), # 'uv_shaped_body': (3, 512, 256,), } - dataset_train = factory.get_dataset(folder='/home/workspace/local-data/train_100', batch_size=32, signature=signature_dynamic, use_filled=False) - static_dataset_train = StaticDataset(folder='/home/workspace/local-data/train_100', signature=signature_static, use_filled=False) + dataset_train = factory.get_dataset(folder='/home/workspace/local-data/train_100', batch_size=32, signature=signature_dynamic, use_filled=True) + static_dataset_train = StaticDataset(folder='/home/workspace/local-data/train_100', signature=signature_static, use_filled=True) dataset_valid = factory.get_dataset(folder='/home/workspace/local-data/jumpsuit_20/valid', batch_size=32, signature=signature_dynamic) static_dataset_valid = StaticDataset(folder='/home/workspace/local-data/jumpsuit_20/valid', signature=signature_static) diff --git a/models/ae_body_model.py b/models/ae_body_model.py new file mode 100644 index 0000000..6e52c69 --- /dev/null +++ b/models/ae_body_model.py @@ -0,0 +1,80 @@ +import tensorflow as tf +from convnext.models.convnext_tf import ConvNeXt, ConvNeXtReverse, Block + + + + +class Bottleneck(tf.keras.Model): + + def __init__(self, dim, latent_dim): + super(Bottleneck, self).__init__() + + self.bottleneck = tf.keras.Sequential( + [Block(dim=dim, drop_path=0, + layer_scale_init_value=1e-6, prefix=f'bottleneck{j}') for j in range(5)] + ) + self.flatten = tf.keras.layers.Flatten() + self.dense = tf.keras.layers.Dense(latent_dim) + + def call(self, inputs, training=None): + x = inputs + + x = self.bottleneck(x) + x = self.flatten(x) + x = self.dense(x) + + return x + + +class Decoder(tf.keras.Model): + + def __init__(self, bottleneck_size, latent_dim): + super(Decoder, self).__init__() + + self.dense = tf.keras.layers.Dense(4 * 2 * bottleneck_size) + self.reshape = tf.keras.layers.Reshape((4, 2, bottleneck_size)) + self.decoder = ConvNeXtReverse(depths=list(reversed([3, 3, 9, 3])), dims=list(reversed([bottleneck_size, 128, 64, 16]))) + + def call(self, inputs, training=None): + x = inputs + + x = self.dense(x) + x = self.reshape(x) + x = self.decoder(x) + + return x + + +class AutoEncoder(tf.keras.Model): + + def __init__(self): + super(AutoEncoder, self).__init__() + + + bottleneck_size = 512 + latent_dim = 128 + + self.encoder = ConvNeXt(depths=[3, 3, 9, 9, 3, 3], dims=[32, 64, 128, 256, 256, bottleneck_size], include_top=False) + self.bottleneck = Bottleneck(bottleneck_size, latent_dim) + self.decoder = Decoder(bottleneck_size, latent_dim) + + + def call(self, inputs, training=None): + x = inputs + + x = tf.transpose(x, [0,2,3,1]) + x = self.encoder(x, training=training) + # x = self.pooling(x) + # x = self.reshape(x) + # x = self.flatten(x) + + x = self.bottleneck(x, training=training) + + x = self.decoder(x, training=training) + x = tf.image.resize(x, (512, 256), tf.image.ResizeMethod.LANCZOS5) + x = tf.transpose(x, [0,3,1,2]) + + # x = x * uv_mask[:,:, tf.newaxis] + # x = x * uv_mask_body[tf.newaxis,tf.newaxis,:,:] + + return x \ No newline at end of file