diff --git a/aaa_helpers.txt b/aaa_helpers.txt index f8ea6ae..50e6430 100644 --- a/aaa_helpers.txt +++ b/aaa_helpers.txt @@ -1,3 +1,6 @@ +nohup python cvae.py --name="lhunor_weights_test_2" > nohup/iccv/weights_test.out 2>&1 & + + one final convolutional layer for smoothing, on the final coordinates skirts!!!! diff --git a/configs/config_abl_all_post.py b/configs/config_abl_all_post.py index 5093733..c45040a 100644 --- a/configs/config_abl_all_post.py +++ b/configs/config_abl_all_post.py @@ -7,7 +7,7 @@ config = dict() # DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512 # DON'T FORGET TO CHECK AVG GARMENT USED -config['use_skinning'] = True # and deshaping +config['use_skinning'] = False # and deshaping config['remove_global_orientation'] = True config['use_curvature'] = True config['use_extra_losses'] = True # edge, collision, 3d mesh @@ -19,8 +19,8 @@ config['only_curvatures'] = False ablation_count = [config['use_skinning'], config['remove_global_orientation'], config['use_curvature'], config['use_extra_losses'], config['use_offsets']].count(False) assert ablation_count == 1 or ablation_count == 0 -config['gpu'] = '1' -config['name'] = 'al_all_post' +config['gpu'] = '5' +config['name'] = 'iccv_weights_test_3' config['notes'] = '' config['avg_garment_path'] = 'custom_data/train_no_shape_avg_uv.npy' #custom_data/train_no_shape_avg_uv.npy # train_no_shape_avg_uv train_no_shape_one_hot_avg_uv @@ -53,7 +53,7 @@ if config['is_cape']: config['smpl_res'] = 3638 -config['pretrained_model'] = '' +config['pretrained_model'] = ''#'checkpoints/post/iccv_weights_test_2' ############### config['lr'] = 0.0001# 0.0001 @@ -86,7 +86,7 @@ config['use_one_hot'] = False config['cvae'] = dict() config['cvae']['is_label'] = False config['cvae']['add_noise'] = True -config['cvae']['noise_amount'] = 0.001 +config['cvae']['noise_amount'] = 0.00001 config['cvae']['kernel_size'] = 7 config['cvae']['encoder_depths'] = [3, 3, 3, 9, 3] diff --git a/convnext/models/convnext_tf.py b/convnext/models/convnext_tf.py index d570c30..5759ecd 100644 --- a/convnext/models/convnext_tf.py +++ b/convnext/models/convnext_tf.py @@ -2,7 +2,7 @@ from unittest import skip import numpy as np import tensorflow as tf from tensorflow.keras.layers import (Conv2D, Conv2DTranspose, Dense, DepthwiseConv2D, - GlobalAveragePooling2D, Layer, + GlobalAveragePooling2D, Layer, Activation, Lambda, LayerNormalization, Flatten, Reshape, UpSampling2D) def drop_path(inputs, drop_prob, is_training): @@ -257,12 +257,25 @@ class ConvNeXtReverse(tf.keras.Model): self.last = Dense(3, activation='tanh') + self.weights_model = tf.keras.Sequential([Block(dim=dims[-1]*2, kernel_size=kernel_size), + Block(dim=dims[-1]*2, kernel_size=kernel_size), + Block(dim=dims[-1]*2, kernel_size=kernel_size), + Flatten(), + Dense(128 * 24), + Reshape((24, 128)), + Dense(14475), + Lambda(lambda x: tf.transpose(x, (0, 2, 1))), + Lambda(lambda x: tf.nn.softmax(x, axis=-1))]) + def call(self, x, training): + weights = self.weights_model(x, training=training) + for i in reversed(range(len(self.upsample_layers))): x = self.upsample_layers[i](x, training=training) x = self.stages[i](x, training=training) + x = self.last(x, training=training) - return x + return x, weights class ConvNeXtReverseWithSkip(tf.keras.Model): diff --git a/custom_utils/custom_utils.py b/custom_utils/custom_utils.py index 77508c1..db0fcf2 100644 --- a/custom_utils/custom_utils.py +++ b/custom_utils/custom_utils.py @@ -2,6 +2,7 @@ import json import numpy as np import tensorflow as tf import scipy as sp +import cmapy as cm import plotly.graph_objects as go from plotly.subplots import make_subplots @@ -216,6 +217,35 @@ def plot_3d(mesh_gt, mesh_pred_unposed, faces, collision, collision_faces, colli return fig +def plot_weights(weights, body, faces): + fig = go.Figure() + colors = np.array([cm.color('jet', 1 - w) for w in weights.numpy()]) + + # if flip_xy: + # mesh_gt = flip_axis(mesh_gt) + # mesh_pred_unposed = flip_axis(mesh_pred_unposed) + # collision = flip_axis(collision, ind=14475) + + fig.add_trace(go.Mesh3d( + x=body[:,0], + y=body[:,2], + z=body[:,1], + i = faces[:,0], + j = faces[:,1], + k = faces[:,2], + vertexcolor=colors + )) + + + fig.update_layout(scene_aspectmode='manual', scene_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,) + + return fig + + def plot_3d_collision(gt, collision_1, collision_2, collision_faces, collision_color, flip_xy=False): fig = make_subplots(rows=1, cols=3, start_cell="top-left", specs = [ [{ 'type': 'scene' } for _ in range(3)] ]) diff --git a/custom_utils/smpl.py b/custom_utils/smpl.py index 77d09c6..7f155c8 100644 --- a/custom_utils/smpl.py +++ b/custom_utils/smpl.py @@ -406,7 +406,8 @@ class SMPL: return T_out, J_out - def run_garment_with_weights(self, R, betas, v_cloth, weights, J=None): + def run_garment_with_weights(self, pose, betas, v_cloth, weights, J=None): + R = self.run_rodrigues(pose) if J is None: J = self.get_joints_template(betas) @@ -430,13 +431,12 @@ class SMPL: J = tf.gather(J, tf.constant([0, 1, 2], tf.int32), axis=1) T = tf.tensordot(weights, results, axes=((1), (0))) - rest_shape_h = tf.concat((v_cloth, tf.ones((v_cloth.get_shape().as_list()[0], 1), dtype=tf.float32)), axis=1) + rest_shape_h = tf.concat((v_cloth, tf.ones((v_cloth.shape[0], 1), dtype=tf.float32)), axis=1) v = tf.matmul(T, tf.reshape(rest_shape_h, (-1, 4, 1))) v = tf.reshape(v, (-1, 4))[:, :3] return v, tf.squeeze(J) - # gender = tf.cast(tf.greater_equal(betas[:, 10] , 0), tf.int32) T_out, J_out = tf.map_fn(single_run, (R, J, v_cloth, weights), (tf.float32, tf.float32)) J0 = tf.reshape(J_out[:,0,:], (-1, 1, 3)) diff --git a/cvae.py b/cvae.py index 59d7c75..74eb621 100644 --- a/cvae.py +++ b/cvae.py @@ -38,7 +38,7 @@ else: from losses import collision_ratio, kl_loss, normal_loss #, concept_loss # from losses import collision_penalty as collision_penalty from losses import collision_loss as collision_penalty -from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d, UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision +from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d, UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision, plot_weights from dataset import DatasetFactory, StaticDataset from custom_utils.smpl import SMPL from models.cvae_model import CVAENew as CVAE @@ -71,9 +71,15 @@ def kl_loss(mean, logvar): return kl_loss +def blend_weights_reg(pred_w): + orig = smpl.weights + l1 = tf.reduce_mean(tf.abs(pred_w - orig[None, 0, :, :])) + return l1 * 1e-3 + + # 3d loss on posed !!!!!!!!!!!! -# @tf.function +@tf.function def train_step(batch): with tf.GradientTape() as tape: @@ -82,7 +88,7 @@ def train_step(batch): else: mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed'] - pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=True) + pred, mean, logvar, weights = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=True) mesh_pred = uv2mesh(pred) @@ -94,25 +100,26 @@ def train_step(batch): mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis] mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped) else: - mesh_pred_posed = mesh_pred + mesh_pred_posed = smpl.run_garment_with_weights(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred, weights) # is the output already masked? e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask'])) c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask']) c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio) - l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2])) + # l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2])) l2_mesh_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, axis=-1), axis=-1)) n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape']) # conc_loss = concept_loss(pred, batch['uv_unposed']) kl = kl_loss(mean, logvar) + weights_l = blend_weights_reg(weights) - reconstr_loss = l2_loss + reconstr_loss = l2_mesh_loss + weights_l if config['use_extra_losses']: if 'block_collision_loss' in config.keys() and config['block_collision_loss'] == True: - reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss) * config['reg_loss_coeff'] + reconstr_loss = reconstr_loss + (e_loss) * config['reg_loss_coeff'] else: - reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss + c_loss) * config['reg_loss_coeff'] + reconstr_loss = reconstr_loss + (e_loss + c_loss) * config['reg_loss_coeff'] if config['use_norm_loss'] and step > 2000: reconstr_loss = reconstr_loss + n_loss * config['reg_loss_coeff'] @@ -128,8 +135,8 @@ def train_step(batch): return { 'train/loss': loss, 'train/edge_loss': e_loss, 'train/collision_loss': c_loss, 'train/euclid_error': metric, 'train/reconstr_loss': reconstr_loss, 'train/collision_ratio': c_ratio, 'train/mean': mean, 'train/logvar': logvar, 'train/kl_loss': kl, 'train/var': np.e ** logvar, - 'train/l2_loss': l2_loss, 'train/l2_mesh_loss': l2_mesh_loss, 'train/normal_loss': n_loss, - # 'train/ms_ssim': ms_ssim, + 'train/l2_mesh_loss': l2_mesh_loss, 'train/normal_loss': n_loss, 'train/weights_loss': weights_l, + # 'train/ms_ssim': ms_ssim, 'train/l2_loss': l2_loss, } @@ -140,7 +147,7 @@ def valid_step(batch): else: mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed'] - pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False) + pred, mean, logvar, weights = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False) mesh_pred = uv2mesh(pred) @@ -152,22 +159,23 @@ def valid_step(batch): mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis] mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped) else: - mesh_pred_posed = mesh_pred + mesh_pred_posed = smpl.run_garment_with_weights(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred, weights) # is the output already masked? e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask'])) c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask']) c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio) - l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2])) + # l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2])) l2_mesh_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, axis=-1), axis=-1)) n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape']) # conc_loss = concept_loss(pred, batch['uv_unposed']) kl = kl_loss(mean, logvar) + weights_l = blend_weights_reg(weights) - reconstr_loss = l2_loss + reconstr_loss = l2_mesh_loss + weights_l if config['use_extra_losses']: - reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss + c_loss) * config['reg_loss_coeff'] + reconstr_loss = reconstr_loss + (e_loss + c_loss) * config['reg_loss_coeff'] if config['use_norm_loss']: reconstr_loss = reconstr_loss + n_loss * config['reg_loss_coeff'] @@ -182,7 +190,7 @@ def valid_step(batch): return { 'valid/loss': loss, 'valid/edge_loss': e_loss, 'valid/collision_loss': c_loss, 'valid/euclid_error': metric, 'valid/reconstr_loss': reconstr_loss, 'valid/l2_mesh_loss': l2_mesh_loss, 'valid/collision_ratio': c_ratio, - 'valid/mean': mean, 'valid/logvar': logvar, 'valid/kl_loss': kl, 'valid/var': np.e ** logvar, + 'valid/mean': mean, 'valid/logvar': logvar, 'valid/kl_loss': kl, 'valid/var': np.e ** logvar, 'valid/weights_loss': weights_l, 'valid/normal_loss': n_loss,# 'valid/ms_ssim': ms_ssim, } @@ -194,7 +202,7 @@ def test_step(batch): else: mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed'] - pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False) + pred, mean, logvar, weights = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False) mesh_pred = uv2mesh(pred) @@ -208,7 +216,7 @@ def test_step(batch): mesh_orig_shaped = mesh_orig + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis] mesh_orig_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_orig_shaped) else: - mesh_pred_posed = mesh_pred + mesh_pred_posed = smpl.run_garment_with_weights(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred, weights) mesh_orig_posed = mesh_orig mesh_pred_posed_fixed = fix_collision(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask']) @@ -250,7 +258,7 @@ def plot_everything(batch: dict, type: str): else: mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed'] - pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False) + pred, mean, logvar, weights = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False) mesh_pred = uv2mesh(pred).numpy() @@ -277,7 +285,7 @@ def plot_everything(batch: dict, type: str): mesh_pred[i, mask[i], :] += shape_offsets.numpy()[i, mask[i], :] mesh_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred).numpy() else: - mesh_posed = mesh_pred + mesh_posed = smpl.run_garment_with_weights(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred, weights).numpy() gt = [mesh_orig[i].numpy()[mask[i], :] for i in range(pred.shape[0])] garment_unposed, faces = maskFacesBatch(mesh_pred, F, mask) @@ -296,13 +304,16 @@ def plot_everything(batch: dict, type: str): collision_fixed = [np.concatenate((body[i], garment_posed_fixed[i]), axis=0) for i in range(len(garment_posed))] collision_gt = [np.concatenate((body[i], gt_posed[i]), axis=0) for i in range(len(garment_posed))] + # figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], faces[i], garment_posed[i], faces[i], collision_color[i], flip_xy=(not config['use_skinning'] and config['remove_global_orientation'])) for i in range(4) } figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], faces[i], collision[i], collision_faces[i], collision_color[i], flip_xy=(not config['use_skinning'] and config['remove_global_orientation'])) for i in range(4) } figs_coll = { type + "/garment_" + str(i) + '_collision': plot_3d_collision(collision_gt[i], collision[i], collision_fixed[i], collision_faces[i], collision_color[i], flip_xy=(not config['use_skinning'] and config['remove_global_orientation'])) for i in range(4) } + figs_weights = { type + '/weights_' + str(i): plot_weights(weights[0,:,i], body[0], F) for i in range(24) } + # figs_weights = { type + '/weights_' + str(i): plot_weights(smpl.weights[0,:,i], body[0], F) for i in range(24) } mean_hist = wandb.Histogram(sequence=mean.numpy().mean(axis=0)) logvar_hist = wandb.Histogram(sequence=logvar.numpy().mean(axis=0)) - return { **figs, **figs_coll, **{ type + '/images': imgs, type + '/mean_hist': mean_hist, type + '/logvar_hist': logvar_hist } } + return { **figs, **figs_coll, **figs_weights, **{ type + '/images': imgs, type + '/mean_hist': mean_hist, type + '/logvar_hist': logvar_hist } } def sample(folder): @@ -476,7 +487,7 @@ def test(): if __name__ == '__main__': - # init_wandb() + init_wandb() parser = argparse.ArgumentParser(description='') parser.add_argument('--name', type=str) args = vars(parser.parse_args()) diff --git a/models/cvae_model.py b/models/cvae_model.py index 3ed4571..b4cf805 100644 --- a/models/cvae_model.py +++ b/models/cvae_model.py @@ -193,12 +193,12 @@ class CVAENew(tf.keras.Model): self.noise_amount = config['cvae']['noise_amount'] self.use_curvature = config['use_curvature'] self.only_curvatures = config['only_curvatures'] if 'only_curvatures' in config.keys() and config['only_curvatures'] == True else None - self.use_offsets_over_body = not config['use_skinning'] + self.use_offsets_over_body = False if self.use_offsets_over_body: assert self.avg_garment is None, 'When we are not using skinning, we can\'t use avg_garment!' - if self.avg_garment is not None: - assert not self.use_offsets_over_body, 'When avg_garment is given, we must use skinning!' + # if self.avg_garment is not None: + # assert not self.use_offsets_over_body, 'When avg_garment is given, we must use skinning!' # @tf.function def sample(self, uv_template, uv_body_posed, uv_curv, uv_mask, noise=None, add_noise=False): @@ -213,7 +213,7 @@ class CVAENew(tf.keras.Model): z = tf.concat([eps, z_cond], axis=-1) - x = self.decoder(z, training=False) + x, weights = self.decoder(z, training=False) if self.avg_garment is not None: x = x + self.avg_garment[tf.newaxis,:,:,:] @@ -223,7 +223,7 @@ class CVAENew(tf.keras.Model): x = x * uv_mask[:,:,:,tf.newaxis] - return x + return x, weights def reparameterize(self, mean, logvar, training, fix_noise=False): @@ -271,7 +271,7 @@ class CVAENew(tf.keras.Model): z = tf.concat([z, z_cond], axis=-1) - x = self.decoder(z, training=training) + x, weights = self.decoder(z, training=training) if self.avg_garment is not None: x = x + self.avg_garment[tf.newaxis,:,:,:] @@ -281,5 +281,5 @@ class CVAENew(tf.keras.Model): x = x * uv_mask[:,:,:,tf.newaxis] - return x, mean, logvar + return x, mean, logvar, weights