diff --git a/aaa_helpers.txt b/aaa_helpers.txt index 4994f34..3a15e57 100644 --- a/aaa_helpers.txt +++ b/aaa_helpers.txt @@ -86,7 +86,7 @@ nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_64_cape_f_03223_SL" > nohup nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_64_cape_f_03223_SS" > nohup/iccv/pyr/iccv_pyr_64_cape_f_03223_SS.out 2>&1 & nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_64_128_cape_f" > nohup/iccv/pyr/iccv_pyr_64_128_cape_f.out 2>&1 & -nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_64_pre_cape_f" > nohup/iccv/pyr/iccv_pyr_64_pre_cape_f.out 2>&1 & +nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_pre_cape_f" > nohup/iccv/pyr/iccv_pyr_32_64_128_pre_cape_f.out 2>&1 & nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128" > nohup/iccv/pyr/iccv_pyr_32_64_128.out 2>&1 & nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_skirt" > nohup/iccv/pyr/iccv_pyr_32_64_128_skirt.out 2>&1 & diff --git a/calculate_error.py b/calculate_error.py index 9f13451..e9e71e7 100644 --- a/calculate_error.py +++ b/calculate_error.py @@ -1,6 +1,6 @@ import os import sys -from configs.iccv.config_abl_pyr_32_64_skin import config +from configs.iccv.config_abl_pyr_32_64_128_skirt import config os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu'] # import tensorflow as tf diff --git a/configs/iccv/config_abl_pyr_32_64_128_pre_cape_f.py b/configs/iccv/config_abl_pyr_32_64_128_pre_cape_f.py new file mode 100644 index 0000000..f256c32 --- /dev/null +++ b/configs/iccv/config_abl_pyr_32_64_128_pre_cape_f.py @@ -0,0 +1,188 @@ +config = dict() + +config['gpu'] = '2' +config['name'] = 'iccv_pyr_32_64_128_pre_cape_f' +config['notes'] = 'load pretrained on cloth3d' +config['tags'] = ['pyr', 'iccv', 'cape_f'] + +# DON'T FORGET TO RESET SSIM LOSS USAGE +# DON'T FORGET TO CHECK MODEL LOADING +# DON'T FORGET TO CHECK IF STORE IN MEMORY +# DON'T FORGET TO CHECK REG LOSS COEFF +# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512 +# DON'T FORGET TO CHECK IF SKIRT +# DON'T FORGET TO CHECK IF CAPE +# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2 +# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS + +config['use_skinning'] = True # and deshaping +config['remove_global_orientation'] = True +config['use_extra_losses'] = True # edge, collision, 3d mesh +config['use_offsets'] = False +config['use_norm_loss'] = True +config['use_curvature'] = True + +config['pretrained_model'] = 'checkpoints/iccv/iccv_pyr_32_64_128' +config['pretrained_model_iteration'] = '' + +config['pyramid'] = dict() +config['pyramid']['resolutions'] = [32, 64, 128] +config['pyramid']['pretrained_pyramid'] = '' +config['pyramid']['final_upscale_enhancer'] = '' + +config['train_dir'] = '/home/workspace/local-data/cape_processed/train/female' +config['valid_dir'] = '/home/workspace/local-data/cape_processed/test/female' +config['test_dir'] = '/home/workspace/local-data_127/cape_processed/test/female' +config['batch_size'] = 4 +config['is_skirt'] = False +config['is_cape'] = True + +config['dataset_in_memory'] = False +config['resolution'] = None + +config['smpl_res'] = 14475 +if config['is_cape']: + config['smpl_res'] = 3638 + +config['lr'] = 0.00001 +config['starting_balancing_coeff'] = 0.001 +config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision +config['avg_garment_path'] = '' +config['bottleneck_scale'] = 2 + +config['signature_dynamic'] = { 'id': (), 'frame_nr': (), + 'pose_shape': (72 + 11,), + 'uv_body_posed': (512, 256, 3), + 'mesh_body_posed': (config['smpl_res'], 3,), + 'mesh_posed': (config['smpl_res'], 3,), + 'mesh_unposed': (config['smpl_res'], 3,), + 'uv_unposed': (512, 256, 3), + 'uv_curvature': (512, 256, 7), + } +config['signature_static'] = { 'uv_static': (512, 256, 3), + 'mesh_mask': (config['smpl_res'],), + 'uv_mask': (512, 256,), + } + +config['pyramid']['is_label'] = False +config['pyramid']['add_noise'] = False +config['pyramid']['noise_amount'] = 0.0 + +config['pyramid']['loss_weights'] = [1,1,1,1,1] + +for res in config['pyramid']['resolutions']: + if res != 512: + res_modifier = '_' + str(res) + config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3) + config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3) + config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7) + config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3) + config['signature_static']['uv_mask' + res_modifier] = (res, res//2) + + +config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1_cape_f' +config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1_cape_f' +config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_cape_f' +config['pyramid']['freeze_encoders'] = True + + +config['pyramid']['levels'] = [] +for res in config['pyramid']['resolutions']: + if res == 512: + level = dict() + level['resolution'] = 512 + level['latent_dim'] = 64 * config['bottleneck_scale'] + level['kernel_size'] = 7 + level['encoder_depths'] = [3, 3, 9, 3] + level['encoder_dims'] = [32, 64, 128, level['latent_dim']] + level['decoder_input'] = (16, 8, 80) + level['decoder_depths'] = [3, 3, 9, 3] + level['decoder_dims'] = [256, 128, 64, 16] + level['avg_garment_path'] = '' + level['upscale_enhancer'] = '' + config['pyramid']['levels'].append(level) + elif res == 256: + level = dict() + level['resolution'] = 256 + level['latent_dim'] = 64 * config['bottleneck_scale'] + level['kernel_size'] = 5 + level['encoder_depths'] = [9, 9, 9, 9] + level['encoder_dims'] = [32, 64, 128, level['latent_dim']] + level['decoder_input'] = (8, 4, 128) + level['decoder_depths'] = [9, 9, 9, 9] + level['decoder_dims'] = [256, 128, 64, 16] + level['avg_garment_path'] = '' + level['upscale_enhancer'] = 'checkpoints/iccv/iccv_'#'checkpoints/up_3_d256_512_2' + level['upscale_enhancer_freeze'] = True + config['pyramid']['levels'].append(level) + elif res == 128: + level = dict() + level['resolution'] = 128 + level['latent_dim'] = 64 * config['bottleneck_scale'] + level['kernel_size'] = 5 + level['encoder_depths'] = [9, 9, 9] + level['encoder_dims'] = [128, 128, level['latent_dim']] + level['decoder_depths'] = level['encoder_depths'] + level['decoder_dims'] = level['encoder_dims'] + level['avg_garment_path'] = '' + level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2_cape_f'#'checkpoints/up_3_d128_256_2' + level['upscale_enhancer_freeze'] = True + config['pyramid']['levels'].append(level) + elif res == 64: + level = dict() + level['resolution'] = 64 + level['latent_dim'] = 64 * config['bottleneck_scale'] + level['kernel_size'] = 3 + level['encoder_depths'] = [9, 9] + level['encoder_dims'] = [64, level['latent_dim']] + level['decoder_depths'] = level['encoder_depths'] + level['decoder_dims'] = level['encoder_dims'] + level['avg_garment_path'] = '' + level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2_cape_f'#checkpoints/up_3_d64_128_2' + level['upscale_enhancer_freeze'] = True + config['pyramid']['levels'].append(level) + elif res == 32: + level = dict() + level['resolution'] = 32 + level['latent_dim'] = 64 * config['bottleneck_scale'] + level['kernel_size'] = 3 + level['encoder_depths'] = [16] + level['encoder_dims'] = [level['latent_dim']] + level['decoder_depths'] = level['encoder_depths'] + level['decoder_dims'] = level['encoder_dims'] + level['avg_garment_path'] = '' + level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2_cape_f'#'checkpoints/up_3_d32_64_2' + level['upscale_enhancer_freeze'] = True + config['pyramid']['levels'].append(level) + else: + raise NotImplementedError + +config['cond_ae_static'] = dict() +config['cond_ae_static']['is_label'] = False +config['cond_ae_static']['kernel_size'] = 7 +config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale'] +config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3] +config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']] +config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths'] +config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims'] +config['cond_ae_static']['activation'] = 'tanh' + +config['cond_ae_curv'] = dict() +config['cond_ae_curv']['is_label'] = True +config['cond_ae_curv']['kernel_size'] = 7 +config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale'] +config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3] +config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']] +config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths'] +config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims'] +config['cond_ae_curv']['activation'] = 'tanh' + +config['cond_ae_body'] = dict() +config['cond_ae_body']['is_label'] = False +config['cond_ae_body']['kernel_size'] = 7 +config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale'] +config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3] +config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']] +config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths'] +config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims'] +config['cond_ae_body']['activation'] = 'tanh' \ No newline at end of file diff --git a/cvae_pyramid.py b/cvae_pyramid.py index e1a7811..154f432 100644 --- a/cvae_pyramid.py +++ b/cvae_pyramid.py @@ -1,6 +1,6 @@ import os import sys -from configs.iccv.config_abl_pyr_64_pre_cape_f import config +from configs.iccv.config_abl_pyr_32_64_128_pre_cape_f import config os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu'] import tensorflow as tf @@ -220,65 +220,70 @@ def train_step(batch): out_levels = model([levels_input, conds], training=True) if config['use_skinning']: - mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed'] + mesh_orig = batch['mesh_unposed'] else: - mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed'] + mesh_orig = batch['mesh_posed'] output = dict() reconstr_loss_total = 0 kl_total = 0 - #for i, res in enumerate(config['pyramid']['resolutions']): - i = -1 - res = config['pyramid']['resolutions'][-1] - res_modifier = '_' + str(res) if res != 512 else '' - pred, mean, logvar = out_levels[i] + for i, res in enumerate(config['pyramid']['resolutions']): + # i = -1 + res = config['pyramid']['resolutions'][i] if i != len(config['pyramid']['resolutions']) - 1 else 512 + res_modifier = '_' + str(res) if res != 512 else '' + pred, mean, logvar = out_levels[i] - mesh_pred = uv2mesh(pred) + if config['use_skinning']: + uv_orig = batch['uv_unposed' + res_modifier] + else: + uv_orig = batch['uv_posed' + res_modifier] - if config['use_skinning']: - shape = batch['pose_shape'][:, 72:] - gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32) - shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])]) + mesh_pred = uv2mesh(pred) - 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 + if config['use_skinning']: + shape = batch['pose_shape'][:, 72:] + gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32) + shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])]) - # is the output already masked? + 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 - 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])) - # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1))) - # ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3)) - 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']) - kl = kl_loss(mean, logvar) + # is the output already masked? - 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'] - else: - reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss) + 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) * batch['uv_mask' + res_modifier], axis=[1, 2])) + # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1))) + # ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3)) + 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']) + kl = kl_loss(mean, logvar) - if config['use_norm_loss'] and step > 2000: - reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff'] - - kl_total += kl + 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'] + else: + reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss) - mean = tf.reduce_mean(mean) - logvar = tf.reduce_mean(logvar) + if config['use_norm_loss'] and step > 2000: + reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff'] + + kl_total += kl - 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']) + mean = tf.reduce_mean(mean) + logvar = tf.reduce_mean(logvar) - 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, + 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']) + + 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, loss = reconstr_loss_total + balancing_coeff * kl_total @@ -294,64 +299,69 @@ def valid_step(batch): if config['use_skinning']: - mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed'] + mesh_orig = batch['mesh_unposed'] else: - mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed'] + mesh_orig = batch['mesh_posed'] output = dict() reconstr_loss_total = 0 kl_total = 0 - #for i, res in enumerate(config['pyramid']['resolutions']): - i = -1 - res = config['pyramid']['resolutions'][-1] - res_modifier = '_' + str(res) if res != 512 else '' - pred, mean, logvar = out_levels[i] + for i, res in enumerate(config['pyramid']['resolutions']): + # i = -1 + res = config['pyramid']['resolutions'][i] if i != len(config['pyramid']['resolutions']) - 1 else 512 + res_modifier = '_' + str(res) if res != 512 else '' + pred, mean, logvar = out_levels[i] - mesh_pred = uv2mesh(pred) + if config['use_skinning']: + uv_orig = batch['uv_unposed' + res_modifier] + else: + uv_orig = batch['uv_posed' + res_modifier] - if config['use_skinning']: - shape = batch['pose_shape'][:, 72:] - gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32) - shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])]) + mesh_pred = uv2mesh(pred) - 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 - # is the output already masked? + if config['use_skinning']: + shape = batch['pose_shape'][:, 72:] + gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32) + shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])]) - 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])) - # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1))) - # ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3)) - 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']) - kl = kl_loss(mean, logvar) + 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 + # is the output already masked? - 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'] - else: - reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss) - - if config['use_norm_loss'] and step > 2000: - reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff'] + 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) * batch['uv_mask' + res_modifier], axis=[1, 2])) + # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1))) + # ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3)) + 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']) + 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'] + else: + reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss) - kl_total += kl + if config['use_norm_loss'] and step > 2000: + reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff'] + + kl_total += kl - mean = tf.reduce_mean(mean) - logvar = tf.reduce_mean(logvar) + mean = tf.reduce_mean(mean) + logvar = tf.reduce_mean(logvar) - 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 = 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']) - 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, + 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, loss = reconstr_loss_total + balancing_coeff * kl_total @@ -810,7 +820,7 @@ if __name__ == '__main__': if config['use_curvature']: model.curv_enc.trainable = False else: - load_model(model, config['pyramid']['pretrained_pyramid'], iteration=(config['pyramid']['pretrained_pyramid_iteration'] if 'pretrained_pyramid_iteration' in config.keys() else '')) + # load_model(model, config['pyramid']['pretrained_pyramid'], iteration=(config['pyramid']['pretrained_pyramid_iteration'] if 'pretrained_pyramid_iteration' in config.keys() else '')) model.static_enc.trainable = False model.body_enc.trainable = False if config['use_curvature']: @@ -828,8 +838,8 @@ if __name__ == '__main__': # load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer']) # model.upscale_enhancer.trainable = False - for i in range(len(model.levels)-1): - model.levels[i].trainable = False + # for i in range(len(model.levels)-1): + # model.levels[i].trainable = False # load_model(model.cond_encoder, config['pyramid']['pretrained_pyramid']) # load_model(model.levels[0], config['pyramid']['pretrained_pyramid']) diff --git a/models/pyramid_model_optimized.py b/models/pyramid_model_optimized.py index cee812b..0bb05b9 100644 --- a/models/pyramid_model_optimized.py +++ b/models/pyramid_model_optimized.py @@ -335,8 +335,8 @@ class PyramidNew(tf.keras.Model): pred = pred + levels_input[0][2] # uv_body_posed_32 if 1 != len(self.levels): pred = self.levels[0].enhance(pred, levels_input[0][-2], training=training) # levels_input[i][-2]=uv_mask_res - pred = tf.image.resize(pred, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.BILINEAR) out_levels.append([pred, mean, logvar]) + pred = tf.image.resize(pred, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.BILINEAR) pred = pred * levels_input[1][-2][:,:,:,tf.newaxis] else: # pred = self.enhance(pred, levels_input[0][-2], training=training)