From c875a6a0caadf3e8b4f09a63becc2c2c9155b076 Mon Sep 17 00:00:00 2001 From: Hunor Laczko Date: Mon, 27 Feb 2023 12:49:18 +0000 Subject: [PATCH] more training --- aaa_helpers.txt | 10 +- configs/iccv/config_abl_all_skirt.py | 125 +++++++++++++++ configs/iccv/config_abl_pyr_32_skirt.py | 12 +- configs/iccv/config_abl_pyr_64_cape_f.py | 188 +++++++++++++++++++++++ cvae.py | 2 +- cvae_pyramid.py | 4 +- upscale_test.py | 6 +- 7 files changed, 333 insertions(+), 14 deletions(-) create mode 100644 configs/iccv/config_abl_all_skirt.py create mode 100644 configs/iccv/config_abl_pyr_64_cape_f.py diff --git a/aaa_helpers.txt b/aaa_helpers.txt index e748bae..1797eca 100644 --- a/aaa_helpers.txt +++ b/aaa_helpers.txt @@ -11,8 +11,13 @@ nohup python auto_encoder_curv.py --name="lhunor_curv_iccv_1" > nohup/iccv/encod nohup python auto_encoder_curv.py --name="lhunor_curv_iccv_1_skirt" > nohup/iccv/encoders/curv_iccv_1_skirt.out 2>&1 & nohup python auto_encoder_curv.py --name="lhunor_curv_iccv_1_cape_f" > nohup/iccv/encoders/curv_iccv_1_cape_f.out 2>&1 & nohup python auto_encoder_curv.py --name="lhunor_curv_iccv_1_cape_m" > nohup/iccv/encoders/curv_iccv_1_cape_m.out 2>&1 & +nohup python cvae.py --name="lhunor_cvae_iccv_gnn_1" > nohup/iccv/cvae_iccv_gnn_1.out 2>&1 & nohup python cvae.py --name="lhunor_abl_all" > nohup/iccv/ablation/abl_all.out 2>&1 & +nohup python cvae.py --name="lhunor_abl_all_gnn" > nohup/iccv/ablation/abl_all_gnn.out 2>&1 & +nohup python cvae.py --name="lhunor_abl_all_gnn_2" > nohup/iccv/ablation/abl_all_gnn.out 2>&1 & + +nohup python cvae.py --name="lhunor_abl_all_skirt" > nohup/iccv/ablation/abl_all_skirt.out 2>&1 & nohup python upscale_test.py --name="iccv_32_2" > nohup/iccv/upscale/iccv_32_2.out 2>&1 & nohup python upscale_test.py --name="iccv_64_2" > nohup/iccv/upscale/iccv_64_2.out 2>&1 & @@ -35,8 +40,9 @@ nohup python upscale_test.py --name="iccv_128_2_cape_m" > nohup/iccv/upscale/icc nohup python upscale_test.py --name="iccv_256_2_cape_m" > nohup/iccv/upscale/iccv_256_2_cape_m.out 2>&1 & nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32" > nohup/iccv/pyr/iccv_pyr_32.out 2>&1 & -nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_skirt" > nohup/iccv/pyr/iccv_pyr_32_skirt.out 2>&1 & -nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_cape_f" > nohup/iccv/pyr/iccv_pyr_32_cape_f.out 2>&1 & +nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_skirt" > nohup/iccv/pyr/iccv_pyr_32_skirt_2.out 2>&1 & + +nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_64_cape_f" > nohup/iccv/pyr/iccv_pyr_64_cape_f.out 2>&1 & skirts!!!! pyramid next week diff --git a/configs/iccv/config_abl_all_skirt.py b/configs/iccv/config_abl_all_skirt.py new file mode 100644 index 0000000..3b8a595 --- /dev/null +++ b/configs/iccv/config_abl_all_skirt.py @@ -0,0 +1,125 @@ +config = dict() + +# 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 AVG GARMENT USED + +config['use_skinning'] = True # and deshaping +config['remove_global_orientation'] = True +config['use_curvature'] = True +config['use_extra_losses'] = True # edge, collision, 3d mesh +config['use_offsets'] = True + +config['use_norm_loss'] = True + +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'] = '3' +config['name'] = 'abl_all_skirt' +config['notes'] = '' +config['tags'] = ['iccv', 'abl_all', 'skirt'] + +config['avg_garment_path'] = 'custom_data/train_no_shape_skirt_avg_uv.npy' #custom_data/train_no_shape_avg_uv.npy # train_no_shape_avg_uv train_no_shape_one_hot_avg_uv +if config['use_skinning']: + assert (config['use_offsets'] and config['avg_garment_path'] != '') or (not config['use_offsets'] and config['avg_garment_path'] == '') + +config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision + +config['batch_size'] = 4 +config['resolution'] = 512 +config['is_skirt'] = True +config['dataset_in_memory'] = False +config['is_cape'] = False + +config['train_dir'] = '/home/workspace/data/dataset/local-cache/train_skirt' +config['valid_dir'] = '/home/workspace/local-data/valid_skirt' +config['test_dir'] = '/home/workspace/data/dataset/test_skirt_ready_2' + +config['static_model'] = 'checkpoints/iccv/static_iccv_1_skirt' +config['body_model'] = 'checkpoints/iccv/body_iccv_1_skirt' +config['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_skirt' + + +config['smpl_res'] = 14475 +if config['is_cape']: + config['smpl_res'] = 3638 + +config['latent_dim'] = 128 + +config['pretrained_model'] = '' + +############### +config['lr'] = 0.0001# 0.0001 +############### +config['starting_balancing_coeff'] = 0.0001 + +config['signature_dynamic'] = { 'id': (), 'frame_nr': (), + 'pose_shape': (72 + 11,), + 'uv_body_posed': (512, 256, 3), + 'mesh_body_posed': (14475, 3,), + 'mesh_posed': (14475, 3,), + 'uv_curvature': (512, 256, 7), + } +config['signature_static'] = { 'uv_static': (512, 256, 3), + 'mesh_mask': (14475,), + 'uv_mask': (512, 256,), + } + +if config['use_skinning']: + config['signature_dynamic']['uv_unposed'] = (512, 256, 3) + config['signature_dynamic']['mesh_unposed'] = (14475, 3,) +else: + config['signature_dynamic']['uv_posed'] = (512, 256, 3) + + +config['upscale_enhancer'] = '' +config['freeze_encoders'] = True +config['use_one_hot'] = False +config['bottleneck_scale'] = 2 + +config['cvae'] = dict() +config['cvae']['is_label'] = False +config['cvae']['latent_dim'] = 64 * config['bottleneck_scale'] +config['cvae']['add_noise'] = False +config['cvae']['noise_amount'] = 0.0 + +config['cvae']['kernel_size'] = 7 +config['cvae']['encoder_depths'] = [3, 3, 3, 9, 3] +config['cvae']['encoder_dims'] = [32, 64, 128, 256, config['cvae']['latent_dim']] +config['cvae']['decoder_depths'] = config['cvae']['encoder_depths'] +config['cvae']['decoder_dims'] = config['cvae']['encoder_dims'] + + +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/configs/iccv/config_abl_pyr_32_skirt.py b/configs/iccv/config_abl_pyr_32_skirt.py index df4c444..02916fe 100644 --- a/configs/iccv/config_abl_pyr_32_skirt.py +++ b/configs/iccv/config_abl_pyr_32_skirt.py @@ -1,7 +1,7 @@ config = dict() config['gpu'] = '5' -config['name'] = 'iccv_pyr_32_skirt' +config['name'] = 'iccv_pyr_32_skirt_2' config['notes'] = '' config['tags'] = ['pyr', 'iccv'] @@ -33,7 +33,7 @@ config['train_dir'] = '/home/workspace/data/dataset/local-cache/train_skirt' config['valid_dir'] = '/home/workspace/local-data/valid_skirt' config['test_dir'] = '/home/workspace/data/dataset/test_skirt_ready_2' config['batch_size'] = 4 -config['is_skirt'] = False +config['is_skirt'] = True config['is_cape'] = False config['dataset_in_memory'] = False @@ -79,9 +79,9 @@ for res in config['pyramid']['resolutions']: config['signature_static']['uv_mask' + res_modifier] = (res, res//2) -config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1' -config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1' -config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1' +config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1_skirt' +config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1_skirt' +config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_skirt' config['pyramid']['freeze_encoders'] = True @@ -151,7 +151,7 @@ for res in config['pyramid']['resolutions']: level['decoder_depths'] = level['encoder_depths'] level['decoder_dims'] = level['encoder_dims'] level['avg_garment_path'] = '' - level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2'#'checkpoints/up_3_d32_64_2' + level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2_skirt'#'checkpoints/up_3_d32_64_2' level['upscale_enhancer_freeze'] = True config['pyramid']['levels'].append(level) else: diff --git a/configs/iccv/config_abl_pyr_64_cape_f.py b/configs/iccv/config_abl_pyr_64_cape_f.py new file mode 100644 index 0000000..44dbbdc --- /dev/null +++ b/configs/iccv/config_abl_pyr_64_cape_f.py @@ -0,0 +1,188 @@ +config = dict() + +config['gpu'] = '6' +config['name'] = 'iccv_pyr_64_cape_f' +config['notes'] = '' +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['pretrained_model'] = '' +config['pretrained_model_iteration'] = '' + +config['pyramid'] = dict() +config['pyramid']['resolutions'] = [64] +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/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'] = 0.0001 +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'] = [16, 9, 9, 9] + level['encoder_dims'] = [64, 128, 128, 64] + level['decoder_input'] = (4, 2, 128) + level['decoder_depths'] = [16, 9, 9, 9] + level['decoder_dims'] = [256, 128, 128, level['latent_dim']] + level['avg_garment_path'] = '' + level['upscale_enhancer'] = 'checkpoints/iccv/iccv_'#'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.py b/cvae.py index 7964455..9dd6994 100644 --- a/cvae.py +++ b/cvae.py @@ -1,6 +1,6 @@ import os import sys -from configs.iccv.config_abl_all import config +from configs.iccv.config_abl_all_skirt import config os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu'] import tensorflow as tf diff --git a/cvae_pyramid.py b/cvae_pyramid.py index b1a5f5d..ef9e5d8 100644 --- a/cvae_pyramid.py +++ b/cvae_pyramid.py @@ -1,6 +1,6 @@ import os import sys -from configs.iccv.config_abl_pyr_32_cape_f import config +from configs.iccv.config_abl_pyr_64_cape_f import config os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu'] import tensorflow as tf @@ -60,7 +60,7 @@ def init_wandb(): artifact.add_file('models/cond_encoder.py') artifact.add_file('dataset.py') artifact.add_file('convnext/models/convnext_tf.py') - config_file_names = [key for key in sys.modules.keys() if key.startswith('configs.post.')] + config_file_names = [key for key in sys.modules.keys() if key.startswith('configs.')] for config_file_name in config_file_names: file_name = '/'.join(config_file_name.split('.')) + '.py' if os.path.exists(file_name): diff --git a/upscale_test.py b/upscale_test.py index 172e7ec..315bafe 100644 --- a/upscale_test.py +++ b/upscale_test.py @@ -36,9 +36,9 @@ from models.upscaler import UpscalerBasicConv as Upscaler # !!!!!!!!!! CHANGE SKIRT OR NOT -low_res = 256 -is_skirt = True -is_cape = False +low_res = 128 +is_skirt = False +is_cape = True is_male = False skirt_modifier = '_skirt' if is_skirt else '' cape_modifier = '_cape' if is_cape else ''