finetune

aaa_helpers.txt

@@ -150,6 +150,7 @@ nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_256_512_skirt" >
 nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_256_512_skin" > nohup/iccv/pyr/iccv_pyr_32_64_128_256_512_skin.out 2>&1 &
 nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_256_512_curv" > nohup/iccv/pyr/iccv_pyr_32_64_128_256_512_curv.out 2>&1 &
 nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_256_512_reg" > nohup/iccv/pyr/iccv_pyr_32_64_128_256_512_reg.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_256_512_fine" > nohup/iccv/pyr/iccv_pyr_32_64_128_256_512_fine.out 2>&1 &
 
 nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32 > nohup/iccv/evaluate/iccv_pyr_32.out 2>&1 &
 nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_skirt > nohup/iccv/evaluate/iccv_pyr_32_skirt.out 2>&1 &

configs/iccv/config_abl_pyr_32_64_128_256_512_fine.py

@@ -0,0 +1,189 @@
+config = dict()
+
+config['gpu'] = '0'
+config['name'] = 'iccv_pyr_32_64_128_256_512_fine'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv']
+
+# 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_256_512'
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32, 64, 128, 256, 512]
+config['pyramid']['pretrained_pyramid'] = ''
+config['pyramid']['pretrained_pyramid_iteration'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data/train'
+config['valid_dir'] = '/home/workspace/local-data/train'
+config['test_dir'] = '/home/workspace/local-data/test_ready'
+# config['frames_file'] = 'frames_00761_0.txt'
+# config['frames_file_valid'] = 'frames_00761_0.txt'
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+
+config['dataset_in_memory'] = True
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.000001
+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'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1'
+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, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    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'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 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_256_2'#'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'#'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'#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'#'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'

cvae_pyramid.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.iccv.config_abl_pyr_32_64_128_skirt_dress import config
+from configs.iccv.config_abl_pyr_32_64_128_256_512_fine import config
 
 os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID"
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
@@ -284,8 +284,8 @@ def train_step(batch):
 
             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/var' + res_modifier: np.e ** logvar, 'train/l2_loss' + res_modifier: l2_loss, 'train/normal_loss' + res_modifier: n_loss,
-                                    'train/euclid_error': metric, 'train/l2_mesh_loss': l2_mesh_loss } } # 'train/ms_ssim' + res_modifier: ms_ssim,
+                                    'train/euclid_error' + res_modifier: metric, 'train/l2_mesh_loss' + res_modifier: l2_mesh_loss } } # 'train/ms_ssim' + res_modifier: ms_ssim,
 
         loss = reconstr_loss_total + balancing_coeff * kl_total
 
@@ -362,8 +362,8 @@ def valid_step(batch):
 
         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/var' + res_modifier: np.e ** logvar, 'valid/l2_loss' + res_modifier: l2_loss, 'valid/normal_loss' + res_modifier: n_loss,
-                                    'valid/euclid_error': metric, 'valid/l2_mesh_loss': l2_mesh_loss } } # 'valid/ms_ssim' + res_modifier: ms_ssim,
+                                    'valid/euclid_error' + res_modifier: metric, 'valid/l2_mesh_loss' + res_modifier: l2_mesh_loss } } # 'valid/ms_ssim' + res_modifier: ms_ssim,
 
     loss = reconstr_loss_total + balancing_coeff * kl_total