luni/cvpr
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

started training pyramid

Browse Source
This commit is contained in:
luni
2023-02-26 22:25:50 +00:00
parent a678724711
commit 64ecb900f5
8 changed files with 314 additions and 79 deletions
Download Patch File Download Diff File Expand all files Collapse all files
configs/iccv/config_abl_pyr_32.py
+29 -25
View File
@@ -1,6 +1,6 @@
config = dict()
config['gpu'] = '2'
config['gpu'] = '0'
config['name'] = 'iccv_pyr_32'
config['notes'] = ''
config['tags'] = ['pyr', 'iccv']
@@ -47,6 +47,7 @@ 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,),
@@ -63,8 +64,8 @@ config['signature_static'] = { 'uv_static': (512, 256, 3),
}
config['pyramid']['is_label'] = False
config['pyramid']['add_noise'] = True
config['pyramid']['noise_amount'] = 0.001
config['pyramid']['add_noise'] = False
config['pyramid']['noise_amount'] = 0.0
config['pyramid']['loss_weights'] = [1,1,1,1,1]
@@ -77,9 +78,10 @@ for res in config['pyramid']['resolutions']:
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/post/static_post_2'
config['pyramid']['body_model'] = 'checkpoints/post/body_post_2'
config['pyramid']['curvature_model'] = 'checkpoints/post/curv_post_1'
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
@@ -88,10 +90,10 @@ for res in config['pyramid']['resolutions']:
if res == 512:
level = dict()
level['resolution'] = 512
level['latent_dim'] = config['latent_dim']
level['latent_dim'] = 64 * config['bottleneck_scale']
level['kernel_size'] = 7
level['encoder_depths'] = [3, 3, 9, 3]
level['encoder_dims'] = [32, 64, 128, 64]
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]
@@ -101,53 +103,55 @@ for res in config['pyramid']['resolutions']:
elif res == 256:
level = dict()
level['resolution'] = 256
level['latent_dim'] = config['latent_dim']
level['kernel_size'] = 7
level['latent_dim'] = 64 * config['bottleneck_scale']
level['kernel_size'] = 5
level['encoder_depths'] = [9, 9, 9, 9]
level['encoder_dims'] = [32, 64, 128, 64]
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/up_3_d256_512_2'
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'] = config['latent_dim']
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, 64]
level['decoder_dims'] = [256, 128, 128, level['latent_dim']]
level['avg_garment_path'] = ''
level['upscale_enhancer'] = ''#'checkpoints/up_3_d128_256_2'
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['kernel_size'] = 5
level['latent_dim'] = 64 * config['bottleneck_scale']
level['kernel_size'] = 3
level['encoder_depths'] = [9, 9]
level['encoder_dims'] = [64, 64]
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/64_512_2'#checkpoints/up_3_d64_128_2'
level['upscale_enhancer'] = 'checkpoints/iccv/iccv_'#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'] = [64]
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/32_512_4'#'checkpoints/up_3_d32_64_2'
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:
@@ -156,9 +160,9 @@ for res in config['pyramid']['resolutions']:
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['cond_ae_static']['encoder_depths'] = [3, 3, 3, 9, 3]
config['cond_ae_static']['encoder_dims'] = [16, 32, 64, 64, config['cond_ae_static']['bottleneck_size']]
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'
@@ -166,7 +170,7 @@ 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['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']
@@ -176,7 +180,7 @@ 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['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']
configs/iccv/config_abl_pyr_32_skirt.py
+188
View File
@@ -0,0 +1,188 @@
config = dict()
config['gpu'] = '0'
config['name'] = 'iccv_pyr_32_skirt'
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['pretrained_model'] = ''
config['pretrained_model_iteration'] = ''
config['pyramid'] = dict()
config['pyramid']['resolutions'] = [32]
config['pyramid']['pretrained_pyramid'] = ''
config['pyramid']['final_upscale_enhancer'] = ''
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_cape'] = False
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'
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, 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_'#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'