img_norm_cfg = dict( mean=[0.0, 0.0, 0.0], std=[255.0, 255.0, 255.0], to_rgb=False) crop_size = (384, 768) global_transform = dict( translates=(0.05, 0.05), zoom=(1.0, 1.5), shear=(0.86, 1.16), rotate=(-10.0, 10.0)) relative_transform = dict( translates=(0.00375, 0.00375), zoom=(0.985, 1.015), shear=(1.0, 1.0), rotate=(-1.0, 1.0)) train_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_occ=True), dict( type='ColorJitter', brightness=0.5, contrast=0.5, saturation=0.5, hue=0.5), dict(type='RandomGamma', gamma_range=(0.7, 1.5)), dict( type='Normalize', mean=[0.0, 0.0, 0.0], std=[255.0, 255.0, 255.0], to_rgb=False), dict(type='GaussianNoise', sigma_range=(0, 0.04), clamp_range=(0.0, 1.0)), dict(type='RandomFlip', prob=0.5, direction='horizontal'), dict(type='RandomFlip', prob=0.5, direction='vertical'), dict( type='RandomAffine', global_transform=dict( translates=(0.05, 0.05), zoom=(1.0, 1.5), shear=(0.86, 1.16), rotate=(-10.0, 10.0)), relative_transform=dict( translates=(0.00375, 0.00375), zoom=(0.985, 1.015), shear=(1.0, 1.0), rotate=(-1.0, 1.0)), check_bound=True), dict(type='RandomCrop', crop_size=(384, 768)), dict(type='DefaultFormatBundle'), dict( type='Collect', keys=['imgs', 'flow_gt', 'occ_gt'], meta_keys=('img_fields', 'ann_fields', 'filename1', 'filename2', 'ori_filename1', 'ori_filename2', 'filename_flow', 'ori_filename_flow', 'ori_shape', 'img_shape', 'img_norm_cfg')) ] test_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations'), dict(type='InputResize', exponent=4), dict( type='Normalize', mean=[0.0, 0.0, 0.0], std=[255.0, 255.0, 255.0], to_rgb=False), dict(type='TestFormatBundle'), dict( type='Collect', keys=['imgs'], meta_keys=('flow_gt', 'filename1', 'filename2', 'ori_filename1', 'ori_filename2', 'ori_shape', 'img_shape', 'img_norm_cfg', 'scale_factor', 'pad_shape')) ] sintel_final_train = dict( type='Sintel', pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_occ=True), dict( type='ColorJitter', brightness=0.5, contrast=0.5, saturation=0.5, hue=0.5), dict(type='RandomGamma', gamma_range=(0.7, 1.5)), dict( type='Normalize', mean=[0.0, 0.0, 0.0], std=[255.0, 255.0, 255.0], to_rgb=False), dict( type='GaussianNoise', sigma_range=(0, 0.04), clamp_range=(0.0, 1.0)), dict(type='RandomFlip', prob=0.5, direction='horizontal'), dict(type='RandomFlip', prob=0.5, direction='vertical'), dict( type='RandomAffine', global_transform=dict( translates=(0.05, 0.05), zoom=(1.0, 1.5), shear=(0.86, 1.16), rotate=(-10.0, 10.0)), relative_transform=dict( translates=(0.00375, 0.00375), zoom=(0.985, 1.015), shear=(1.0, 1.0), rotate=(-1.0, 1.0)), check_bound=True), dict(type='RandomCrop', crop_size=(384, 768)), dict(type='DefaultFormatBundle'), dict( type='Collect', keys=['imgs', 'flow_gt', 'occ_gt'], meta_keys=('img_fields', 'ann_fields', 'filename1', 'filename2', 'ori_filename1', 'ori_filename2', 'filename_flow', 'ori_filename_flow', 'ori_shape', 'img_shape', 'img_norm_cfg')) ], data_root='data/Sintel', test_mode=False, pass_style='final') sintel_clean_test = dict( type='Sintel', pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations'), dict(type='InputResize', exponent=4), dict( type='Normalize', mean=[0.0, 0.0, 0.0], std=[255.0, 255.0, 255.0], to_rgb=False), dict(type='TestFormatBundle'), dict( type='Collect', keys=['imgs'], meta_keys=('flow_gt', 'filename1', 'filename2', 'ori_filename1', 'ori_filename2', 'ori_shape', 'img_shape', 'img_norm_cfg', 'scale_factor', 'pad_shape')) ], data_root='data/Sintel', test_mode=True, pass_style='clean') sintel_final_test = dict( type='Sintel', pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations'), dict(type='InputResize', exponent=4), dict( type='Normalize', mean=[0.0, 0.0, 0.0], std=[255.0, 255.0, 255.0], to_rgb=False), dict(type='TestFormatBundle'), dict( type='Collect', keys=['imgs'], meta_keys=('flow_gt', 'filename1', 'filename2', 'ori_filename1', 'ori_filename2', 'ori_shape', 'img_shape', 'img_norm_cfg', 'scale_factor', 'pad_shape')) ], data_root='data/Sintel', test_mode=True, pass_style='final') data = dict( train_dataloader=dict( samples_per_gpu=1, workers_per_gpu=5, drop_last=True, persistent_workers=True), val_dataloader=dict(samples_per_gpu=1, workers_per_gpu=5, shuffle=False), test_dataloader=dict(samples_per_gpu=1, workers_per_gpu=5, shuffle=False), train=dict( type='Sintel', pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_occ=True), dict( type='ColorJitter', brightness=0.5, contrast=0.5, saturation=0.5, hue=0.5), dict(type='RandomGamma', gamma_range=(0.7, 1.5)), dict( type='Normalize', mean=[0.0, 0.0, 0.0], std=[255.0, 255.0, 255.0], to_rgb=False), dict( type='GaussianNoise', sigma_range=(0, 0.04), clamp_range=(0.0, 1.0)), dict(type='RandomFlip', prob=0.5, direction='horizontal'), dict(type='RandomFlip', prob=0.5, direction='vertical'), dict( type='RandomAffine', global_transform=dict( translates=(0.05, 0.05), zoom=(1.0, 1.5), shear=(0.86, 1.16), rotate=(-10.0, 10.0)), relative_transform=dict( translates=(0.00375, 0.00375), zoom=(0.985, 1.015), shear=(1.0, 1.0), rotate=(-1.0, 1.0)), check_bound=True), dict(type='RandomCrop', crop_size=(384, 768)), dict(type='DefaultFormatBundle'), dict( type='Collect', keys=['imgs', 'flow_gt', 'occ_gt'], meta_keys=('img_fields', 'ann_fields', 'filename1', 'filename2', 'ori_filename1', 'ori_filename2', 'filename_flow', 'ori_filename_flow', 'ori_shape', 'img_shape', 'img_norm_cfg')) ], data_root='data/Sintel', test_mode=False, pass_style='final'), val=dict( type='ConcatDataset', datasets=[ dict( type='Sintel', pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations'), dict(type='InputResize', exponent=4), dict( type='Normalize', mean=[0.0, 0.0, 0.0], std=[255.0, 255.0, 255.0], to_rgb=False), dict(type='TestFormatBundle'), dict( type='Collect', keys=['imgs'], meta_keys=('flow_gt', 'filename1', 'filename2', 'ori_filename1', 'ori_filename2', 'ori_shape', 'img_shape', 'img_norm_cfg', 'scale_factor', 'pad_shape')) ], data_root='data/Sintel', test_mode=True, pass_style='clean'), dict( type='Sintel', pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations'), dict(type='InputResize', exponent=4), dict( type='Normalize', mean=[0.0, 0.0, 0.0], std=[255.0, 255.0, 255.0], to_rgb=False), dict(type='TestFormatBundle'), dict( type='Collect', keys=['imgs'], meta_keys=('flow_gt', 'filename1', 'filename2', 'ori_filename1', 'ori_filename2', 'ori_shape', 'img_shape', 'img_norm_cfg', 'scale_factor', 'pad_shape')) ], data_root='data/Sintel', test_mode=True, pass_style='final') ], separate_eval=True), test=dict( type='ConcatDataset', datasets=[ dict( type='Sintel', pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations'), dict(type='InputResize', exponent=4), dict( type='Normalize', mean=[0.0, 0.0, 0.0], std=[255.0, 255.0, 255.0], to_rgb=False), dict(type='TestFormatBundle'), dict( type='Collect', keys=['imgs'], meta_keys=('flow_gt', 'filename1', 'filename2', 'ori_filename1', 'ori_filename2', 'ori_shape', 'img_shape', 'img_norm_cfg', 'scale_factor', 'pad_shape')) ], data_root='data/Sintel', test_mode=True, pass_style='clean'), dict( type='Sintel', pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations'), dict(type='InputResize', exponent=4), dict( type='Normalize', mean=[0.0, 0.0, 0.0], std=[255.0, 255.0, 255.0], to_rgb=False), dict(type='TestFormatBundle'), dict( type='Collect', keys=['imgs'], meta_keys=('flow_gt', 'filename1', 'filename2', 'ori_filename1', 'ori_filename2', 'ori_shape', 'img_shape', 'img_norm_cfg', 'scale_factor', 'pad_shape')) ], data_root='data/Sintel', test_mode=True, pass_style='final') ], separate_eval=True)) optimizer = dict( type='Adam', lr=3e-05, weight_decay=0.0004, betas=(0.9, 0.999)) optimizer_config = dict(grad_clip=None) lr_config = dict( policy='MultiStage', by_epoch=False, gammas=[0.5, 0.5], milestone_lrs=[3e-05, 2e-05], milestone_iters=[0, 150000], steps=[[ 45000, 65000, 85000, 95000, 97500, 100000, 110000, 120000, 130000, 140000 ], [ 195000, 215000, 235000, 245000, 247500, 250000, 260000, 270000, 280000, 290000 ]]) runner = dict(type='IterBasedRunner', max_iters=300000) checkpoint_config = dict(by_epoch=False, interval=50000) evaluation = dict(interval=50000, metric='EPE') log_config = dict( interval=50, hooks=[dict(type='TextLoggerHook'), dict(type='TensorboardLoggerHook')]) dist_params = dict(backend='nccl', port=11111) log_level = 'INFO' load_from = 'work_dir/irrft_s/latest.pth' resume_from = None workflow = [('train', 1)] model = dict( type='IRRPWC', encoder=dict( type='PWCNetEncoder', in_channels=3, net_type='Small', pyramid_levels=[ 'level1', 'level2', 'level3', 'level4', 'level5', 'level6' ], out_channels=(16, 32, 64, 96, 128, 196), strides=(2, 2, 2, 2, 2, 2), dilations=(1, 1, 1, 1, 1, 1), act_cfg=dict(type='LeakyReLU', negative_slope=0.1)), decoder=dict( type='IRRPWCDecoder', flow_levels=[ 'level0', 'level1', 'level2', 'level3', 'level4', 'level5', 'level6' ], corr_in_channels=dict( level2=32, level3=64, level4=96, level5=128, level6=196), corr_feat_channels=32, flow_decoder_in_channels=115, occ_decoder_in_channels=114, corr_cfg=dict(type='Correlation', max_displacement=4), scaled=True, warp_cfg=dict(type='Warp', align_corners=True), densefeat_channels=(128, 128, 96, 64, 32), flow_post_processor=dict( type='ContextNet', in_channels=565, out_channels=2, feat_channels=(128, 128, 128, 96, 64, 32), dilations=(1, 2, 4, 8, 16, 1), act_cfg=dict(type='LeakyReLU', negative_slope=0.1)), flow_refine=dict( type='FlowRefine', in_channels=35, feat_channels=(128, 128, 64, 64, 32, 32), patch_size=3, warp_cfg=dict(type='Warp', align_corners=True, use_mask=True), act_cfg=dict(type='LeakyReLU', negative_slope=0.1)), occ_post_processor=dict( type='ContextNet', in_channels=563, out_channels=1, feat_channels=(128, 128, 128, 96, 64, 32), dilations=(1, 2, 4, 8, 16, 1), act_cfg=dict(type='LeakyReLU', negative_slope=0.1)), occ_refine=dict( type='OccRefine', in_channels=65, feat_channels=(128, 128, 64, 64, 32, 32), patch_size=3, act_cfg=dict(type='LeakyReLU', negative_slope=0.1), warp_cfg=dict(type='Warp', align_corners=True)), occ_upsample=dict( type='OccShuffleUpsample', in_channels=11, feat_channels=32, infeat_channels=16, out_channels=1, warp_cfg=dict(type='Warp', align_corners=True, use_mask=True), act_cfg=dict(type='LeakyReLU', negative_slope=0.1)), occ_refined_levels=['level0', 'level1'], flow_div=20.0, act_cfg=dict(type='LeakyReLU', negative_slope=0.1), flow_loss=dict( type='MultiLevelEPE', weights=dict( level6=0.32, level5=0.08, level4=0.02, level3=0.01, level2=0.005, level1=0.00125, level0=0.0003125), p=1, q=0.4, eps=0.01, reduction='sum'), occ_loss=dict( type='MultiLevelBCE', weights=dict( level6=0.32, level5=0.08, level4=0.02, level3=0.01, level2=0.005, level1=0.00125, level0=0.0003125), reduction='sum')), init_cfg=dict( type='Kaiming', a=0.1, nonlinearity='leaky_relu', layer=['Conv2d', 'ConvTranspose2d'], mode='fan_in', bias=0), train_cfg=dict(), test_cfg=dict()) custom_hooks = [dict(type='EMAHook')] work_dir = 'work_dir/irrft_sfinal' gpu_ids = range(0, 1)