2025-07-07 11:09:02,802 - PropVG - INFO - dataset = 'RefCOCOPlusUNC' data_root = './data/seqtr_type/' img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375]) train_pipeline = [ dict( type='LoadImageAnnotationsFromFile_TO', max_token=20, with_mask=True, with_bbox=True, dataset='RefCOCOPlusUNC', use_token_type='beit3', refer_file='data/seqtr_type/annotations/mixed-seg/coco_all.json', object_area_filter=100, object_area_rate_filter=[0.05, 0.8]), dict(type='Resize', img_scale=(384, 384), keep_ratio=False), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375]), dict(type='DefaultFormatBundle'), dict( type='CollectData', keys=[ 'img', 'ref_expr_inds', 'text_attention_mask', 'gt_mask_rle', 'gt_bbox' ], meta_keys=[ 'filename', 'expression', 'ori_shape', 'img_shape', 'pad_shape', 'scale_factor', 'gt_ori_mask', 'target', 'empty', 'refer_target_index' ]) ] val_pipeline = [ dict( type='LoadImageAnnotationsFromFile_TO', max_token=20, with_mask=True, with_bbox=True, dataset='RefCOCOPlusUNC', use_token_type='beit3', refer_file='data/seqtr_type/annotations/mixed-seg/coco_all.json', object_area_filter=100, object_area_rate_filter=[0.05, 0.8]), dict(type='Resize', img_scale=(384, 384), keep_ratio=False), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375]), dict(type='DefaultFormatBundle'), dict( type='CollectData', keys=[ 'img', 'ref_expr_inds', 'text_attention_mask', 'gt_mask_rle', 'gt_bbox' ], meta_keys=[ 'filename', 'expression', 'ori_shape', 'img_shape', 'pad_shape', 'scale_factor', 'gt_ori_mask', 'target', 'empty', 'refer_target_index' ]) ] test_pipeline = [ dict( type='LoadImageAnnotationsFromFile_TO', max_token=20, with_mask=True, with_bbox=True, dataset='RefCOCOPlusUNC', use_token_type='beit3', refer_file='data/seqtr_type/annotations/mixed-seg/coco_all.json', object_area_filter=100, object_area_rate_filter=[0.05, 0.8]), dict(type='Resize', img_scale=(384, 384), keep_ratio=False), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375]), dict(type='DefaultFormatBundle'), dict( type='CollectData', keys=[ 'img', 'ref_expr_inds', 'text_attention_mask', 'gt_mask_rle', 'gt_bbox' ], meta_keys=[ 'filename', 'expression', 'ori_shape', 'img_shape', 'pad_shape', 'scale_factor', 'gt_ori_mask', 'target', 'empty', 'refer_target_index' ]) ] word_emb_cfg = dict(type='GloVe') data = dict( samples_per_gpu=8, workers_per_gpu=4, train=dict( type='RefCOCOPlusUNC', which_set='train', img_source=['coco'], annsfile= './data/seqtr_type/annotations/refcocoplus-unc/instances_withid.json', imgsfile='./data/seqtr_type/images/mscoco/train2014', pipeline=[ dict( type='LoadImageAnnotationsFromFile_TO', max_token=20, with_mask=True, with_bbox=True, dataset='RefCOCOPlusUNC', use_token_type='beit3', refer_file= 'data/seqtr_type/annotations/mixed-seg/coco_all.json', object_area_filter=100, object_area_rate_filter=[0.05, 0.8]), dict(type='Resize', img_scale=(384, 384), keep_ratio=False), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375]), dict(type='DefaultFormatBundle'), dict( type='CollectData', keys=[ 'img', 'ref_expr_inds', 'text_attention_mask', 'gt_mask_rle', 'gt_bbox' ], meta_keys=[ 'filename', 'expression', 'ori_shape', 'img_shape', 'pad_shape', 'scale_factor', 'gt_ori_mask', 'target', 'empty', 'refer_target_index' ]) ], word_emb_cfg=dict(type='GloVe')), val=dict( type='RefCOCOPlusUNC', which_set='val', img_source=['coco'], annsfile= './data/seqtr_type/annotations/refcocoplus-unc/instances_withid.json', imgsfile='./data/seqtr_type/images/mscoco/train2014', pipeline=[ dict( type='LoadImageAnnotationsFromFile_TO', max_token=20, with_mask=True, with_bbox=True, dataset='RefCOCOPlusUNC', use_token_type='beit3', refer_file= 'data/seqtr_type/annotations/mixed-seg/coco_all.json', object_area_filter=100, object_area_rate_filter=[0.05, 0.8]), dict(type='Resize', img_scale=(384, 384), keep_ratio=False), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375]), dict(type='DefaultFormatBundle'), dict( type='CollectData', keys=[ 'img', 'ref_expr_inds', 'text_attention_mask', 'gt_mask_rle', 'gt_bbox' ], meta_keys=[ 'filename', 'expression', 'ori_shape', 'img_shape', 'pad_shape', 'scale_factor', 'gt_ori_mask', 'target', 'empty', 'refer_target_index' ]) ], word_emb_cfg=dict(type='GloVe')), testA=dict( type='RefCOCOPlusUNC', which_set='testA', img_source=['coco'], annsfile= './data/seqtr_type/annotations/refcocoplus-unc/instances_withid.json', imgsfile='./data/seqtr_type/images/mscoco/train2014', pipeline=[ dict( type='LoadImageAnnotationsFromFile_TO', max_token=20, with_mask=True, with_bbox=True, dataset='RefCOCOPlusUNC', use_token_type='beit3', refer_file= 'data/seqtr_type/annotations/mixed-seg/coco_all.json', object_area_filter=100, object_area_rate_filter=[0.05, 0.8]), dict(type='Resize', img_scale=(384, 384), keep_ratio=False), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375]), dict(type='DefaultFormatBundle'), dict( type='CollectData', keys=[ 'img', 'ref_expr_inds', 'text_attention_mask', 'gt_mask_rle', 'gt_bbox' ], meta_keys=[ 'filename', 'expression', 'ori_shape', 'img_shape', 'pad_shape', 'scale_factor', 'gt_ori_mask', 'target', 'empty', 'refer_target_index' ]) ], word_emb_cfg=dict(type='GloVe')), testB=dict( type='RefCOCOPlusUNC', which_set='testB', img_source=['coco'], annsfile= './data/seqtr_type/annotations/refcocoplus-unc/instances_withid.json', imgsfile='./data/seqtr_type/images/mscoco/train2014', pipeline=[ dict( type='LoadImageAnnotationsFromFile_TO', max_token=20, with_mask=True, with_bbox=True, dataset='RefCOCOPlusUNC', use_token_type='beit3', refer_file= 'data/seqtr_type/annotations/mixed-seg/coco_all.json', object_area_filter=100, object_area_rate_filter=[0.05, 0.8]), dict(type='Resize', img_scale=(384, 384), keep_ratio=False), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375]), dict(type='DefaultFormatBundle'), dict( type='CollectData', keys=[ 'img', 'ref_expr_inds', 'text_attention_mask', 'gt_mask_rle', 'gt_bbox' ], meta_keys=[ 'filename', 'expression', 'ori_shape', 'img_shape', 'pad_shape', 'scale_factor', 'gt_ori_mask', 'target', 'empty', 'refer_target_index' ]) ], word_emb_cfg=dict(type='GloVe'))) ema = False ema_factor = 0.999 use_fp16 = False seed = 6666 deterministic = True log_level = 'INFO' log_interval = 50 save_interval = -1 resume_from = None load_from = 'work_dir/refcoco+/PropVG-refcoco+.pth' finetune_from = None evaluate_interval = 1 start_evaluate_epoch = 0 start_save_checkpoint = 20 max_token = 20 img_size = 384 patch_size = 16 model = dict( type='MIXRefUniModel_OMG', vis_enc=dict( type='BEIT3', img_size=384, patch_size=16, vit_type='base', drop_path_rate=0.1, vocab_size=64010, freeze_layer=-1, vision_embed_proj_interpolate=False, pretrain='pretrain_weights/beit3_base_patch16_224.zip'), lan_enc=None, fusion=None, head=dict( type='REFHead', input_channels=768, hidden_channels=256, num_queries=20, detr_loss=dict( criterion=dict(loss_class=1.0, loss_bbox=5.0, loss_giou=2.0), matcher=dict(cost_class=1.0, cost_bbox=5.0, cost_giou=2.0)), loss_weight=dict( mask=dict(dice=1.0, bce=1.0, nt=0.2, neg=0), bbox=0.1, allbbox=0.1, refer=1.0), MTD=dict(K=100)), post_params=dict( score_weighted=False, mask_threshold=0.5, score_threshold=0.7, with_nms=False, with_mask=True), process_visual=True, visualize_params=dict(row_columns=(4, 5)), visual_mode='test') grad_norm_clip = 0.15 lr = 0.0005 optimizer_config = dict( type='Adam', lr=0.0005, lr_vis_enc=5e-05, lr_lan_enc=0.0005, betas=(0.9, 0.98), eps=1e-09, weight_decay=0, amsgrad=True) scheduler_config = dict( type='MultiStepLRWarmUp', warmup_epochs=1, decay_steps=[21, 27], decay_ratio=0.1, max_epoch=30) launcher = 'pytorch' distributed = True rank = 0 world_size = 4 2025-07-07 11:09:07,978 - PropVG - INFO - RefCOCOPlusUNC-val size: 10758 2025-07-07 11:09:13,867 - PropVG - INFO - RefCOCOPlusUNC-testA size: 5726 2025-07-07 11:09:19,990 - PropVG - INFO - RefCOCOPlusUNC-testB size: 4889 2025-07-07 11:09:24,879 - PropVG - INFO - loaded checkpoint from work_dir/refcoco+/PropVG-refcoco+.pth 2025-07-07 11:09:24,886 - PropVG - INFO - PropVG - evaluating set val 2025-07-07 11:11:17,140 - PropVG - INFO - ------------ validate ------------ time: 112.25, DetACC: 83.73, mIoU: 72.94, oIoU: 70.24, MaskACC@0.5-0.9: [83.12, 80.60, 76.04, 65.37, 33.26]DetACC@0.5-0.9: [83.73, 81.30, 77.10, 68.58, 42.65] 2025-07-07 11:11:18,910 - PropVG - INFO - PropVG - evaluating set testA 2025-07-07 11:12:32,835 - PropVG - INFO - ------------ validate ------------ time: 73.92, DetACC: 88.01, mIoU: 76.49, oIoU: 74.32, MaskACC@0.5-0.9: [88.04, 86.00, 81.37, 70.53, 33.52]DetACC@0.5-0.9: [88.01, 85.91, 82.12, 73.80, 47.14] 2025-07-07 11:12:34,541 - PropVG - INFO - PropVG - evaluating set testB 2025-07-07 11:13:39,576 - PropVG - INFO - ------------ validate ------------ time: 65.03, DetACC: 76.59, mIoU: 67.21, oIoU: 63.41, MaskACC@0.5-0.9: [75.57, 71.83, 66.95, 57.38, 33.87]DetACC@0.5-0.9: [76.59, 73.26, 68.11, 59.24, 36.12] 2025-07-07 11:13:41,507 - PropVG - INFO - sucessfully save the results to work_dir/refcoco+/refer_output_thr0.7_no-nms_no-sw_0.5_100.xlsx !!!