| 2025-07-07 11:14:04,236 - PropVG - INFO - dataset = 'RefCOCOgUMD' | |
| 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='RefCOCOgUMD', | |
| 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='RefCOCOgUMD', | |
| 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='RefCOCOgUMD', | |
| 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='RefCOCOgUMD', | |
| which_set='train', | |
| img_source=['coco'], | |
| annsfile= | |
| './data/seqtr_type/annotations/refcocog-umd/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='RefCOCOgUMD', | |
| 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='RefCOCOgUMD', | |
| which_set='val', | |
| img_source=['coco'], | |
| annsfile= | |
| './data/seqtr_type/annotations/refcocog-umd/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='RefCOCOgUMD', | |
| 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')), | |
| test=dict( | |
| type='RefCOCOgUMD', | |
| which_set='test', | |
| img_source=['coco'], | |
| annsfile= | |
| './data/seqtr_type/annotations/refcocog-umd/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='RefCOCOgUMD', | |
| 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/refcocog/PropVG-refcocog.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 = 1 | |
| 2025-07-07 11:14:09,303 - PropVG - INFO - RefCOCOg-val size: 4896 | |
| 2025-07-07 11:14:14,811 - PropVG - INFO - RefCOCOg-test size: 9602 | |
| 2025-07-07 11:14:19,468 - PropVG - INFO - loaded checkpoint from work_dir/refcocog/PropVG-refcocog.pth | |
| 2025-07-07 11:14:19,479 - PropVG - INFO - PropVG - evaluating set val | |
| 2025-07-07 11:16:13,025 - PropVG - INFO - ------------ validate ------------ time: 113.54, DetACC: 83.50, mIoU: 71.34, oIoU: 69.30, MaskACC@0.5-0.9: [81.19, 77.33, 71.51, 60.15, 30.78]DetACC@0.5-0.9: [83.50, 80.09, 75.41, 66.07, 40.54] | |
| 2025-07-07 11:16:15,090 - PropVG - INFO - PropVG - evaluating set test | |
| 2025-07-07 11:19:29,251 - PropVG - INFO - ------------ validate ------------ time: 194.16, DetACC: 84.44, mIoU: 72.10, oIoU: 70.53, MaskACC@0.5-0.9: [82.53, 78.47, 72.66, 61.23, 30.31]DetACC@0.5-0.9: [84.44, 81.32, 76.33, 67.14, 42.69] | |
| 2025-07-07 11:19:31,176 - PropVG - INFO - sucessfully save the results to work_dir/refcocog/refer_output_thr0.7_no-nms_no-sw_0.5_100.xlsx !!! | |