Upload 2 files

faster_rcnn_vmrn_r101_caffe_c4_1x_vmrd4683.py

@@ -0,0 +1,301 @@
+norm_cfg = dict(type='BN', requires_grad=False)
+model = dict(
+    type='FasterRCNNVMRN',
+    backbone=dict(
+        type='mmdet.ResNet',
+        depth=101,
+        num_stages=3,
+        strides=(1, 2, 2),
+        dilations=(1, 1, 1),
+        out_indices=(2, ),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=False),
+        norm_eval=True,
+        style='caffe',
+        init_cfg=dict(
+            type='Pretrained',
+            checkpoint='open-mmlab://detectron2/resnet101_caffe')),
+    rpn_head=dict(
+        type='mmdet.RPNHead',
+        in_channels=1024,
+        feat_channels=1024,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[8, 16, 32],
+            ratios=[0.33, 0.5, 1.0, 2.0, 3.0],
+            strides=[16]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[0.0, 0.0, 0.0, 0.0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='mmdet.CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='mmdet.L1Loss', loss_weight=1.0)),
+    roi_head=dict(
+        type='mmdet.StandardRoIHead',
+        shared_head=dict(
+            type='mmdet.ResLayer',
+            depth=50,
+            stage=3,
+            stride=1,
+            style='caffe',
+            norm_cfg=dict(type='BN', requires_grad=False),
+            norm_eval=True),
+        bbox_roi_extractor=dict(
+            type='mmdet.SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
+            out_channels=1024,
+            featmap_strides=[16]),
+        bbox_head=dict(
+            type='mmdet.BBoxHead',
+            with_avg_pool=True,
+            roi_feat_size=7,
+            in_channels=2048,
+            num_classes=31,
+            bbox_coder=dict(
+                type='DeltaXYWHBBoxCoder',
+                target_means=[0.0, 0.0, 0.0, 0.0],
+                target_stds=[0.1, 0.1, 0.2, 0.2]),
+            reg_class_agnostic=False,
+            loss_cls=dict(
+                type='mmdet.CrossEntropyLoss',
+                use_sigmoid=False,
+                loss_weight=1.0),
+            loss_bbox=dict(type='mmdet.L1Loss', loss_weight=1.0))),
+    vmrn_head=dict(
+        type='invigorate.PairedRoIHead',
+        shared_head=dict(
+            type='invigorate.PairedResLayer',
+            depth=50,
+            stage=3,
+            stride=1,
+            style='caffe',
+            norm_eval=False,
+            share_weights=False),
+        paired_roi_extractor=dict(
+            type='invigorate.VMRNPairedRoIExtractor',
+            roi_layer=dict(type='RoIPool', output_size=7),
+            out_channels=1024,
+            featmap_strides=[16]),
+        relation_head=dict(
+            type='invigorate.BBoxPairHead',
+            with_avg_pool=True,
+            roi_feat_size=7,
+            in_channels=2048,
+            num_relations=2,
+            loss_cls=dict(
+                type='mmdet.CrossEntropyLoss',
+                use_sigmoid=False,
+                loss_weight=1.0))),
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=0,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_pre=12000,
+            max_per_img=2000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.5,
+                match_low_quality=False,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            pos_weight=-1,
+            debug=False),
+        vmrn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.7,
+                match_low_quality=False,
+                ignore_iof_thr=-1),
+            relation_sampler=dict(
+                type='RandomRelationSampler',
+                num=32,
+                pos_fraction=0.5,
+                cls_ratio_ub=-1,
+                add_gt_as_proposals=True,
+                num_relation_cls=2),
+            pos_weight=-1,
+            online_data=True,
+            online_start_iteration=0)),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=6000,
+            max_per_img=300,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.3),
+            max_per_img=100),
+        vmrn=dict(
+            bbox_score_thr=0.5, verbose_relation=False, average_scores=False)))
+dataset_type = 'VMRDDataset'
+data_root = 'data/vmrd/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile', to_float32=True),
+    dict(
+        type='LoadAnnotationsCustom',
+        keys=['gt_bboxes', 'gt_labels', 'gt_relmats']),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='Expand', mean=[123.675, 116.28, 103.53]),
+    dict(type='Resize', img_scale=(1000, 600), keep_ratio=True),
+    dict(
+        type='Normalize',
+        mean=[123.675, 116.28, 103.53],
+        std=[1.0, 1.0, 1.0],
+        to_rgb=True),
+    dict(type='Pad', size_divisor=32),
+    dict(
+        type='DefaultFormatBundleCustom',
+        keys=['img', 'gt_bboxes', 'gt_labels', 'gt_relmats']),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_relmats'])
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1000, 600),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(
+                type='Normalize',
+                mean=[123.675, 116.28, 103.53],
+                std=[1.0, 1.0, 1.0],
+                to_rgb=True),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img'])
+        ])
+]
+data = dict(
+    samples_per_gpu=8,
+    workers_per_gpu=8,
+    train=dict(
+        type='RepeatDataset',
+        times=3,
+        dataset=dict(
+            type='VMRDDataset',
+            ann_file='data/vmrd/ImageSets/Main/trainval.txt',
+            img_prefix='data/vmrd/',
+            pipeline=[
+                dict(type='LoadImageFromFile', to_float32=True),
+                dict(
+                    type='LoadAnnotationsCustom',
+                    keys=['gt_bboxes', 'gt_labels', 'gt_relmats']),
+                dict(type='RandomFlip', flip_ratio=0.5),
+                dict(type='PhotoMetricDistortion'),
+                dict(type='Expand', mean=[123.675, 116.28, 103.53]),
+                dict(type='Resize', img_scale=(1000, 600), keep_ratio=True),
+                dict(
+                    type='Normalize',
+                    mean=[123.675, 116.28, 103.53],
+                    std=[1.0, 1.0, 1.0],
+                    to_rgb=True),
+                dict(type='Pad', size_divisor=32),
+                dict(
+                    type='DefaultFormatBundleCustom',
+                    keys=['img', 'gt_bboxes', 'gt_labels', 'gt_relmats']),
+                dict(
+                    type='Collect',
+                    keys=['img', 'gt_bboxes', 'gt_labels', 'gt_relmats'])
+            ])),
+    val=dict(
+        type='VMRDDataset',
+        ann_file='data/vmrd/ImageSets/Main/test.txt',
+        img_prefix='data/vmrd/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(
+                type='MultiScaleFlipAug',
+                img_scale=(1000, 600),
+                flip=False,
+                transforms=[
+                    dict(type='Resize', keep_ratio=True),
+                    dict(
+                        type='Normalize',
+                        mean=[123.675, 116.28, 103.53],
+                        std=[1.0, 1.0, 1.0],
+                        to_rgb=True),
+                    dict(type='Pad', size_divisor=32),
+                    dict(type='ImageToTensor', keys=['img']),
+                    dict(type='Collect', keys=['img'])
+                ])
+        ]),
+    test=dict(
+        type='VMRDDataset',
+        ann_file='data/vmrd/ImageSets/Main/test.txt',
+        img_prefix='data/vmrd/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(
+                type='MultiScaleFlipAug',
+                img_scale=(1000, 600),
+                flip=False,
+                transforms=[
+                    dict(type='Resize', keep_ratio=True),
+                    dict(
+                        type='Normalize',
+                        mean=[123.675, 116.28, 103.53],
+                        std=[1.0, 1.0, 1.0],
+                        to_rgb=True),
+                    dict(type='Pad', size_divisor=32),
+                    dict(type='ImageToTensor', keys=['img']),
+                    dict(type='Collect', keys=['img'])
+                ])
+        ]))
+evaluation = dict(interval=1, metric=['mAP', 'ImgAcc'])
+optimizer = dict(type='SGD', lr=0.005, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=100, norm_type=2))
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=0.001,
+    step=[8])
+runner = dict(type='EpochBasedRunner', max_epochs=20)
+checkpoint_config = dict(interval=1, max_keep_ckpts=3)
+log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
+custom_hooks = [dict(type='NumClassCheckHook')]
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
+opencv_num_threads = 0
+mp_start_method = 'fork'
+auto_scale_lr = dict(enable=False, base_batch_size=16)
+mmdet = None
+mmdet_root = '/data/home/hanbo/projects/alpha_vision/mmdetection/mmdet'
+work_dir = './work_dirs/faster_rcnn_vmrn_r101_caffe_c4_1x_vmrd4683'
+gpu_ids = range(0, 2)