ins-waste-detection-faster_rcnn_1xcoco-mmdetection-config.py

num_batch_size = 4
num_epochs = 15
num_frozen_stages = 2

auto_scale_lr = dict(base_batch_size=2, enable=False)
backend_args = None
data_root = 'C:/vs_code_workspaces/mmdetection/mmdetection/data/ins/v9'
dataset_type = 'CocoDataset'
default_hooks = dict(
    checkpoint=dict(interval=1, type='CheckpointHook'),
    logger=dict(interval=50, type='LoggerHook'),
    param_scheduler=dict(type='ParamSchedulerHook'),
    sampler_seed=dict(type='DistSamplerSeedHook'),
    timer=dict(type='IterTimerHook'),
    visualization=dict(type='DetVisualizationHook'))
default_scope = 'mmdet'
env_cfg = dict(cudnn_benchmark=False, dist_cfg=dict(backend='nccl'), mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
launcher = 'none'
load_from = 'C:/vs_code_workspaces/mmdetection/mmdetection/ins_development/resources/add300_frozen2/epoch_9.pth'
log_level = 'INFO'
log_processor = dict(by_epoch=True, type='LogProcessor', window_size=50)
metainfo = dict(classes=('waste', ), palette=[ (220, 20, 60, ),])
model = dict(
    backbone=dict(
        depth=101,
        frozen_stages=num_frozen_stages,
        init_cfg=dict(checkpoint='C:/Users/INS/.cache/torch/hub/checkpoints/resnet101-63fe2227.pth', type='Pretrained'),
        norm_cfg=dict(requires_grad=True, type='BN'),
        norm_eval=True,
        num_stages=4,
        out_indices=(0, 1, 2, 3, ),
        style='pytorch',
        type='ResNet'),
    data_preprocessor=dict(
        bgr_to_rgb=True,
        mean=[123.675, 116.28, 103.53, ],
        pad_size_divisor=32,
        std=[58.395, 57.12, 57.375, ],
        type='DetDataPreprocessor'),
    neck=dict(in_channels=[256, 512, 1024, 2048, ],
        num_outs=5,
        out_channels=256,
        type='FPN'),
    roi_head=dict(
        bbox_head=dict(
            bbox_coder=dict(
                target_means=[0.0, 0.0, 0.0, 0.0,],
                target_stds=[0.1, 0.1, 0.2, 0.2,],
                type='DeltaXYWHBBoxCoder'),
            fc_out_channels=1024,
            in_channels=256,
            loss_bbox=dict(loss_weight=1.0, type='L1Loss'),
            loss_cls=dict(
                loss_weight=1.0, type='CrossEntropyLoss', use_sigmoid=False),
            num_classes=1,
            reg_class_agnostic=False,
            roi_feat_size=7,
            type='Shared2FCBBoxHead'),
        bbox_roi_extractor=dict(
            featmap_strides=[4, 8, 16, 32, ],
            out_channels=256,
            roi_layer=dict(output_size=7, sampling_ratio=0, type='RoIAlign'),
            type='SingleRoIExtractor'),
        type='StandardRoIHead'),
    rpn_head=dict(
        anchor_generator=dict(
            ratios=[0.5, 1.0, 2.0, ],
            scales=[8,],
            strides=[4, 8, 16, 32, 64, ],
            type='AnchorGenerator'),
        bbox_coder=dict(
            target_means=[0.0, 0.0, 0.0, 0.0, ],
            target_stds=[1.0, 1.0, 1.0, 1.0, ],
            type='DeltaXYWHBBoxCoder'),
        feat_channels=256,
        in_channels=256,
        loss_bbox=dict(loss_weight=1.0, type='L1Loss'),
        loss_cls=dict(loss_weight=1.0, type='CrossEntropyLoss', use_sigmoid=True),
        type='RPNHead'),
    test_cfg=dict(
        rcnn=dict(
            max_per_img=100,
            nms=dict(iou_threshold=0.5, type='nms'),
            score_thr=0.05),
        rpn=dict(
            max_per_img=1000,
            min_bbox_size=0,
            nms=dict(iou_threshold=0.7, type='nms'),
            nms_pre=1000)),
    train_cfg=dict(
        rcnn=dict(
            assigner=dict(
                ignore_iof_thr=-1,
                match_low_quality=False,
                min_pos_iou=0.5,
                neg_iou_thr=0.5,
                pos_iou_thr=0.5,
                type='MaxIoUAssigner'),
            debug=False,
            pos_weight=-1,
            sampler=dict(
                add_gt_as_proposals=True,
                neg_pos_ub=-1,
                num=512,
                pos_fraction=0.25,
                type='RandomSampler')),
        rpn=dict(
            allowed_border=-1,
            assigner=dict(
                ignore_iof_thr=-1,
                match_low_quality=True,
                min_pos_iou=0.3,
                neg_iou_thr=0.3,
                pos_iou_thr=0.7,
                type='MaxIoUAssigner'),
            debug=False,
            pos_weight=-1,
            sampler=dict(
                add_gt_as_proposals=False,
                neg_pos_ub=-1,
                num=256,
                pos_fraction=0.5,
                type='RandomSampler')),
        rpn_proposal=dict(
            max_per_img=1000,
            min_bbox_size=0,
            nms=dict(iou_threshold=0.7, type='nms'),
            nms_pre=2000)),
    type='FasterRCNN')
optim_wrapper = dict(
    optimizer=dict(lr=0.02, momentum=0.9, type='SGD', weight_decay=0.0001),
    type='OptimWrapper')
param_scheduler = [
    dict(begin=0, by_epoch=False, end=500, start_factor=0.001, type='LinearLR'),
    dict(begin=0, by_epoch=True, end=12, gamma=0.1, milestones=[8, 11, ], type='MultiStepLR'),
]
resume = False
test_cfg = dict(type='TestLoop')
test_dataloader = dict(
    batch_size=num_batch_size,
    dataset=dict(
        ann_file='test/annotations_coco.json',
        backend_args=None,
        data_prefix=dict(img='test/'),
        data_root=data_root,
        metainfo=dict(classes=('waste', ), palette=[(220, 20, 60, ), ]),
        pipeline=[
            dict(backend_args=None, type='LoadImageFromFile'),
            dict(keep_ratio=True, scale=(1280, 1280, ), type='Resize'),
            dict(type='LoadAnnotations', with_bbox=True),
            dict(meta_keys=( 'img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor',), type='PackDetInputs'),
        ],
        test_mode=True,
        type='CocoDataset'),
    drop_last=False,
    num_workers=2,
    persistent_workers=True,
    sampler=dict(shuffle=False, type='DefaultSampler'))
test_evaluator = dict(
    ann_file='data/ins_annotated_v9/test/annotations_coco.json',
    backend_args=None,
    format_only=False,
    metric='bbox',
    type='CocoMetric')
test_pipeline = [
    dict(backend_args=None, type='LoadImageFromFile'),
    dict(keep_ratio=True, scale=(1280, 1280,), type='Resize'),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor',),type='PackDetInputs'),
]
train_cfg = dict(max_epochs=num_epochs, type='EpochBasedTrainLoop', val_interval=1)
train_dataloader = dict(
    batch_sampler=dict(type='AspectRatioBatchSampler'),
    batch_size=num_batch_size,
    dataset=dict(
        ann_file='train/annotations_coco.json',
        backend_args=None,
        data_prefix=dict(img='train/'),
        data_root=data_root,
        filter_cfg=dict(filter_empty_gt=True, min_size=32),
        metainfo=dict(classes=('waste', ), palette=[(220, 20, 60, ),]),
        pipeline=[
            dict(backend_args=None, type='LoadImageFromFile'),
            dict(type='LoadAnnotations', with_bbox=True),
            dict(keep_ratio=True, scale=(1280, 1280, ), type='Resize'),
            dict(prob=0.5, type='RandomFlip'),
            dict(type='PackDetInputs'),
        ],
        type='CocoDataset'),
    num_workers=2,
    persistent_workers=True,
    sampler=dict(shuffle=True, type='DefaultSampler'))
train_pipeline = [
    dict(backend_args=None, type='LoadImageFromFile'),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(keep_ratio=True, scale=(1280, 1280, ), type='Resize'),
    dict(prob=0.5, type='RandomFlip'),
    dict(type='PackDetInputs'),
]
val_cfg = dict(type='ValLoop')
val_dataloader = dict(
    batch_size=num_batch_size,
    dataset=dict(
        ann_file='valid/annotations_coco.json',
        backend_args=None,
        data_prefix=dict(img='valid/'),
        data_root=data_root,
        metainfo=dict(classes=('waste', ), palette=[(220, 20, 60, ),]),
        pipeline=[
            dict(backend_args=None, type='LoadImageFromFile'),
            dict(keep_ratio=True, scale=(1280, 1280,), type='Resize'),
            dict(type='LoadAnnotations', with_bbox=True),
            dict(meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor', ),type='PackDetInputs'),
        ],
        test_mode=True,
        type='CocoDataset'),
    drop_last=False,
    num_workers=2,
    persistent_workers=True,
    sampler=dict(shuffle=False, type='DefaultSampler'))
val_evaluator = dict(
    ann_file='data/ins_annotated_v9/valid/annotations_coco.json',
    backend_args=None,
    format_only=False,
    metric='bbox',
    type='CocoMetric')
val_pipeline = [
    dict(backend_args=None, type='LoadImageFromFile'),
    dict(keep_ratio=True, scale=(1280, 1280, ), type='Resize'),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor',), type='PackDetInputs'),
]
vis_backends = [dict(type='LocalVisBackend'), ]
visualizer = dict(name='visualizer', type='DetLocalVisualizer', vis_backends=[dict(type='LocalVisBackend'), ])
work_dir = './ins_development/training/ins_annotated_v9/pretrained/add300/faster/2frozen/e9\\'