Training on your own data set, once you start with precision, the next epoch will all become zeros

[luoyq6]

auto_scale_lr = dict(base_batch_size=16, enable=True) backend_args = None data_root = '/data/luoyq/data/toutu/v3' dataset_type = 'VOCDataset' default_hooks = dict( checkpoint=dict(rule='greater', save_best='auto', 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 = 'pytorch' load_from = None log_level = 'INFO' log_processor = dict(by_epoch=True, type='LogProcessor', window_size=50) model = dict( backbone=dict( base_width=4, depth=50, frozen_stages=1, groups=32, init_cfg=dict( checkpoint='open-mmlab://resnext50_32x4d', 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='ResNeXt'), 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(beta=1.0, loss_weight=1.0, type='SmoothL1Loss'), loss_cls=dict( loss_weight=1.0, type='CrossEntropyLoss', use_sigmoid=False), num_classes=4, reg_class_agnostic=True, roi_feat_size=7, type='Shared2FCBBoxHead'), dict( bbox_coder=dict( target_means=[ 0.0, 0.0, 0.0, 0.0, ], target_stds=[ 0.05, 0.05, 0.1, 0.1, ], type='DeltaXYWHBBoxCoder'), fc_out_channels=1024, in_channels=256, loss_bbox=dict(beta=1.0, loss_weight=1.0, type='SmoothL1Loss'), loss_cls=dict( loss_weight=1.0, type='CrossEntropyLoss', use_sigmoid=False), num_classes=4, reg_class_agnostic=True, roi_feat_size=7, type='Shared2FCBBoxHead'), dict( bbox_coder=dict( target_means=[ 0.0, 0.0, 0.0, 0.0, ], target_stds=[ 0.033, 0.033, 0.067, 0.067, ], type='DeltaXYWHBBoxCoder'), fc_out_channels=1024, in_channels=256, loss_bbox=dict(beta=1.0, loss_weight=1.0, type='SmoothL1Loss'), loss_cls=dict( loss_weight=1.0, type='CrossEntropyLoss', use_sigmoid=False), num_classes=4, reg_class_agnostic=True, 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'), num_stages=3, stage_loss_weights=[ 1, 0.5, 0.25, ], type='CascadeRoIHead'), rpn_head=dict( anchor_generator=dict( ratios=[ 0.0625, 0.08333333333333333, 0.5, 1.0, 2.0, 12.0, 16.0, ], scales=[ 4, 8, 16, ], 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( beta=0.1111111111111111, loss_weight=1.0, type='SmoothL1Loss'), 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')), dict( assigner=dict( ignore_iof_thr=-1, match_low_quality=False, min_pos_iou=0.6, neg_iou_thr=0.6, pos_iou_thr=0.6, 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')), dict( assigner=dict( ignore_iof_thr=-1, match_low_quality=False, min_pos_iou=0.7, neg_iou_thr=0.7, pos_iou_thr=0.7, 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=0, 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=2000, min_bbox_size=0, nms=dict(iou_threshold=0.7, type='nms'), nms_pre=2000)), type='CascadeRCNN') optim_wrapper = dict( loss_scale='dynamic', optimizer=dict(lr=0.02, momentum=0.9, type='SGD', weight_decay=0.0001), type='AmpOptimWrapper') 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=[ 30, 60, 90, ], type='MultiStepLR'), ] resume = False test_cfg = dict(type='TestLoop') test_dataloader = dict( batch_size=2, dataset=dict( ann_file='VOC2007/ImageSets/Main/val.txt', backend_args=None, data_prefix=dict(sub_data_root='VOC2007/'), data_root='/data/luoyq/data/toutu/v3', pipeline=[ dict(backend_args=None, type='LoadImageFromFile'), dict(keep_ratio=True, scale=( 2048, 1024, ), 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='VOCDataset'), drop_last=False, num_workers=6, persistent_workers=True, sampler=dict(shuffle=False, type='DefaultSampler')) test_evaluator = dict(eval_mode='11points', metric='mAP', type='VOCMetric') test_pipeline = [ dict(backend_args=None, type='LoadImageFromFile'), dict(keep_ratio=True, scale=( 2048, 1024, ), 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=100, type='EpochBasedTrainLoop', val_interval=1) train_dataloader = dict( batch_sampler=dict(type='AspectRatioBatchSampler'), batch_size=2, dataset=dict( dataset=dict( datasets=[ dict( ann_file='VOC2007/ImageSets/Main/train.txt', backend_args=None, data_prefix=dict(sub_data_root='VOC2007/'), data_root='/data/luoyq/data/toutu/v3', filter_cfg=dict( bbox_min_size=0, filter_empty_gt=True, min_size=32), pipeline=[ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict( keep_ratio=True, scale=[ ( 2600, 1440, ), ( 2048, 1280, ), ], type='RandomResize'), dict(prob=0.5, type='RandomFlip'), dict(type='PackDetInputs'), ], type='VOCDataset'), dict( ann_file='VOC2007/ImageSets/Main/val.txt', backend_args=None, data_prefix=dict(sub_data_root='VOC2007/'), data_root='/data/luoyq/data/toutu/v3', filter_cfg=dict( bbox_min_size=0, filter_empty_gt=True, min_size=32), pipeline=[ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict( keep_ratio=True, scale=[ ( 2600, 1440, ), ( 2048, 1280, ), ], type='RandomResize'), dict(prob=0.5, type='RandomFlip'), dict(type='PackDetInputs'), ], type='VOCDataset'), ], ignore_keys=[ 'dataset_type', ], type='ConcatDataset'), times=3, type='RepeatDataset'), num_workers=6, 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=[ ( 2600, 1440, ), ( 2048, 1280, ), ], type='RandomResize'), dict(prob=0.5, type='RandomFlip'), dict(type='PackDetInputs'), ] val_cfg = dict(type='ValLoop') val_dataloader = dict( batch_size=2, dataset=dict( ann_file='VOC2007/ImageSets/Main/val.txt', backend_args=None, data_prefix=dict(sub_data_root='VOC2007/'), data_root='/data/luoyq/data/toutu/v3', pipeline=[ dict(backend_args=None, type='LoadImageFromFile'), dict(keep_ratio=True, scale=( 2048, 1024, ), 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='VOCDataset'), drop_last=False, num_workers=6, persistent_workers=True, sampler=dict(shuffle=False, type='DefaultSampler')) val_evaluator = dict(eval_mode='11points', metric='mAP', type='VOCMetric') vis_backends = [ dict(type='LocalVisBackend'), ] visualizer = dict( name='visualizer', type='DetLocalVisualizer', vis_backends=[ dict(type='LocalVisBackend'), ]) work_dir = 'work-dir/toutu/v3'

[sunrongqian]

Have you solved this issue yet? I'm conducting instance segmentation for 5 categories, but the AP (Average Precision) for each epoch remains at 0. I've already made changes where I thought were necessary.

[luoyq6]

你解决了这个问题吗？我正在对 5 个类别进行实例分割，但每个 epoch 的 AP （Average Precision） 仍为 0。我已经在我认为必要的地方做了改变。
no

[luoyq6]

@hhaAndroid

[sunrongqian]

你解决了这个问题吗？我正在对 5 个类别进行实例分割，但每个 epoch 的 AP （Average Precision） 仍为 0。我已经在我认为必要的地方做了改变。
no

I have solved the problem. You can try to modify from the example given by the official documentation, that is, build a new weight file, and supplement the parameters you want to change, rather than modify in the original py file. After modification, run python setup.py install on the terminal, and then train.