CPU overload

[JulioZhao97]

When running program CPU is heavily overload which is not gonna happen on MMDETECTION(in my experience)?

[JulioZhao97]

config file as follows:

img_norm_cfg = dict( mean=[103.53, 116.28, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False) train_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict( type='Resize', img_scale=[(1333, 480), (1333, 512), (1333, 544), (1333, 576), (1333, 608), (1333, 640), (1333, 672), (1333, 704), (1333, 736), (1333, 768), (1333, 800)], keep_ratio=True, multiscale_mode='value'), dict(type='RandomFlip', flip_ratio=0.5), dict( type='Normalize', mean=[103.53, 116.28, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False), dict(type='Pad', size_divisor=32), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']) ] test_pipeline = [ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1333, 800), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='RandomFlip'), dict( type='Normalize', mean=[103.53, 116.28, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ] data_root = 'data/VOCdevkit/' data = dict( samples_per_gpu=2, workers_per_gpu=2, train=dict( type='FewShotVOCDefaultDataset', save_dataset=True, ann_cfg=[dict(method='TFA', setting='SPLIT3_5SHOT')], img_prefix='data/VOCdevkit/', num_novel_shots=5, num_base_shots=5, pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict( type='Resize', img_scale=[(1333, 480), (1333, 512), (1333, 544), (1333, 576), (1333, 608), (1333, 640), (1333, 672), (1333, 704), (1333, 736), (1333, 768), (1333, 800)], keep_ratio=True, multiscale_mode='value'), dict(type='RandomFlip', flip_ratio=0.5), dict( type='Normalize', mean=[103.53, 116.28, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False), dict(type='Pad', size_divisor=32), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']) ], classes='ALL_CLASSES_SPLIT3', use_difficult=False, instance_wise=False), val=dict( type='FewShotVOCDataset', ann_cfg=[ dict( type='ann_file', ann_file='data/VOCdevkit/VOC2007/ImageSets/Main/test.txt') ], img_prefix='data/VOCdevkit/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1333, 800), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='RandomFlip'), dict( type='Normalize', mean=[103.53, 116.28, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ], classes='ALL_CLASSES_SPLIT3'), test=dict( type='FewShotVOCDataset', ann_cfg=[ dict( type='ann_file', ann_file='data/VOCdevkit/VOC2007/ImageSets/Main/test.txt') ], img_prefix='data/VOCdevkit/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1333, 800), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='RandomFlip'), dict( type='Normalize', mean=[103.53, 116.28, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ], test_mode=True, classes='ALL_CLASSES_SPLIT3')) evaluation = dict( interval=20000, metric='mAP', class_splits=['BASE_CLASSES_SPLIT3', 'NOVEL_CLASSES_SPLIT3']) optimizer = dict(type='SGD', lr=0.001, momentum=0.9, weight_decay=0.0001) optimizer_config = dict(grad_clip=None) lr_config = dict( policy='step', warmup='linear', warmup_iters=10, warmup_ratio=0.001, step=[18000]) runner = dict(type='IterBasedRunner', max_iters=20000) model = dict( type='TFA', pretrained='open-mmlab://detectron2/resnet101_caffe', backbone=dict( type='ResNet', depth=101, num_stages=4, out_indices=(0, 1, 2, 3), frozen_stages=4, norm_cfg=dict(type='BN', requires_grad=False), norm_eval=True, style='caffe'), neck=dict( type='FPN', in_channels=[256, 512, 1024, 2048], out_channels=256, num_outs=5, init_cfg=[ dict( type='Caffe2Xavier', override=dict(type='Caffe2Xavier', name='lateral_convs')), dict( type='Caffe2Xavier', override=dict(type='Caffe2Xavier', name='fpn_convs')) ]), rpn_head=dict( type='RPNHead', in_channels=256, feat_channels=256, anchor_generator=dict( type='AnchorGenerator', scales=[8], ratios=[0.5, 1.0, 2.0], strides=[4, 8, 16, 32, 64]), 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='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0), loss_bbox=dict(type='L1Loss', loss_weight=1.0)), roi_head=dict( type='StandardRoIHead', bbox_roi_extractor=dict( type='SingleRoIExtractor', roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0), out_channels=256, featmap_strides=[4, 8, 16, 32]), bbox_head=dict( type='CosineSimBBoxHead', in_channels=256, fc_out_channels=1024, roi_feat_size=7, num_classes=20, 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='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0), loss_bbox=dict(type='L1Loss', loss_weight=1.0), init_cfg=[ dict( type='Caffe2Xavier', override=dict(type='Caffe2Xavier', name='shared_fcs')), dict( type='Normal', override=dict(type='Normal', name='fc_cls', std=0.01)), dict( type='Normal', override=dict(type='Normal', name='fc_reg', std=0.001)) ], num_shared_fcs=2, scale=20)), 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=-1, pos_weight=-1, debug=False), rpn_proposal=dict( nms_pre=2000, max_per_img=1000, 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=512, pos_fraction=0.25, neg_pos_ub=-1, add_gt_as_proposals=True), pos_weight=-1, debug=False)), test_cfg=dict( rpn=dict( nms_pre=1000, max_per_img=1000, nms=dict(type='nms', iou_threshold=0.7), min_bbox_size=0), rcnn=dict( score_thr=0.05, nms=dict(type='nms', iou_threshold=0.5), max_per_img=100)), frozen_parameters=[ 'backbone', 'neck', 'rpn_head', 'roi_head.bbox_head.shared_fcs' ]) checkpoint_config = dict(interval=20000) log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')]) custom_hooks = [dict(type='NumClassCheckHook')] dist_params = dict(backend='nccl') log_level = 'INFO' load_from = 'work_dirs/voc/split3/tfa/tfa_r101_fpn_voc-split3_base-training_20211031_114840_random-init-bbox-head-9bb8c09b.pth' resume_from = None workflow = [('train', 1)] use_infinite_sampler = True seed = 42 work_dir = './work_dirs/voc/split3/tfa/3shot/tfa_r101_fpn_voc-split3_3shot-fine-tuning' gpu_ids = range(0, 1)

[linyq17]

The config file seems right. I'm not sure what causes this problem since the fine-tuning only train the bbox classification head. We will look into it.