22-8-4 mmaction2 slowfast训练日志

model = dict( type='FastRCNN', backbone=dict( type='ResNet3dSlowFast', pretrained=None, resample_rate=8, speed_ratio=8, channel_ratio=8, slow_pathway=dict( type='resnet3d', depth=50, pretrained=None, lateral=True, conv1_kernel=(1, 7, 7), dilations=(1, 1, 1, 1), conv1_stride_t=1, pool1_stride_t=1, inflate=(0, 0, 1, 1), spatial_strides=(1, 2, 2, 1)), fast_pathway=dict( type='resnet3d', depth=50, pretrained=None, lateral=False, base_channels=8, conv1_kernel=(5, 7, 7), conv1_stride_t=1, pool1_stride_t=1, spatial_strides=(1, 2, 2, 1))), roi_head=dict( type='AVARoIHead', bbox_roi_extractor=dict( type='SingleRoIExtractor3D', roi_layer_type='RoIAlign', output_size=8, with_temporal_pool=True), bbox_head=dict( type='BBoxHeadAVA', in_channels=2304, num_classes=81, multilabel=True, dropout_ratio=0.5)), train_cfg=dict( rcnn=dict( assigner=dict( type='MaxIoUAssignerAVA', pos_iou_thr=0.9, neg_iou_thr=0.9, min_pos_iou=0.9), sampler=dict( type='RandomSampler', num=32, pos_fraction=1, neg_pos_ub=-1, add_gt_as_proposals=True), pos_weight=1.0, debug=False)), test_cfg=dict(rcnn=dict(action_thr=0.002))) dataset_type = 'AVADataset' data_root = '/home/MPCLST/Dataset/rawframes' anno_root = '/home/MPCLST/Dataset/annotations' ann_file_train = '/home/MPCLST/Dataset/annotations/train.csv' ann_file_val = '/home/MPCLST/Dataset/annotations/val.csv' exclude_file_train = '/home/MPCLST/Dataset/annotations/train_excluded_timestamps.csv' exclude_file_val = '/home/MPCLST/Dataset/annotations/val_excluded_timestamps.csv' label_file = '/home/MPCLST/Dataset/annotations/action_list.pbtxt' proposal_file_train = '/home/MPCLST/Dataset/annotations/dense_proposals_train.pkl' proposal_file_val = '/home/MPCLST/Dataset/annotations/dense_proposals_val.pkl' img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False) train_pipeline = [ dict(type='SampleAVAFrames', clip_len=32, frame_interval=2), dict(type='RawFrameDecode'), dict(type='RandomRescale', scale_range=(256, 320)), dict(type='RandomCrop', size=256), dict(type='Flip', flip_ratio=0.5), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False), dict(type='FormatShape', input_format='NCTHW', collapse=True), dict(type='Rename', mapping=dict(imgs='img')), dict(type='ToTensor', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']), dict( type='ToDataContainer', fields=[ dict(key=['proposals', 'gt_bboxes', 'gt_labels'], stack=False) ]), dict( type='Collect', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels'], meta_keys=['scores', 'entity_ids']) ] val_pipeline = [ dict(type='SampleAVAFrames', clip_len=32, frame_interval=2), dict(type='RawFrameDecode'), dict(type='Resize', scale=(-1, 256)), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False), dict(type='FormatShape', input_format='NCTHW', collapse=True), dict(type='Rename', mapping=dict(imgs='img')), dict(type='ToTensor', keys=['img', 'proposals']), dict(type='ToDataContainer', fields=[dict(key='proposals', stack=False)]), dict( type='Collect', keys=['img', 'proposals'], meta_keys=['scores', 'img_shape'], nested=True) ] data = dict( videos_per_gpu=5, workers_per_gpu=2, val_dataloader=dict(videos_per_gpu=1), test_dataloader=dict(videos_per_gpu=1), train=dict( type='AVADataset', ann_file='/home/MPCLST/Dataset/annotations/train.csv', exclude_file= '/home/MPCLST/Dataset/annotations/train_excluded_timestamps.csv', pipeline=[ dict(type='SampleAVAFrames', clip_len=32, frame_interval=2), dict(type='RawFrameDecode'), dict(type='RandomRescale', scale_range=(256, 320)), dict(type='RandomCrop', size=256), dict(type='Flip', flip_ratio=0.5), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False), dict(type='FormatShape', input_format='NCTHW', collapse=True), dict(type='Rename', mapping=dict(imgs='img')), dict( type='ToTensor', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']), dict( type='ToDataContainer', fields=[ dict( key=['proposals', 'gt_bboxes', 'gt_labels'], stack=False) ]), dict( type='Collect', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels'], meta_keys=['scores', 'entity_ids']) ], label_file='/home/MPCLST/Dataset/annotations/action_list.pbtxt', proposal_file= '/home/MPCLST/Dataset/annotations/dense_proposals_train.pkl', person_det_score_thr=0.9, data_prefix='/home/MPCLST/Dataset/rawframes', start_index=1), val=dict( type='AVADataset', ann_file='/home/MPCLST/Dataset/annotations/val.csv', exclude_file= '/home/MPCLST/Dataset/annotations/val_excluded_timestamps.csv', pipeline=[ dict(type='SampleAVAFrames', clip_len=32, frame_interval=2), dict(type='RawFrameDecode'), dict(type='Resize', scale=(-1, 256)), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False), dict(type='FormatShape', input_format='NCTHW', collapse=True), dict(type='Rename', mapping=dict(imgs='img')), dict(type='ToTensor', keys=['img', 'proposals']), dict( type='ToDataContainer', fields=[dict(key='proposals', stack=False)]), dict( type='Collect', keys=['img', 'proposals'], meta_keys=['scores', 'img_shape'], nested=True) ], label_file='/home/MPCLST/Dataset/annotations/action_list.pbtxt', proposal_file= '/home/MPCLST/Dataset/annotations/dense_proposals_val.pkl', person_det_score_thr=0.9, data_prefix='/home/MPCLST/Dataset/rawframes', start_index=1), test=dict( type='AVADataset', ann_file='/home/MPCLST/Dataset/annotations/val.csv', exclude_file= '/home/MPCLST/Dataset/annotations/val_excluded_timestamps.csv', pipeline=[ dict(type='SampleAVAFrames', clip_len=32, frame_interval=2), dict(type='RawFrameDecode'), dict(type='Resize', scale=(-1, 256)), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False), dict(type='FormatShape', input_format='NCTHW', collapse=True), dict(type='Rename', mapping=dict(imgs='img')), dict(type='ToTensor', keys=['img', 'proposals']), dict( type='ToDataContainer', fields=[dict(key='proposals', stack=False)]),