slowonly_r50_video_4x16x1_256e_kinetics400_rgb.py

model = dict(
    type='Recognizer3D',
    backbone=dict(
        type='ResNet3dSlowOnly',
        depth=50,
        pretrained=None,
        lateral=False,
        conv1_kernel=(1, 7, 7),
        conv1_stride_t=1,
        pool1_stride_t=1,
        inflate=(0, 0, 1, 1),
        norm_eval=False),
    cls_head=dict(
        type='I3DHead',
        in_channels=2048,
        num_classes=400,
        spatial_type='avg',
        dropout_ratio=0.5))
train_cfg = None
test_cfg = dict(average_clips=None)
dataset_type = 'VideoDataset'
data_root = 'data/kinetics400/videos_train'
data_root_val = 'data/kinetics400/videos_val'
ann_file_train = 'data/kinetics400/kinetics400_train_list_videos.txt'
ann_file_val = 'data/kinetics400/kinetics400_val_list_videos.txt'
ann_file_test = 'data/kinetics400/kinetics400_val_list_videos.txt'
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='DecordInit'),
    dict(type='SampleFrames', clip_len=4, frame_interval=16, num_clips=1),
    dict(type='DecordDecode'),
    dict(type='Resize', scale=(-1, 256)),
    dict(type='RandomResizedCrop'),
    dict(type='Resize', scale=(224, 224), keep_ratio=False),
    dict(type='Flip', flip_ratio=0.5),
    dict(type='Normalize', **img_norm_cfg),
    dict(type='FormatShape', input_format='NCTHW'),
    dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
    dict(type='ToTensor', keys=['imgs', 'label'])
]
val_pipeline = [
    dict(type='DecordInit'),
    dict(
        type='SampleFrames',
        clip_len=4,
        frame_interval=16,
        num_clips=1,
        test_mode=True),
    dict(type='DecordDecode'),
    dict(type='Resize', scale=(-1, 256)),
    dict(type='CenterCrop', crop_size=224),
    dict(type='Flip', flip_ratio=0),
    dict(type='Normalize', **img_norm_cfg),
    dict(type='FormatShape', input_format='NCTHW'),
    dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
    dict(type='ToTensor', keys=['imgs'])
]
test_pipeline = [
    dict(type='DecordInit'),
    dict(
        type='SampleFrames',
        clip_len=4,
        frame_interval=16,
        num_clips=10,
        test_mode=True),
    dict(type='DecordDecode'),
    dict(type='Resize', scale=(-1, 256)),
    dict(type='ThreeCrop', crop_size=256),
    dict(type='Flip', flip_ratio=0),
    dict(type='Normalize', **img_norm_cfg),
    dict(type='FormatShape', input_format='NCTHW'),
    dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
    dict(type='ToTensor', keys=['imgs'])
]
data = dict(
    videos_per_gpu=8,
    workers_per_gpu=4,
    train=dict(
        type=dataset_type,
        ann_file=ann_file_train,
        data_prefix=data_root,
        pipeline=train_pipeline),
    val=dict(
        type=dataset_type,
        ann_file=ann_file_val,
        data_prefix=data_root_val,
        pipeline=val_pipeline),
    test=dict(
        type=dataset_type,
        ann_file=ann_file_test,
        data_prefix=data_root_val,
        pipeline=test_pipeline))
# optimizer
optimizer = dict(
    type='SGD', lr=0.1, momentum=0.9,
    weight_decay=0.0001)  # this lr is used for 8 gpus
optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
# learning policy
lr_config = dict(policy='CosineAnnealing', min_lr=0)
total_epochs = 256
checkpoint_config = dict(interval=4)
workflow = [('train', 1)]
evaluation = dict(
    interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'], topk=(1, 5))
log_config = dict(
    interval=20,
    hooks=[
        dict(type='TextLoggerHook'),
        #    dict(type='TensorboardLoggerHook'),
    ])
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/slowonly_r50_video_4x16x1_256e_kinetics400_rgb'
load_from = None
resume_from = None
find_unused_parameters = False