tsn_imagenet-pretrained-r50_8xb32-1x1x8-50e_sthv2-rgb.py

_base_ = [
    '../../_base_/models/tsn_r50.py', '../../_base_/schedules/sgd_50e.py',
    '../../_base_/default_runtime.py'
]

# model settings
model = dict(cls_head=dict(num_classes=174, dropout_ratio=0.5))

# dataset settings
dataset_type = 'VideoDataset'
data_root = 'data/sthv2/videos'
ann_file_train = 'data/sthv2/sthv2_train_list_videos.txt'
ann_file_val = 'data/sthv2/sthv2_val_list_videos.txt'

file_client_args = dict(io_backend='disk')

sthv2_flip_label_map = {86: 87, 87: 86, 93: 94, 94: 93, 166: 167, 167: 166}
train_pipeline = [
    dict(type='DecordInit', **file_client_args),
    dict(type='SampleFrames', clip_len=1, frame_interval=1, num_clips=8),
    dict(type='DecordDecode'),
    dict(type='Resize', scale=(-1, 256)),
    dict(
        type='MultiScaleCrop',
        input_size=224,
        scales=(1, 0.875, 0.75, 0.66),
        random_crop=False,
        max_wh_scale_gap=1),
    dict(type='Resize', scale=(224, 224), keep_ratio=False),
    dict(type='Flip', flip_ratio=0.5, flip_label_map=sthv2_flip_label_map),
    dict(type='FormatShape', input_format='NCHW'),
    dict(type='PackActionInputs')
]
val_pipeline = [
    dict(type='DecordInit', **file_client_args),
    dict(
        type='SampleFrames',
        clip_len=1,
        frame_interval=1,
        num_clips=8,
        test_mode=True),
    dict(type='DecordDecode'),
    dict(type='Resize', scale=(-1, 256)),
    dict(type='CenterCrop', crop_size=224),
    dict(type='FormatShape', input_format='NCHW'),
    dict(type='PackActionInputs')
]
test_pipeline = [
    dict(type='DecordInit', **file_client_args),
    dict(
        type='SampleFrames',
        clip_len=1,
        frame_interval=1,
        num_clips=25,
        test_mode=True),
    dict(type='DecordDecode'),
    dict(type='Resize', scale=(-1, 256)),
    dict(type='TenCrop', crop_size=224),
    dict(type='FormatShape', input_format='NCHW'),
    dict(type='PackActionInputs')
]

train_dataloader = dict(
    batch_size=32,
    num_workers=8,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=True),
    dataset=dict(
        type=dataset_type,
        ann_file=ann_file_train,
        data_prefix=dict(video=data_root),
        pipeline=train_pipeline))
val_dataloader = dict(
    batch_size=32,
    num_workers=8,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=dict(
        type=dataset_type,
        ann_file=ann_file_val,
        data_prefix=dict(video=data_root),
        pipeline=val_pipeline,
        test_mode=True))
test_dataloader = dict(
    batch_size=1,
    num_workers=8,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=dict(
        type=dataset_type,
        ann_file=ann_file_val,
        data_prefix=dict(video=data_root),
        pipeline=test_pipeline,
        test_mode=True))

val_evaluator = dict(type='AccMetric')
test_evaluator = val_evaluator

default_hooks = dict(checkpoint=dict(interval=3, max_keep_ckpts=3))

train_cfg = dict(
    type='EpochBasedTrainLoop', max_epochs=50, val_begin=1, val_interval=5)

# Default setting for scaling LR automatically
#   - `enable` means enable scaling LR automatically
#       or not by default.
#   - `base_batch_size` = (8 GPUs) x (32 samples per GPU).
auto_scale_lr = dict(enable=False, base_batch_size=256)