_base_ = [
    '../../_base_/models/c2d_r50.py', '../../_base_/schedules/sgd_100e.py',
    '../../_base_/default_runtime.py'
]

# dataset settings
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'

file_client_args = dict(io_backend='disk')
train_pipeline = [
    dict(type='DecordInit', **file_client_args),
    dict(type='SampleFrames', clip_len=8, frame_interval=8, num_clips=1),
    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),
    dict(type='FormatShape', input_format='NCTHW'),
    dict(type='PackActionInputs')
]
val_pipeline = [
    dict(type='DecordInit', **file_client_args),
    dict(
        type='SampleFrames',
        clip_len=8,
        frame_interval=8,
        num_clips=1,
        test_mode=True),
    dict(type='DecordDecode'),
    dict(type='Resize', scale=(-1, 256)),
    dict(type='CenterCrop', crop_size=224),
    dict(type='FormatShape', input_format='NCTHW'),
    dict(type='PackActionInputs')
]
test_pipeline = [
    dict(type='DecordInit', **file_client_args),
    dict(
        type='SampleFrames',
        clip_len=8,
        frame_interval=8,
        num_clips=10,
        test_mode=True),
    dict(type='DecordDecode'),
    dict(type='Resize', scale=(-1, 224)),
    dict(type='ThreeCrop', crop_size=224),
    dict(type='FormatShape', input_format='NCTHW'),
    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_val),
        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_val),
        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))

# 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)