_base_ = [
    '../../_base_/models/slowonly_r50.py',
    '../../_base_/schedules/sgd_150e_warmup.py',
    '../../_base_/default_runtime.py'
]

# model settings
model = dict(cls_head=dict(num_classes=101))

# dataset settings
dataset_type = 'RawframeDataset'
data_root = '../mmaction/data/ucf101/rawframes/'
data_root_val = '../mmaction/data/ucf101/rawframes/'
split = 1  # official train/test splits. valid numbers: 1, 2, 3
ann_file_train = f'../mmaction/data/ucf101/ucf101_train_split_{split}_rawframes.txt'
ann_file_val = f'../mmaction/data/ucf101/ucf101_val_split_{split}_rawframes.txt'
ann_file_test = f'../mmaction/data/ucf101/ucf101_val_split_{split}_rawframes.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='SampleFrames', clip_len=8, frame_interval=4, num_clips=1),
    dict(type='RawFrameDecode'),
    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='SampleFrames',
        clip_len=8,
        frame_interval=4,
        num_clips=1,
        test_mode=True),
    dict(type='RawFrameDecode'),
    dict(type='Resize', scale=(-1, 256)),
    dict(type='CenterCrop', crop_size=224),
    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='SampleFrames',
        clip_len=8,
        frame_interval=4,
        num_clips=10,
        test_mode=True),
    dict(type='RawFrameDecode'),
    dict(type='Resize', scale=(-1, 256)),
    dict(type='ThreeCrop', crop_size=256),
    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=2,
    test_dataloader=dict(videos_per_gpu=1),
    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))
evaluation = dict(
    interval=1, metrics=['top_k_accuracy', 'mean_class_accuracy'])

# optimizer
optimizer = dict(lr=0.1)  # this lr is used for 8 gpus
# learning policy
lr_config = dict(policy='CosineAnnealing', min_lr=0, by_epoch=False)
total_epochs = 64

# runtime settings
work_dir = './work_dirs/slowonly_r50_8x4x1_64e_ucf101_rgb'