_base_ = [
    '../../_base_/schedules/sgd_tsm_50e.py', '../../_base_/default_runtime.py'
]

# model settings
model = dict(
    type='Recognizer2D',
    backbone=dict(
        type='ResNet',
        pretrained='torchvision://resnet101',
        depth=101,
        norm_eval=False),
    cls_head=dict(
        type='TSNHead',
        num_classes=313,
        in_channels=2048,
        spatial_type='avg',
        consensus=dict(type='AvgConsensus', dim=1),
        loss_cls=dict(type='BCELossWithLogits', loss_weight=160.0),
        dropout_ratio=0.5,
        init_std=0.01,
        multi_class=True,
        label_smooth_eps=0))
# model training and testing settings
train_cfg = None
test_cfg = dict(average_clips=None)

# dataset settings
dataset_type = 'RawframeDataset'
data_root = 'data/mmit/rawframes'
data_root_val = '/data/mmit/rawframes'
ann_file_train = 'data/mmit/mmit_train_rawframes.txt'
ann_file_val = 'data/mmit/mmit_val_rawframes.txt'
ann_file_test = 'data/mmit/mmit_val_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=1, frame_interval=1, num_clips=5),
    dict(type='RawFrameDecode'),
    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='Normalize', **img_norm_cfg),
    dict(type='FormatShape', input_format='NCHW'),
    dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
    dict(type='ToTensor', keys=['imgs', 'label'])
]
val_pipeline = [
    dict(
        type='SampleFrames',
        clip_len=1,
        frame_interval=1,
        num_clips=5,
        test_mode=True),
    dict(type='RawFrameDecode'),
    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='NCHW'),
    dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
    dict(type='ToTensor', keys=['imgs'])
]
test_pipeline = [
    dict(
        type='SampleFrames',
        clip_len=1,
        frame_interval=1,
        num_clips=5,
        test_mode=True),
    dict(type='RawFrameDecode'),
    dict(type='Resize', scale=(-1, 256)),
    dict(type='MultiGroupCrop', crop_size=256, groups=1),
    dict(type='Flip', flip_ratio=0),
    dict(type='Normalize', **img_norm_cfg),
    dict(type='FormatShape', input_format='NCHW'),
    dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
    dict(type='ToTensor', keys=['imgs'])
]

data = dict(
    videos_per_gpu=16,
    workers_per_gpu=4,
    train=dict(
        type=dataset_type,
        ann_file=ann_file_train,
        data_prefix=data_root,
        pipeline=train_pipeline,
        multi_class=True,
        num_classes=313),
    val=dict(
        type=dataset_type,
        ann_file=ann_file_val,
        data_prefix=data_root_val,
        pipeline=val_pipeline,
        multi_class=True,
        num_classes=313),
    test=dict(
        type=dataset_type,
        ann_file=ann_file_test,
        data_prefix=data_root_val,
        pipeline=test_pipeline,
        multi_class=True,
        num_classes=313))
evaluation = dict(interval=5, metrics=['mmit_mean_average_precision'])

# runtime settings
checkpoint_config = dict(interval=5)
work_dir = './work_dirs/tsn_r101_1x1x5_50e_mmit_rgb/'
