i3d_r50_8x8x1_48e_mit_rgb.py

_base_ = [
    '../_base_/models/i3d_r50_8f.py', '../_base_/schedules/sgd_48e.py',
    '../_base_/default_runtime.py'
]

# model settings
model = dict(cls_head=dict(num_classes=339))

# dataset settings
dataset_type = 'VideoDataset'
data_root = 'data/mit/videos/training'
data_root_val = 'data/mit/videos/validation'
ann_file_train = 'data/mit/mit_train_list_videos.txt'
ann_file_val = 'data/mit/mit_val_list_videos.txt'
ann_file_test = 'data/mit/mit_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=8, frame_interval=8, num_clips=1),
    dict(type='DecordDecode'),
    dict(type='RandomRescale', scale_range=(256, 320)),
    dict(type='RandomCrop', size=224),
    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=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='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=8,
        frame_interval=8,
        num_clips=10,
        test_mode=True),
    dict(type='DecordDecode'),
    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=8,
    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_val,
        data_prefix=data_root_val,
        pipeline=test_pipeline))
evaluation = dict(
    interval=1, metrics=['top_k_accuracy', 'mean_class_accuracy'])

# runtime settings
checkpoint_config = dict(interval=1)
work_dir = './work_dirs/i3d_r50_8x8x1_48e_mit_rgb/'