posec3d_action_demo.py

Go to the documentation of this file.

model = dict(
    type='ActionRecognitionRunner',
    backbone=dict(
        resnet3d = dict(
            type='ResNet3d',
            in_channels = 17,
            base_channels = 64,
            stage_blocks = (4, 6, 3),
            out_indices = (2, ),
            spatial_strides = (2, 2, 2),
            temporal_strides = (1, 1, 2),
            dilations = (1, 1, 1),
            conv1_kernel = (1, 7, 7),
            conv1_stride_s = 1,
            conv1_stride_t = 1,
            pool1_stride_s = 1,
            pool1_stride_t = 1,
            inflate = (0, 1, 1),
            inflate_style = '3x1x1',
            input_key = 'pose_heatmap'
        ),
    ),
    head=dict(
        action_upper = dict(
            type='I3DHead',
            in_channels=1024,
            num_classes=6,
            dropout_ratio=0.5,
            input_key = 'resnet3d',
        ),
        action_lower = dict(
            type='I3DHead',
            in_channels=1024,
            num_classes=12,
            dropout_ratio=0.5,
            input_key = 'resnet3d',
        ),
    ),
    predict_keys = dict(
        #예측한 라벨의 키 = 헤드의 키(스코어의 키)
        pred_action_upper = 'action_upper',
        pred_action_lower = 'action_lower',
    )
)
 
score_keys = ['action_upper', 'action_lower']
pred_keys = ['pred_action_upper', 'pred_action_lower']
gt_keys = ['label', 'label']
target_tasks = ['action_upper', 'action_lower']
 
loss = dict(
    MutiTaskCrossEntropyLoss = dict(
        weight = 1.0,
        task_key = 'category',
        pred_keys = score_keys,
        gt_keys = gt_keys,
        target_tasks = target_tasks,
        weights = [1.0, 1.0],
        # data_num = dict(action = [100, 100, 100, 24, 100, 34, 3, 100, 100], pose = [98, 517, 11, 35])
    )
)
 
metric_args = dict(pred_key=pred_keys, 
                   gt_key=gt_keys, 
                   target_tasks=target_tasks,
                   task_key='category')
 
collect_keys = ['pose_heatmap', 'label']
 
data_loader = dict(
    type = 'ActionDatasetLoader_v22',
    data_folder = '/media/safemotion/HDD5/pjm_test/action_train_dataset_2023/action_v22_1st_split',
    category_info = dict(action_upper = 6,
                         action_lower = 12),
    clip_len = 20,
)
ep_mul = 20
train = dict(
    num_workers = 8,
    init_lr = 0.2,
    batch_size = 32,
    epochs = 150*ep_mul,
    optimizer = 'SGD',
    optimizer_args = dict(momentum=0.9, nesterov=True, weight_decay=0.0001),
    # scheduler = 'CosineAnnealingLR',
    scheduler = 'StepLR',
    scheduler_args = dict(T_max=30*ep_mul, eta_min=0),
    adjust_lr_epoch = [10*ep_mul, 50*ep_mul, 100*ep_mul, 130*ep_mul],
    adjust_lr_rate = [0.5, 0.1, 0.1, 0.1],
    val_interval = 1,
 
    
    update_loss_weight = False,
    update_loss_weight_interval = 20,
    base_weight = 0.5,
 
    pretrained = None,#'/media/safemotion/HDD5/pjm_test/action_train_test/9.pth',
    save_root = '/media/safemotion/HDD5/pjm_test/action_train_result/action_2st',
 
)
 
test = dict(
    model_path = '/media/safemotion/HDD5/pjm_test/action_train_result/1st/weights/2835.pth',
    save_root = '',
)