Is it for one video (sequence of images) or a batch of videos?

[maniver7]

Thank you for providing your code. While checking the example code

for batch_idx in range(1000):
    # 'video' should be either a list of images from type of numpy array or PIL images
    video = load_batch(batch_idx)
    video_aug = seq(video)
    train_on_video(video)

the loop is running on batch_idx (i suppose batch of videos) but in comment it says video is list of images. Can I give a batch of videos or I will have to give single video at a time?

[ynalcakan]

I am using vidaug with batches in TF2 like this, I hope it helps:

from vidaug import augmentors as va

# Image augmentation module
def get_augmenter(batch):    
    aug_array = np.zeros_like(batch)
    
    sometimes = lambda aug: va.Sometimes(0.5, aug)
    seq = va.OneOf([
        sometimes(va.VerticalFlip()),
        sometimes(va.RandomRotate(degrees=5)),
        sometimes(va.Downsample()),
        sometimes(va.Upsample()),
        sometimes(va.RandomShear(x=0.2, y=0.2))
    ])
    
    for i, vid in enumerate(batch):
        aug_vid = seq(vid.numpy())
        aug_array[i] = aug_vid
    aug_array = tf.convert_to_tensor(aug_array)
    return aug_array