U
(d @ sx d dl Z d dlZd dlmZmZmZmZmZmZ d dl m
Z
ddl m Z m
Z
ddlmZ ddlmZ G dd d eZdS )
N)OptionalCallableTupleDictAnyList)Tensor ) find_classes make_dataset)
VideoClips)
VisionDatasetc s e Zd ZdZdZdddZdZdZdeee e e
e e e e
e e
e
eef e e e e e edd fd
d
Zee
eef dddZee ee e ee dddZe dddZe eeee f dddZ ZS )HMDB51a
`HMDB51 `_
dataset.
HMDB51 is an action recognition video dataset.
This dataset consider every video as a collection of video clips of fixed size, specified
by ``frames_per_clip``, where the step in frames between each clip is given by
``step_between_clips``.
To give an example, for 2 videos with 10 and 15 frames respectively, if ``frames_per_clip=5``
and ``step_between_clips=5``, the dataset size will be (2 + 3) = 5, where the first two
elements will come from video 1, and the next three elements from video 2.
Note that we drop clips which do not have exactly ``frames_per_clip`` elements, so not all
frames in a video might be present.
Internally, it uses a VideoClips object to handle clip creation.
Args:
root (string): Root directory of the HMDB51 Dataset.
annotation_path (str): Path to the folder containing the split files.
frames_per_clip (int): Number of frames in a clip.
step_between_clips (int): Number of frames between each clip.
fold (int, optional): Which fold to use. Should be between 1 and 3.
train (bool, optional): If ``True``, creates a dataset from the train split,
otherwise from the ``test`` split.
transform (callable, optional): A function/transform that takes in a TxHxWxC video
and returns a transformed version.
output_format (str, optional): The format of the output video tensors (before transforms).
Can be either "THWC" (default) or "TCHW".
Returns:
tuple: A 3-tuple with the following entries:
- video (Tensor[T, H, W, C] or Tensor[T, C, H, W]): The `T` video frames
- audio(Tensor[K, L]): the audio frames, where `K` is the number of channels
and `L` is the number of points
- label (int): class of the video clip
zJhttps://serre-lab.clps.brown.edu/wp-content/uploads/2013/10/hmdb51_org.rarzQhttps://serre-lab.clps.brown.edu/wp-content/uploads/2013/10/test_train_splits.rarZ 15e67781e70dcfbdce2d7dbb9b3344b5)urlmd5r NTr THWC)rootannotation_pathframes_per_clipstep_between_clips
frame_ratefoldtrain transform_precomputed_metadata num_workers _video_width
_video_height_video_min_dimension_audio_samples
output_formatreturnc
s t | |dkr"td| d}t| j\| _}t| j||| _dd | jD }t||||| |
| | |
||d }|| _ || _
|| _ | ||||| _
|| j
| _|| _d S )N)r r z$fold should be between 1 and 3, got )Zavic S s g | ] \}}|qS r$ ).0path_r$ r$ ?/tmp/pip-unpacked-wheel-vx7f76es/torchvision/datasets/hmdb51.py
Z s z#HMDB51.__init__..)r r r r r r! )super__init__
ValueErrorr
r classesr samplesr full_video_clipsr r _select_foldindicesZsubset video_clipsr )selfr r r r r r r r r r r r r r r!
extensionsZ class_to_idxZ video_pathsr2 __class__r$ r( r+ < s< zHMDB51.__init__)r" c C s | j jS N)r/ metadatar3 r$ r$ r( r8 r s zHMDB51.metadata)
video_listannotations_dirr r r" c
C s |r
| j n| j}d| d}tj||}t|}t } |D ]P}
t|
} | } W 5 Q R X | D ]*}
|
\}}t
|}||krb| | qbq>g }t |D ]"\}}tj
|| kr|| q|S )Nz *test_splitz.txt) TRAIN_TAGTEST_TAGosr& joinglobsetopen readlinessplitintadd enumeratebasenameappend)r3 r: r; r r Z
target_tagZsplit_pattern_nameZsplit_pattern_pathZannotation_pathsZselected_filesfilepathZfidlineslineZvideo_filenameZ
tag_stringtagr1 Z video_indexZ
video_pathr$ r$ r( r0 v s$
zHMDB51._select_foldc C s
| j S r7 )r2 Z num_clipsr9 r$ r$ r( __len__ s zHMDB51.__len__)idxr" c C sJ | j |\}}}}| j| }| j| \}}| jd k r@| |}|||fS r7 )r2 Zget_clipr1 r. r )r3 rO videoaudior' Z video_idxZ sample_indexZ class_indexr$ r$ r( __getitem__ s
zHMDB51.__getitem__) r Nr TNNr r r r r r )__name__
__module__ __qualname____doc__Zdata_urlsplitsr< r= strrE r boolr r r r+ propertyr8 r r0 rN r r rR
__classcell__r$ r$ r5 r( r sT ' 6 r )r@ r> typingr r r r r r Ztorchr folderr
r Z video_utilsr Zvisionr
r r$ r$ r$ r( s