U
hS @ s d dl Z d dlZd dlmZ d dlmZmZmZmZm Z m
Z
m Z d dl m
Z
ddlmZmZ ddlmZ ddlmZ G d d
d
eZdS ) N)Path)AnyCallableDictListOptionalTupleUnion)Tensor ) find_classes make_dataset)
VideoClips)
VisionDatasetc s e Zd ZdZdZdddZdZdZdee e
f e e e e e e e
e e e ee ef e e e e e e dd fd
d
Zeee ef dddZee e e 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 (str or ``pathlib.Path``): 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$fold should be between 1 and 3, got )Zavic S s g | ] \}}|qS r& ).0path_r& r& M/var/www/html/venv/lib/python3.8/site-packages/torchvision/datasets/hmdb51.py
[ s z#HMDB51.__init__..)r r r r! r" r# )super__init__
ValueErrorr r classesr
samplesr full_video_clipsr r _select_foldindicesZsubset video_clipsr )selfr r r r r r r r r r r r r! r" r#
extensionsZ class_to_idxZ video_pathsr4 __class__r& r* r- = s< zHMDB51.__init__)r$ c C s | j jS N)r1 metadatar5 r& r& r* r: s 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)r5 r< r= r r Z
target_tagZsplit_pattern_nameZsplit_pattern_pathZannotation_pathsZselected_filesfilepathZfidlineslineZvideo_filenameZ
tag_stringtagr3 Z video_indexZ
video_pathr& r& r* r2 w s$
zHMDB51._select_foldc C s
| j S r9 )r4 Z num_clipsr; r& r& r* __len__ s zHMDB51.__len__)idxr$ c C sJ | j |\}}}}| j| }| j| \}}| jd k r@| |}|||fS r9 )r4 Zget_clipr3 r0 r )r5 rQ ZvideoZaudior) 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_urlZsplitsr> r? r strr rG r boolr r r r- propertyr: r r2 rP r r
rR
__classcell__r& r& r7 r* r
sT '
6 r )rB r@ pathlibr typingr r r r r r r Ztorchr
folderr r
Z video_utilsr Zvisionr r r& r& r& r* s $