Ei@ S SK r S SKrS SKJr S SKJrJrJrJr S SK J
r
SSK J r J
r
SSKJr SSKJr " S S
\5 rg) N)Path)AnyCallableOptionalUnion)Tensor ) find_classes make_dataset)
VideoClips)
VisionDatasetc ! @ ^ \ rS rSrSrSrSSS.rSrSr S#S
\ \
\ 4 S \
S \ S
\ S\
\ S\ S\S\
\ S\
\\
\4 S\ S\ S\ S\ S\ S\
SS 4 U 4S jjjr\S\\
\4 4S j5 rS \\
S \
S\ S\S\\ 4
S jrS\ 4S jrS \ S\\\\ 4 4S! jrS"rU =r $ )$HMDB51
a>
`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.rar 15e67781e70dcfbdce2d7dbb9b3344b5)urlmd5r Nrootannotation_pathframes_per_clipstep_between_clips
frame_ratefoldtrain transform_precomputed_metadata num_workers _video_width
_video_height_video_min_dimension_audio_samples
output_formatreturnc > [ TU ] U5 US; a [ SU 35 eSn[ U R 5 u U l n[
U R UU5 U l U R VVs/ s H u nnUPM
nnn[ UUUUU U
U U U
UUS9 nUU l X`l
Xpl U R UX&U5 U l
UR U R 5 U l Xl g s snnf )N)r r z$fold should be between 1 and 3, got )avi)r r r r! r" r# )super__init__
ValueErrorr
r classesr samplesr full_video_clipsr r _select_foldindicessubset video_clipsr )selfr r r r r r r r r r r r r! r" r#
extensions class_to_idxpath_ video_pathsr1 __class__s X/home/mande/repo/quber/.venv/lib/python3.13/site-packages/torchvision/datasets/hmdb51.pyr) HMDB51.__init__= s $ y CD6 JK K
%1$))%<" l# II
.2\\:\ qt\ : !#%'!5)'
!,
((oUS &--dll;"- ;s /C&c . U R R $ N)r- metadatar2 s r9 r= HMDB51.metadatas s $$---
video_listannotations_dirc b U( a U R O U R nSU S3n[ R R X&5 n[
R
" U5 n[
5 n U Hf n
[ U
5 n U R 5 n S S S 5 W H9 n
U
R 5 u p[ U5 nUU:X d M( U R U5 M; Mh / n[ U5 H< u nn[ R R U5 U ; d M+ UR U5 M> U$ ! , ( d f N= f)Nz *test_splitz.txt) TRAIN_TAGTEST_TAGosr5 joinglobsetopen readlinessplitintadd enumeratebasenameappend)r2 rA rB r r
target_tagsplit_pattern_namesplit_pattern_pathannotation_pathsselected_filesfilepathfidlineslinevideo_filename
tag_stringtagr/ video_index
video_paths r9 r. HMDB51._select_foldw s ',T^^$--
*4& 5 WW\\/ N 99%78 (Hh 3
-1ZZ\**o*$"&&~6 ) '0'< #Kww
+~={+ (= s 5D
D. c 6 U R R 5 $ r< )r1 num_clipsr> s r9 __len__HMDB51.__len__ s ))++r@ idxc U R R U5 u p#pEU R U nU R U u pGU R b U R U5 nX#U4$ r< )r1 get_clipr/ r, r )r2 re videoaudior6 video_idx sample_index class_indexs r9 __getitem__HMDB51.__getitem__ s^ %)%5%5%>%>s%C"a||I. l3 >> %NN5)E[((r@ )r+ r r- r/ r, r r r1 ) r Nr TNNr r r r r THWC) __name__
__module__ __qualname____firstlineno____doc__data_urlsplitsrD rE r strr rM r boolr dictr r) propertyr= listr. rc tupler rm __static_attributes__
__classcell__)r8 s @r9 r r
s %N \Hb1F IH #$$((,:> $% #!4#CI 4# 4# 4#
4# SM
4# 4# 4# H%4# (S#X 74# 4# 4# 4# " 4# 4# !4#"
#4# 4#l .$sCx. . .tCy 3 c Z^ cghkcl ,, ,)s )uVVS-@'A ) )r@ r )rH rF pathlibr typingr r r r torchr folderr
r video_utilsr visionr
r r@ r9 r s. 1 1 . # !K)] K)r@