Di@ d dl Z d dlZd dlmZ d dlmZmZmZmZ d dl m
Z
ddl m Z m
Z
ddlmZ ddlmZ G d d
e Zy) N)Path)AnyCallableOptionalUnion)Tensor ) find_classes make_dataset)
VideoClips)
VisionDatasetc ! * e Zd ZdZdZdddZdZdZ d!d ee e
f d
e d e d e d
e e de de
de e de ee ef de de de de de de ddf fd
Zedee ef fd Zdee d e de de
dee f
d Zde fd Zd e deeee f fd Z xZS )"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.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
t | | |dvrt d| d}t | j \ | _ }t
| j || | _ | j D cg c] \ }}| }}}t ||||| |
| | |
|| }|| _ || _
|| _ | j |||| | _
|j | j | _ || _ y c c}}w )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_pathsr0 __class__s ]/var/www/pod-logistic/pod-ai/venv/lib/python3.12/site-packages/torchvision/datasets/hmdb51.pyr( zHMDB51.__init__= s $ y CD6 JK K
%1$))%<" l# II
.2\\: qt: : !#%'!5)'
!,
((otUS &--dll;"- ;s - C(c . | j j S N)r, metadatar1 s r8 r; zHMDB51.metadatas s $$---
video_listannotations_dirc : |r | j n | j }d| d}t j j || }t j
| }t
} |D ]b }
t |
5 } | j } d d d D ]7 }
|
j \ }}t | }||k( s'| j | 9 d g }t | D ]8 \ }}t j j | | v s(|j | : |S # 1 sw Y xY w)Nz *test_splitz.txt) TRAIN_TAGTEST_TAGosr4 joinglobsetopen readlinessplitintadd enumeratebasenameappend)r1 r> r? r r
target_tagsplit_pattern_namesplit_pattern_pathannotation_pathsselected_filesfilepathfidlineslinevideo_filename
tag_stringtagr. video_index
video_paths r8 r- zHMDB51._select_foldw s ',T^^$--
*4& 5 WW\\/;M N 99%78 ( 7Hh
(3
(
7-1ZZ\*
*o*$"&&~6
7 7 '0'< , #Kww
+~={+ ,
(
(s 0DD c 6 | j j S r: )r0 num_clipsr< s r8 __len__zHMDB51.__len__ s ))++r= idxc | j j | \ }}}}| j | }| j | \ }}| j | j | }|||fS r: )r0 get_clipr. r+ r )r1 r` videoaudior5 video_idx sample_index class_indexs r8 __getitem__zHMDB51.__getitem__ sf %)%5%5%>%>s%C"ua||I. l3; >> %NN5)Ee[((r= ) r Nr TNNr r r r r THWC)__name__
__module__ __qualname____doc__data_urlsplitsrA rB r strr rJ r boolr dictr r( propertyr; listr- r_ tupler rh
__classcell__)r7 s @r8 r r
s %N \Hb1F IH #$$((,:> $% #!4#CI 4# 4# 4#
4# SM
4# 4# 4# H%4# (S#X 74# 4# 4# 4# " 4# 4# !4#"
#4#l .$sCx. . .tCy 3 c Z^ cghkcl ,, ,)s )uVVS-@'A )r= r )rE rC pathlibr typingr r r r torchr folderr
r video_utilsr visionr
r r= r8 r~ s. 1 1 . # !K)] K)r=