Ph N L d dl Z d dlZd dlmZmZ d dlmZ d dlmZ d dlm Z m
Z
m Z m Z m
Z
d dlZd dlZd dlmZ ddlmZ d d
lmZmZ d d lmZ e ej$ ej$ e ej4 e ej4 f Ze ej$ ej$ e ej4 f Z d Z G d
dee Z G d de Z G d de Z G d de Z! G d de Z" G d de Z#de$dej4 fdZ%de$de ej4 ej4 f fd Z&y) N)ABCabstractmethod)globPath)CallableListOptionalTupleUnion)Image ) _read_png_16 ) _read_pfmverify_str_arg)
VisionDataset) KittiFlowSintelFlyingThings3D FlyingChairsHD1Kc e Zd ZdZddedee ddf fd
Zdedej fdZ e
defd Z d
e de
eef fd Zde fd Zd
e dej& j( j* fdZ xZS ) FlowDatasetFNroot
transformsreturnc P t | | || _ g | _ g | _ y )N)r )super__init__r
_flow_list _image_list)selfr r __class__s mC:\Users\daisl\Desktop\realtime-object-detection\venv\Lib\site-packages\torchvision/datasets/_optical_flow.pyr zFlowDataset.__init__$ s)
d#$%',. file_namec p t j | }|j dk7 r|j d }|S )NRGB)r
openmodeconvert)r# r' imgs r% _read_imgzFlowDataset._read_img, s/ jj# 88u ++e$C
r& c y N r# r' s r%
_read_flowzFlowDataset._read_flow2 s
r& indexc | j | j | d }| j | j | d }| j r3| j | j | }| j r|\ }}nd }nd x}}| j
| j |||| \ }}}}| j s|||||fS |||fS )Nr r )r. r" r! r3 _has_builtin_flow_maskr )r# r4 img1img2flowvalid_flow_masks r% __getitem__zFlowDataset.__getitem__7 s ~~d . .u 5a 89~~d . .u 5a 89 ????4??5#9:D**(,%o"&%) )D? ?? &04dDRa0b -D$o & &/*Et_4 4t# #r& c , t | j S r0 )lenr" )r# s r% __len__zFlowDataset.__len__N s 4##$$r& vc \ t j j j | g|z S r0 )torchutilsdata
ConcatDataset)r# r? s r% __rmul__zFlowDataset.__rmul__Q s# {{ --tfqj99r& r0 )__name__
__module__ __qualname__r6 strr
r r r
r. r r3 intr T1T2r; r> rA rB rC rD rE
__classcell__r$ s @r% r r s #/S /hx.@ /D /3 5;;
C
$ $r2v $.% %:# :%++"2"2"@"@ :r& r c e Zd ZdZ d
dedededee ddf
fd
Zd ede e
e f f fd
Z d ede
j fd Z xZS )r a `Sintel `_ Dataset for optical flow.
The dataset is expected to have the following structure: ::
root
Sintel
testing
clean
scene_1
scene_2
...
final
scene_1
scene_2
...
training
clean
scene_1
scene_2
...
final
scene_1
scene_2
...
flow
scene_1
scene_2
...
Args:
root (string): Root directory of the Sintel Dataset.
split (string, optional): The dataset split, either "train" (default) or "test"
pass_name (string, optional): The pass to use, either "clean" (default), "final", or "both". See link above for
details on the different passes.
transforms (callable, optional): A function/transform that takes in
``img1, img2, flow, valid_flow_mask`` and returns a transformed version.
``valid_flow_mask`` is expected for consistency with other datasets which
return a built-in valid mask, such as :class:`~torchvision.datasets.KittiFlow`.
Nr split pass_namer r c @ t | || t |dd t |dd |dk( rdd gn|g}t | d
z }|d z d z }|D ] }|d
k( rd n|}||z |z }t j
| D ] } t
t t || z dz }
t t |
dz
D ]# } | xj |
| |
| dz ggz
c_ % |d
k( si| xj t
t t || z dz z
c_ y )Nr r rP traintest valid_valuesrQ cleanfinalbothr\ rZ r[ r trainingr9 rU *.pngr *.flo)
r r r r oslistdirsortedr rI ranger= r" r! )
r# r rP rQ r passes flow_root split_dir
image_rootscene
image_listir$ s
r% r zSintel.__init__~ s* dz:ug4EFy+`__ dataset for optical flow (2015).
The dataset is expected to have the following structure: ::
root
KittiFlow
testing
image_2
training
image_2
flow_occ
Args:
root (string): Root directory of the KittiFlow Dataset.
split (string, optional): The dataset split, either "train" (default) or "test"
transforms (callable, optional): A function/transform that takes in
``img1, img2, flow, valid_flow_mask`` and returns a transformed version.
TNr rP r r c t | || t |dd t | dz |dz z }t t t
|dz dz }t t t
|dz d z }|r|s t d
t || D ] \ }}| xj ||ggz
c_ |d k( r)t t t
|d z dz | _
y y )
NrS rP rT rW r ingimage_2z*_10.pngz*_11.pngzZCould not find the Kitti flow images. Please make sure the directory structure is correct.rU flow_occ) r r r r rb r rI FileNotFoundErrorzipr" r! ) r# r rP r images1images2r7 r8 r$ s r% r zKittiFlow.__init__ s
dz:ug4EFDzK'55=9c$"2Z"? @ABc$"2Z"? @ABg#l
gw/JD$ $ . 0 G $T#dZ.?*.L*M%N ODO r& r4 c " t | | S )a Return example at given index.
Args:
index(int): The index of the example to retrieve
Returns:
tuple: A 4-tuple with ``(img1, img2, flow, valid_flow_mask)``
where ``valid_flow_mask`` is a numpy boolean mask of shape (H, W)
indicating which flow values are valid. The flow is a numpy array of
shape (2, H, W) and the images are PIL images. ``flow`` and ``valid_flow_mask`` are None if
``split="test"``.
rm rn s r% r; zKittiFlow.__getitem__ ro r& r' c t | S r0 )_read_16bits_png_with_flow_and_valid_maskr2 s r% r3 zKittiFlow._read_flow
8CCr& rU N)rF rG rH ru r6 rI r
r r rJ r rK rL r; r rv rw r3 rM rN s @r% r r s & "PS P PHXDV Pbf P(
*
*r2v
* DC DE"**bjj2H,I Dr& r c ~ e Zd ZdZd dededee ddf fd
Zdede e
e f f fd Z d
ede
j fd Z xZS )
r a
`FlyingChairs `_ Dataset for optical flow.
You will also need to download the FlyingChairs_train_val.txt file from the dataset page.
The dataset is expected to have the following structure: ::
root
FlyingChairs
data
00001_flow.flo
00001_img1.ppm
00001_img2.ppm
...
FlyingChairs_train_val.txt
Args:
root (string): Root directory of the FlyingChairs Dataset.
split (string, optional): The dataset split, either "train" (default) or "val"
transforms (callable, optional): A function/transform that takes in
``img1, img2, flow, valid_flow_mask`` and returns a transformed version.
``valid_flow_mask`` is expected for consistency with other datasets which
return a built-in valid mask, such as :class:`~torchvision.datasets.KittiFlow`.
Nr rP r r c t
| || t |dd t | dz }t t t
|dz dz }t t t
|dz dz }d }t j j ||z s t d
t j t
||z t j }t t | D ]] }|| } |d k( r| d
k( s |dk( s| dk( s | xj || gz
c_ | xj" |d|z |d|z d
z ggz
c_ _ y )NrS rP )rU valrW r rC z*.ppmr_ zFlyingChairs_train_val.txtzmThe FlyingChairs_train_val.txt file was not found - please download it from the dataset page (see docstring).)dtyperU r r r )r r r r rb r rI r` pathexistsr} rv loadtxtint32rc r= r! r" ) r# r rP r imagesflowssplit_file_name
split_listrj split_idr$ s r% r zFlyingChairs.__init__ s-
dz:ug4DEDzN*S !8 9:;tCv
7 89:6ww~~d_ 45#
ZZD?$: ;288L
s5z"A!!}H X]8WX=E!H:- fQUmVAEAI5F%G$HH #r& r4 c " t | | S )a Return example at given index.
Args:
index(int): The index of the example to retrieve
Returns:
tuple: A 3-tuple with ``(img1, img2, flow)``.
The flow is a numpy array of shape (2, H, W) and the images are PIL images.
``flow`` is None if ``split="val"``.
If a valid flow mask is generated within the ``transforms`` parameter,
a 4-tuple with ``(img1, img2, flow, valid_flow_mask)`` is returned.
rm rn s r% r; zFlyingChairs.__getitem__ ro r& r' c t | S r0 rq r2 s r% r3 zFlyingChairs._read_flow) rs r& r rt rN s @r% r r sf 2IS I IHXDV Ibf I.
*
*r2v
* $C $BJJ $r& r c
e Zd ZdZ ddededededee ddf fd
Zd
ede e
e f f fd Z d ede
j fd
Z xZS )r a `FlyingThings3D `_ dataset for optical flow.
The dataset is expected to have the following structure: ::
root
FlyingThings3D
frames_cleanpass
TEST
TRAIN
frames_finalpass
TEST
TRAIN
optical_flow
TEST
TRAIN
Args:
root (string): Root directory of the intel FlyingThings3D Dataset.
split (string, optional): The dataset split, either "train" (default) or "test"
pass_name (string, optional): The pass to use, either "clean" (default) or "final" or "both". See link above for
details on the different passes.
camera (string, optional): Which camera to return images from. Can be either "left" (default) or "right" or "both".
transforms (callable, optional): A function/transform that takes in
``img1, img2, flow, valid_flow_mask`` and returns a transformed version.
``valid_flow_mask`` is expected for consistency with other datasets which
return a built-in valid mask, such as :class:`~torchvision.datasets.KittiFlow`.
Nr rP rQ camerar r c
$ t | || t |dd |j }t |dd dgdgddgd| }t d d
d k( rd d
gng}t | dz }d}t j ||| D ]~ \ }t t t ||z |z dz } t fd| D } t t t |dz |z dz }
t fd|
D }
| r|
s t d t | |
D ] \ } } t t t | dz }
t t t | dz }t t | dz
D ] }dk( r;| xj |
| |
|dz ggz
c_ | xj || gz
c_ Cdk( sI| xj |
|dz |
| ggz
c_ | xj ||dz gz
c_ y )NrS rP rT rW rQ rY frames_cleanpassframes_finalpassr )leftrightr\ r\ r r r ) into_future into_pastz*/*c 3 : K | ] }t | z y wr0 r ).0 image_dirr s r% z*FlyingThings3D.__init__..f s U*YY& 8*s optical_flowc 3 @ K | ] }t | z z y wr0 r )r flow_dirr directions r% r z*FlyingThings3D.__init__..i s" ]S\xtH~ 9F BS\s zcCould not find the FlyingThings3D flow images. Please make sure the directory structure is correct.r^ z*.pfmr r r )r r r upperr itertoolsproductrb r rI r} r~ rc r= r" r! )r# r rP rQ r r rd cameras
directions
image_dirs flow_dirsr r r r rj r r$ s ` @r% r zFlyingThings3D.__init__J s" dz:ug4EF
y+? tC7(:$; <= s5zA~.A M1 ((fQiA -G,HH( E!H:5"k1 ((fQUmVAY-G,HH( E!a%L>9
/ (B -[r& r4 c " t | | S rl rm rn s r% r; zFlyingThings3D.__getitem__| ro r& r' c t | S r0 )r r2 s r% r3 zFlyingThings3D._read_flow rs r& )rU rZ r Nrt rN s @r% r r - s > )-
0:0: 0: 0:
0: X&
0:
0:d
*
*r2v
* $C $BJJ $r& r c e Zd ZdZdZd
dededee ddf fd
Zd ede e
j e
j f fd
Z d e
deeef f fd Z xZS )r a `HD1K `__ dataset for optical flow.
The dataset is expected to have the following structure: ::
root
hd1k
hd1k_challenge
image_2
hd1k_flow_gt
flow_occ
hd1k_input
image_2
Args:
root (string): Root directory of the HD1K Dataset.
split (string, optional): The dataset split, either "train" (default) or "test"
transforms (callable, optional): A function/transform that takes in
``img1, img2, flow, valid_flow_mask`` and returns a transformed version.
TNr rP r r c
t | || t |dd t | dz }|dk( rt d D ] }t t
t |dz d z |d
d z }t t
t |d z d
z |d
d z }t t | dz
D ]< }| xj || gz
c_ | xj || ||dz ggz
c_
> nxt t
t |dz d
z dz }t t
t |dz d
z dz } t || D ] \ }
} | xj |
| ggz
c_
| j s t d y )NrS rP rT rW hd1krU $ hd1k_flow_gtr| 06dz_*.png
hd1k_inputr{ r hd1k_challengez*10.pngz*11.pngzTCould not find the HD1K images. Please make sure the directory structure is correct.)
r r r r rc rb r rI r= r! r" r~ r} )
r# r rP r seq_idxr r rj r r image1image2r$ s
r% r z
HD1K.__init__ s
dz:ug4EFDzF" G 9 tC~(=
(JPWX[}\bMc(c$d ef S )N *2A2q!8 4nQ1W6M/D 5LB D%**,O ::< ..0 00r& )'r r` abcr r r pathlibr typingr r r
r r r rv rA PILr
io.imager rB r r visionr rw rK rL __all__r r r r r r rI rr r r1 r& r% r s # 9 9 # , ! 5;; Xbjj%98BJJ;O OP
5;; Xbjj%9 9: 4:#} 4:nT$[ T$n:D :DzA$; A$H_$[ _$D@*; @*F8 8 8"1 1rzzSUS]S]G]A^ 1r&