QЦiL T S SK r S SKrS SKJrJr S SKJr S SKJr S SKJ r J
r
J r J r J
r
S SKrS SKrS SKJr SSKJrJr S S
KJrJr S S KJr \ \R$ \R$ \ \R6 \ \R6 4 r \ \R$ \R$ \ \R6 4 r S r " S
S\\5 r " S S\ 5 r " S S\ 5 r! " S S\ 5 r" " S S\ 5 r# " S S\ 5 r$S\%S\R6 4S jr&S\%S\ \R6 \R6 4 4S jr'g) N)ABCabstractmethod)globPath)CallableListOptionalTupleUnion)Image )
decode_png read_file ) _read_pfmverify_str_arg)
VisionDataset) KittiFlowSintelFlyingThings3D FlyingChairsHD1Kc ^ \ rS rSrSrSS\\\4 S\\ SS4U 4S jjjr
S\S\ R 4S jr \
S\4S
j5 rS \S\\\4 4S jrS\4S
jrS\S\R* R, R. 4S jrSrU =r$ ) FlowDataset FNroot
transformsreturnc H > [ TU ] US9 X l / U l / U l g )N)r )super__init__r
_flow_list _image_list)selfr r __class__s a/var/www/html/ai-image-ml/venv/lib/python3.13/site-packages/torchvision/datasets/_optical_flow.pyr" FlowDataset.__init__# s'
d#$%',. file_namec t [ R " U5 nUR S:w a UR S5 nU$ )NRGB)r
openmodeconvert)r% r* imgs r' _read_imgFlowDataset._read_img+ s/ jj# 88u ++e$C
r) c g N r% r* s r'
_read_flowFlowDataset._read_flow1 s
r) indexc U R U R U S 5 nU R U R U S 5 nU R ( a7 U R U R U 5 nU R ( a Uu pEOS nOS =pEU R
b U R X#XE5 u p#pEU R ( d Ub X#XE4$ X#U4$ )Nr r )r1 r$ r# r7 _has_builtin_flow_maskr )r% r9 img1img2flowvalid_flow_masks r' __getitem__FlowDataset.__getitem__6 s ~~d . .u 5a 89~~d . .u 5a 89 ????4??5#9:D**(,%o"&%) )D ?? &04D0b -D & &/*Et4 4t# #r) c , [ U R 5 $ r4 )lenr$ )r% s r' __len__FlowDataset.__len__M s 4##$$r) vc \ [ R R R U /U- 5 $ r4 )torchutilsdata
ConcatDataset)r% rF s r' __rmul__FlowDataset.__rmul__P s# {{ --tfqj99r) )r# r$ r r4 )__name__
__module__ __qualname____firstlineno__r; r strr r
r r" r
r1 r r7 intT1T2r@ rD rH rI rJ rK rL __static_attributes__
__classcell__r& s @r' r r s #/U39 - /8H;M /Y] / /3 5;;
C
$ $r2v $.% %:# :%++"2"2"@"@ : :r) r c ^ \ rS rSrSr SS\\\4 S\S\S\\ SS4
U 4S jjjr
S
\ S\\ \
4 4U 4S jjrS \S\R 4S
jrSrU =r$ )r T aD `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 (str or ``pathlib.Path``): 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 8 > [ T U ] XS9 [ USSS9 [ USSS9 US:X a SS /OU/n[ U5 S
- nUS - S - nU H nUS
:X a S OUnX- U- n[ R
" U5 H n [
[ [ X- S- 5 5 5 n
[ [ U
5 S-
5 H" n U =R X XS- //-
sl M$ US
:X d Mj U =R [
[ [ Xi- S- 5 5 5 -
sl M M g )Nr r r[ traintest valid_valuesr\ cleanfinalbothrg re rf r trainingr> r` *.pngr *.flo)
r! r" r r oslistdirsortedr rR rangerC r$ r# )
r% r r[ r\ r passes flow_root split_dir
image_rootscene
image_listir& s
r' r" Sintel.__init__} s d:ug4EFy+ [ TU ] U5 $ 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="test"``.
If a valid flow mask is generated within the ``transforms`` parameter,
a 4-tuple with ``(img1, img2, flow, valid_flow_mask)`` is returned.
r! r@ r% r9 r& s r' r@ Sintel.__getitem__ w"5))r) r* c [ U5 $ r4 _read_flor6 s r' r7 Sintel._read_flow
##r) r5 )r` re NrN rO rP rQ __doc__r rR r r
r r" rS rT rU r@ npndarrayr7 rV rW rX s @r' r r T s &V )- VCI V V V
X& V
V V6
*
*r2v
* $C $BJJ $ $r) r c ^ \ rS rSrSrSrSS\\\4 S\S\ \
SS4U 4S jjjr S
\ S\\
\4 4U 4S jjrS \S\\R$ \R$ 4 4S
jrSrU =r$ )r a `KITTI `__ 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 (str or ``pathlib.Path``): 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 r[ r r c > [ TU ] XS9 [ USSS9 [ U5 S- US- - n[ [ [
US- S- 5 5 5 n[ [ [
US- S - 5 5 5 nU( a U( d [ S
5 e[ XE5 H u pgU =R Xg//-
sl M US :X a) [ [ [
US - S- 5 5 5 U l
g g )
Nr^ r[ r_ rb r ingimage_2z*_10.pngz*_11.pngzZCould not find the Kitti flow images. Please make sure the directory structure is correct.r` flow_occ) r! r" r r rm r rR FileNotFoundErrorzipr$ r# ) r% r r[ r images1images2r< r= r& s r' r" KittiFlow.__init__ s
d:ug4EFDzK'55=9c$"2Z"? @ABc$"2Z"? @ABg#l
g/JD $ . 0 G $T#dZ.?*.L*M%N ODO r) r9 c " > [ TU ] U5 $ )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"``.
ry rz s r' r@ KittiFlow.__getitem__ r| r) r* c [ U5 $ r4 )_read_16bits_png_with_flow_and_valid_maskr6 s r' r7 KittiFlow._read_flow
8CCr) )r# r` N)rN rO rP rQ r r; r rR r r
r r" rS rT rU r@ r r r r7 rV rW rX s @r' r r s & "PU39 - Pc PQYZbQc Pos P P(
*
*r2v
* DC DE"**bjj2H,I D Dr) r c ^ \ rS rSrSrSS\\\4 S\S\\ SS4U 4S jjjr
S \ S\\ \
4 4U 4S
jjrS \S\R 4S jrS
rU =r$ )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 (str or ``pathlib.Path``): 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 r[ r r c > [ T
U ] XS9 [ USSS9 [ U5 S- n[ [ [
US- S- 5 5 5 n[ [ [
US- S- 5 5 5 nS n[ R R X- 5 ( d [ S
5 e[ R " [
X- 5 [ R S 9n[ [ U5 5 Hb nXx n US :X a U S
:X d US:X d M U S:X d M# U =R XX /-
sl U =R" USU- USU- S
- //-
sl Md g )Nr^ r[ )r` valrb r rJ z*.ppmrj zFlyingChairs_train_val.txtzmThe FlyingChairs_train_val.txt file was not found - please download it from the dataset page (see docstring).)dtyper` r r r )r! r" r r rm r rR rk pathexistsr r loadtxtint32rn rC r# r$ ) r% r r[ r imagesflowssplit_file_name
split_listru split_idr& s r' r" FlyingChairs.__init__ s&
d:ug4DEDzN*S !8 9:;tCv
7 89:6ww~~d 455#
ZZD$: ;288L
s5z"A!}H X]8WX=EH:- fQUmVAEAI5F%G$HH #r) r9 c " > [ TU ] U5 $ )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.
ry rz s r' r@ FlyingChairs.__getitem__ r| r) r* c [ U5 $ r4 r~ r6 s r' r7 FlyingChairs._read_flow( r r) r5 r r rX s @r' r r s| 2IU39 - Ic IQYZbQc Ios I I.
*
*r2v
* $C $BJJ $ $r) r c
^ \ rS rSrSr SS\\\4 S\S\S\S\\ S S4 U 4S
jjjr
S \ S \\ \
4 4U 4S jjrS
\S \R 4S jrSrU =r$ )r i, 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 (str or ``pathlib.Path``): 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 r[ r\ camerar r c
& >^^ [ TU ] XS9 [ USSS9 UR 5 n[ USSS9 S/S/SS/S.U n[ TS S
S9 TS :X a S S
/OT/n[ U5 S- nSn[
R " XgU5 GH u nmm[ [ [ X- U- S- 5 5 5 n [ U4S jU 5 5 n [ [ [ US- U- S- 5 5 5 n
[ UU4S jU
5 5 n
U ( a U
( d [ S5 e[ X5 H u p[ [ [ U S- 5 5 5 n
[ [ [ U S- 5 5 5 n[ [ U5 S-
5 H nTS:X a9 U =R X XS- //-
sl U =R X /-
sl MB TS:X d MJ U =R XS- X //-
sl U =R XS- /-
sl M M GM g )Nr^ r[ r_ rb r\ rd frames_cleanpassframes_finalpassr )leftrightrg rg r r r ) into_future into_pastz*/*c 3 @ ># U H n[ U5 T- v M g 7fr4 r ).0 image_dirr s r' *FlyingThings3D.__init__..e s U*YY& 8*s optical_flowc 3 F ># U H n[ U5 T- T- v M g 7fr4 r )r flow_dirr directions r' r r h s! ]S\xtH~ 9F BS\s !zcCould not find the FlyingThings3D flow images. Please make sure the directory structure is correct.ri z*.pfmr r r )r! r" r upperr itertoolsproductrm r rR r r rn rC r$ r# )r% r r[ r\ r r ro cameras
directions
image_dirs flow_dirsr r r r ru r r& s ` @r' r" FlyingThings3D.__init__I s d:ug4EF
y+? tC7(:$; <= s5zA~.A M1 ((fiA -G,HH( EH:5"k1 ((fUmVY-G,HH( Ea%L>9
/ (B -[r) r9 c " > [ TU ] U5 $ rx ry rz s r' r@ FlyingThings3D.__getitem__{ r| r) r* c [ U5 $ r4 )r r6 s r' r7 FlyingThings3D._read_flow r r) r5 )r` re r Nr rX s @r' r r , s > )-
0:CI 0: 0: 0:
0: X&
0:
0: 0:d
*
*r2v
* $C $BJJ $ $r) r c ^ \ rS rSrSrSrSS\\\4 S\S\ \
SS4U 4S jjjr S
\S\ \
R \
R 4 4S jrS \S\\\4 4U 4S
jjrSrU =r$ )r i au `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 (str or ``pathlib.Path``): 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 r[ r r c
> [ T U ] XS9 [ USSS9 [ U5 S- nUS:X a [ S5 H n[ [
[ US- S - US
S 3- 5 5 5 n[ [
[ US - S
- US
S 3- 5 5 5 n[ [ U5 S-
5 H: nU =R XW /-
sl U =R Xg XgS- //-
sl
M< M Ow[ [
[ US- S
- S- 5 5 5 n[ [
[ US- S
- S- 5 5 5 n [ X5 H u pU =R X//-
sl
M U R ( d [ S5 eg )Nr^ r[ r_ rb hd1kr` $ 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 rn rm r rR rC r# r$ r r )
r% r r[ r seq_idxr r ru r r image1image2r& s
r' r"
HD1K.__init__ s}
d:ug4EFDzF" G 9 tC~(=
(JPWX[}\bMc(c$d ef S ) [ TU ] U5 $ )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"``.
ry rz s r' r@ HD1K.__getitem__ r| r) r5 r )rN rO rP rQ r r; r rR r r
r r" r r r r7 rS rT rU r@ rV rW rX s @r' r r s ( "U39 - c QYZbQc os 2DC DE"**bjj2H,I D
*
*r2v
*
*r) r r* r c [ U S5 n[ R " USSS9R 5 nUS:w a [ S5 e[ [ R " USSS95 n[ [ R " USSS95 n[ R " US S
U- U- S9nUR
XCS
5 R S
S S5 sS S S 5 $ ! , ( d f g = f)
z#Read .flo file in Middlebury formatrbc )counts PIEHz)Magic number incorrect. Invalid .flo filez r? s r' r r sy ) 4588 GN *2A2q!8 4nQ1W6M/ 5LB D%**,O ::< ..0 00r) )(r rk abcr r r pathlibr typingr r r
r r r r rH PILr
io.imager r rI r r visionr r rT rU __all__r r r r r r rR r r r5 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)