o
0iL @ sl 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 ejeje ej e ej f Ze ejeje ej f Z d Z G d
d deeZ G dd de Z G dd de Z G dd de Z!G dd de Z"G dd de Z#de$dejfdd Z%de$de ejejf fd d Z&dS ) N)ABCabstractmethod)globPath)CallableListOptionalTupleUnion)Image ) _read_png_16 ) _read_pfmverify_str_arg)
VisionDataset) KittiFlowSintelFlyingThings3D FlyingChairsHD1Kc s e Zd ZdZddeeef dee ddf fdd
Z dede
j
fd d
Z e defd d Z
d
edeeef fddZdefddZdedejjjfddZ ZS ) FlowDatasetFNroot
transformsreturnc s$ t j|d || _g | _g | _d S )N)r )super__init__r
_flow_list _image_list)selfr r __class__ `/home/ubuntu/SoloSpeech/.venv/lib/python3.10/site-packages/torchvision/datasets/_optical_flow.pyr # s
zFlowDataset.__init__ file_namec C s" t |}|jdkr|d}|S )NRGB)r openmodeconvert)r r% imgr# r# r$ _read_img+ s
zFlowDataset._read_imgc C s d S Nr# r r% r# r# r$
_read_flow1 s zFlowDataset._read_flowindexc C s | | j| d }| | j| d }| jr*| | j| }| jr'|\}}nd }nd }}| jd ur?| ||||\}}}}| jsF|d urL||||fS |||fS )Nr r )r+ r r r. _has_builtin_flow_maskr )r r/ img1img2flowvalid_flow_maskr# r# r$ __getitem__6 s
zFlowDataset.__getitem__c C s
t | jS r, )lenr )r r# r# r$ __len__M s
zFlowDataset.__len__vc C s t jj| g| S r, )torchutilsdata
ConcatDataset)r r8 r# r# r$ __rmul__P s zFlowDataset.__rmul__r, )__name__
__module__ __qualname__r0 r strr r r r r r+ r r. intT1T2r5 r7 r9 r: r; r< r=
__classcell__r# r# r! r$ r s ( r c s| e Zd ZdZ ddeeef dededee d df
fd
d
Z d e
d ee e f f fd
d Z
ded ejfddZ ZS )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 (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`.
traincleanNr split pass_namer r c s t j||d t|ddd t|ddd |dkr dd gn|g}t|d
}|d d }|D ]T}|d
kr7d n|}|| | }t|D ]>} ttt|| d }
t t
|
d D ]} | j |
| |
| d gg7 _ qZ|d
kr| j ttt|| d 7 _ qDq/d S )Nr r rH rF test valid_valuesrI rG finalbothrQ rG rP r trainingr3 rF *.pngr *.flo)
r r r r oslistdirsortedr rA ranger6 r r ) r r rH rI r passes flow_root split_dir
image_rootscene
image_listir! r# r$ r } s$ ""zSintel.__init__r/ 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="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 r5 r r/ r! r# r$ r5
zSintel.__getitem__r% c C t |S r, _read_flor- r# r# r$ r. zSintel._read_flow)rF rG Nr> r? r@ __doc__r rA r r r r rB rC rD r5 npndarrayr. rE r# r# r! r$ r T s$ +
r c s e Zd ZdZdZddeeef dedee ddf fd d
Z
d e dee e
f f fd d
Zdedeejejf fddZ ZS )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.
TrF Nr rH r r c s t j||d t|ddd t|d |d }ttt|d d }ttt|d d }|r5|s9td
t||D ]\}}| j ||gg7 _ q>|d kr`ttt|d d | _
d S d S )
NrJ rH rK rM r ingimage_2z*_10.pngz*_11.pngzZCould not find the Kitti flow images. Please make sure the directory structure is correct.rF flow_occ) r r r r rW r rA FileNotFoundErrorzipr r )r r rH r images1images2r1 r2 r! r# r$ r s zKittiFlow.__init__r/ c r` )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"``.
rb rc r! r# r$ r5 rd zKittiFlow.__getitem__r% c C re r, )_read_16bits_png_with_flow_and_valid_maskr- r# r# r$ r. rh zKittiFlow._read_flowrF N)r> r? r@ rj r0 r rA r r r r rB rC rD r5 r
rk rl r. rE r# r# r! r$ r s , &r c sr e Zd ZdZddeeef dedee ddf fdd
Z d
e
dee e f f fd d Z
d
edejfddZ ZS )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`.
rF Nr rH r r c
s t j||d t|ddd t|d }ttt|d d }ttt|d d }d }tj || s;t
d
t j t|| t j
d }tt|D ]4}|| } |d kr[| d
ksc|dkr| dkr| j|| g7 _| j|d| |d| d
gg7 _qMd S )NrJ rH )rF valrM r r; z*.ppmrT zFlyingChairs_train_val.txtzmThe FlyingChairs_train_val.txt file was not found - please download it from the dataset page (see docstring).)dtyperF r rw r
)r r r r rW r rA rU pathexistsrp rk loadtxtint32rX r6 r r )
r r rH r imagesflowssplit_file_name
split_listr_ split_idr! r# r$ r s$ (zFlyingChairs.__init__r/ c r` )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.
rb rc r! r# r$ r5 rd zFlyingChairs.__getitem__r% c C re r, rf r- r# r# r$ r. ( rh zFlyingChairs._read_flowrv ri r# r# r! r$ r s
, r c
s e Zd ZdZ ddeeef deded ed
ee d df fd d
Z de
d ee e f f fdd Z
ded ejfddZ ZS )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 (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`.
rF rG leftNr rH rI camerar r c s t j||d t|ddd | }t|ddd dgdgddgd| }t d d
d d kr5d d
gn g}t|d }d}t|||D ]\} ttt || | d } t fdd| D } ttt |d | d }
t fdd|
D }
| r|
st
dt | |
D ]b\} } ttt | d }
ttt | d }t t
|d D ]A}dkr| j|
| |
|d gg7 _| j|| g7 _qdkr| j|
|d |
| gg7 _| j||d g7 _qqqGd S )NrJ rH rK rM rI rO frames_cleanpassframes_finalpassr )r rightrQ rQ r r r ) into_future into_pastz*/*c 3 s | ] }t | V qd S r, r ).0 image_dir)r r# r$ e s z*FlyingThings3D.__init__.. optical_flowc 3 s | ] }t | V qd S r, r )r flow_dirr directionr# r$ r h s zcCould not find the FlyingThings3D flow images. Please make sure the directory structure is correct.rS z*.pfmr r r )r r r upperr itertoolsproductrW r rA rp rq rX r6 r r )r r rH rI r r rY cameras
directions
image_dirs flow_dirsr r r} r~ r_ r! r r$ r I sJ zFlyingThings3D.__init__r/ c r` ra rb rc r! r# r$ r5 { rd zFlyingThings3D.__getitem__r% c C re r, )r r- r# r# r$ r. rh zFlyingThings3D._read_flow)rF rG r Nri r# r# r! r$ r , s*
2 r c s e Zd ZdZdZddeeef dedee ddf fd d
Z
d ede e j
e j
f fd d
Zdedeeef f fdd Z ZS )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 (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.
TrF Nr rH r r c sF t j||d t|ddd t|d }|dkrjtdD ]K}ttt|d d |d
d }ttt|d d
|d
d }tt|d D ] }| j || g7 _ | j
|| ||d gg7 _
qKq n0ttt|d d
d }ttt|d d
d } t || D ]\}
} | j
|
| gg7 _
q| j
st dd S )NrJ rH rK rM hd1krF $ hd1k_flow_gtro 06dz_*.png
hd1k_inputrn r hd1k_challengez*10.pngz*11.pngzTCould not find the HD1K images. Please make sure the directory structure is correct.)
r r r r rX rW r rA r6 r r rq rp ) r r rH r seq_idxr~ r} r_ rr rs image1image2r! r# r$ r s* $$" z
HD1K.__init__r% c C re r, rt r- r# r# r$ r. rh zHD1K._read_flowr/ c r` )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"``.
rb rc r! r# r$ r5 rd zHD1K.__getitem__rv )r> r? r@ rj r0 r rA r r r r r
rk rl r. rB rC rD r5 rE r# r# r! r$ r s , &r r% r c C s t | dF}tj|ddd }|dkrtdttj|ddd}ttj|ddd}tj|d d
| | d}|||d
d
d dW d S 1 sNw Y d S )
z#Read .flo file in Middlebury formatrbc )counts PIEHz)Magic number incorrect. Invalid .flo filez s. 7W=DbC"