U
hL @ sh 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#e$ejdddZ%e$e ejejf dd d Z&dS ) N)ABCabstractmethod)globPath)CallableListOptionalTupleUnion)Image ) _read_png_16 ) _read_pfmverify_str_arg)
VisionDataset) KittiFlowSintelFlyingThings3D FlyingChairsHD1Kc s e Zd ZdZdeeef ee dd fdd
Z ee
j
dddZ e ed d
d Z
eeeef d d
dZedddZeejjjdddZ ZS ) FlowDatasetFN)root
transformsreturnc s$ t j|d || _g | _g | _d S )N)r )super__init__r
_flow_list _image_list)selfr r __class__ T/var/www/html/venv/lib/python3.8/site-packages/torchvision/datasets/_optical_flow.pyr # s zFlowDataset.__init__ file_namer c C s" t |}|jdkr |d}|S )NRGB)r openmodeconvert)r r& Zimgr# r# r$ _read_img+ s
zFlowDataset._read_img)r& c C s d S Nr# r r& r# r# r$
_read_flow1 s zFlowDataset._read_flowindexr c C s | | j| d }| | j| d }| jrT| | j| }| jrN|\}}q\d }nd }}| jd k r~| ||||\}}}}| js|d k r||||fS |||fS d S )Nr r )r+ r r r. _has_builtin_flow_maskr )r r0 img1img2flowvalid_flow_maskr# r# r$ __getitem__6 s
zFlowDataset.__getitem__)r c C s
t | jS r, )lenr )r r# r# r$ __len__M s zFlowDataset.__len__)vr c C s t jj| g| S r, )torchutilsdata
ConcatDataset)r r9 r# r# r$ __rmul__P s zFlowDataset.__rmul__)N)__name__
__module__ __qualname__r1 r strr r r r r r+ r r. intT1T2r6 r8 r: r; r< r= r>
__classcell__r# r# r! r$ r s $r c sj e Zd ZdZdeeef eeee dd fdd
Z e
ee e f d fd d
Z
eejd d d
Z ZS )r a `Sintel `_ Dataset for optical flow.
The dataset is expected to have the following structure: ::
root
Sintel
testing
clean
scene_1
scene_2
...
final
scene_1
scene_2
...
training
clean
scene_1
scene_2
...
final
scene_1
scene_2
...
flow
scene_1
scene_2
...
Args:
root (str or ``pathlib.Path``): Root directory of the Sintel Dataset.
split (string, optional): The dataset split, either "train" (default) or "test"
pass_name (string, optional): The pass to use, either "clean" (default), "final", or "both". See link above for
details on the different passes.
transforms (callable, optional): A function/transform that takes in
``img1, img2, flow, valid_flow_mask`` and returns a transformed version.
``valid_flow_mask`` is expected for consistency with other datasets which
return a built-in valid mask, such as :class:`~torchvision.datasets.KittiFlow`.
traincleanN)r split pass_namer r c s t j||d t|ddd t|ddd |dkr`__ dataset for optical flow (2015).
The dataset is expected to have the following structure: ::
root
KittiFlow
testing
image_2
training
image_2
flow_occ
Args:
root (str or ``pathlib.Path``): Root directory of the KittiFlow Dataset.
split (string, optional): The dataset split, either "train" (default) or "test"
transforms (callable, optional): A function/transform that takes in
``img1, img2, flow, valid_flow_mask`` and returns a transformed version.
TrG Nr rI r r c s t j||d t|ddd t|d |d }ttt|d d }ttt|d d }|rj|srtd
t||D ] \}}| j ||gg7 _ q||d krttt|d d | _
d S )
NrK rI rL rN r Zingimage_2z*_10.pngz*_11.pngzZCould not find the Kitti flow images. Please make sure the directory structure is correct.rG flow_occ) r r r r rV r rB FileNotFoundErrorzipr r )r r rI r images1images2r2 r3 r! r# r$ r s zKittiFlow.__init__r/ c s 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"``.
r[ r\ r! r# r$ r6 s
zKittiFlow.__getitem__r% c C s t |S r, )_read_16bits_png_with_flow_and_valid_maskr- r# r# r$ r. s zKittiFlow._read_flow)rG N)r? r@ rA r` r1 r rB r r r r rC rD rE r6 r
ra rb r. rF r# r# r! r$ r s
& r c sh e Zd ZdZd
eeef eee dd fdd
Z e
ee e f d fdd Z
eejd
d d Z 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`.
rG Nrc c
s t j||d t|ddd t|d }ttt|d d }ttt|d d }d }tj || svt
d
t j t|| t j
d }tt|D ]h}|| } |d kr| d
ks|dkr| dkr| j|| g7 _| j|d| |d| d
gg7 _qd S )NrK rI )rG valrN r r< z*.ppmrS zFlyingChairs_train_val.txtzmThe FlyingChairs_train_val.txt file was not found - please download it from the dataset page (see docstring).)ZdtyperG r rl r
)r r r r rV r rB rT pathexistsrf ra ZloadtxtZint32rW r7 r r )
r r rI r imagesflowsZsplit_file_nameZ
split_listrY Zsplit_idr! r# r$ r s zFlyingChairs.__init__r/ c s 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.
r[ r\ r! r# r$ r6 s
zFlyingChairs.__getitem__r% c C s t |S r, r] r- r# r# r$ r. ( s zFlyingChairs._read_flow)rG Nr_ r# r# r! r$ r s & r c sl e Zd ZdZdeeef eeeee dd fdd
Z e
ee e f d fd
d Z
eejd d
dZ 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`.
rG rH leftN)r rI rJ camerar r c s t j||d t|ddd | }t|ddd dgdgddgd| }t d d
d d krjd d
gn g}t|d }d}t|||D ]\\} ttt || | d } t fdd| D } ttt |d | d }
t fdd|
D }
| r |
st
dt | |
D ]\} } ttt | d }
ttt | d }t t
|d D ]}dkr| j|
| |
|d gg7 _| j|| g7 _nBdkr^| j|
|d |
| gg7 _| j||d g7 _q^q qd S )NrK rI rL rN rJ rO Zframes_cleanpassZframes_finalpassrr )rq rightrQ rQ rq rs r ) into_future into_pastz*/*c 3 s | ]}t | V qd S r, r ).0 image_dir)rr r# r$ e s z*FlyingThings3D.__init__..Z optical_flowc 3 s | ]}t | V qd S r, r )rv flow_dirrr directionr# r$ rx h s zcCould not find the FlyingThings3D flow images. Please make sure the directory structure is correct.rR z*.pfmr rt ru )r r r upperr itertoolsproductrV r rB rf rg rW r7 r r )r r rI rJ rr r rX ZcamerasZ
directionsZ
image_dirsZ flow_dirsrw ry ro rp rY r! rz r$ r I sB
zFlyingThings3D.__init__r/ c s t |S rZ r[ r\ r! r# r$ r6 { s
zFlyingThings3D.__getitem__r% c C s t |S r, )r r- r# r# r$ r. s zFlyingThings3D._read_flow)rG rH rq Nr_ r# r# r! r$ r , s
2 r c sv e Zd ZdZdZdeeef eee dd fdd
Z
ee e j
e j
f dd d
Zeeeef d fd d
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.
TrG Nrc c sJ t j||d t|ddd t|d }|dkrtdD ]}ttt|d d |d
d }ttt|d d
|d
d }tt|d D ]8}| j || g7 _ | j
|| ||d gg7 _
qq:nbttt|d d
d }ttt|d d
d } t || D ] \}
} | j
|
| gg7 _
q| j
sFt dd S )NrK rI rL rN Zhd1krG $ Z hd1k_flow_gtre Z06dz_*.pngZ
hd1k_inputrd r Zhd1k_challengez*10.pngz*11.pngzTCould not find the HD1K images. Please make sure the directory structure is correct.)
r r r r rW rV r rB r7 r r rg rf ) r r rI r Zseq_idxrp ro rY rh ri Zimage1Zimage2r! r# r$ r s$ $$& z
HD1K.__init__r% c C s t |S r, rj r- r# r# r$ r. s zHD1K._read_flowr/ c s 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"``.
r[ r\ r! r# r$ r6 s
zHD1K.__getitem__)rG N)r? r@ rA r` r1 r rB r r r r r
ra rb r. rC rD rE r6 rF r# r# r! r$ r s
& r r% c
C s t | d}tj|ddd }|dkr0tdttj|ddd}ttj|ddd}tj|d d
| | d}|||d
d
d dW 5 Q R S Q R X d S )
z#Read .flo file in Middlebury formatrbc )counts PIEHz)Magic number incorrect. Invalid .flo filez s, 7W=DbC