/j
~ d dl mZ d dlZd dlmZ d dlmZ d dlmZ d dl Z d dl
Z d dl Z d dl
mZmZmZ d dl
mZ d dlmZmZmZmZmZmZmZ d d lm Z m Z m Z d d
l m Z G d d Z! e! Z" G d
d Z# e e d ed dfd Z$ ed dddddfdQd!Z%e e j& d"e j' # dd$ddd%d&dd'f dRd9 Z( e dSdTd< Z)dUdVdEZ* e dWdXdI Z+ e dJ edK fdYdP Z,dS )Z ) annotationsN)Callable)Path)Any)Image ImageDraw ImageFont) __version__)IS_COLAB IS_KAGGLELOGGER TryExceptops plt_settingsthreaded)
check_font
check_versionis_ascii)increment_pathc : e Zd ZdZd Zddd
Zedd
ZdS )Colorsa Ultralytics color palette for visualization and plotting.
This class provides methods to work with the Ultralytics color palette, including converting hex color codes to RGB
values and accessing predefined color schemes for object detection and pose estimation.
## Ultralytics Color Palette
| Index | Color | HEX | RGB |
|-------|-------------------------------------------------------------------|-----------|-------------------|
| 0 | | `#042aff` | (4, 42, 255) |
| 1 | | `#0bdbeb` | (11, 219, 235) |
| 2 | | `#f3f3f3` | (243, 243, 243) |
| 3 | | `#00dfb7` | (0, 223, 183) |
| 4 | | `#111f68` | (17, 31, 104) |
| 5 | | `#ff6fdd` | (255, 111, 221) |
| 6 | | `#ff444f` | (255, 68, 79) |
| 7 | | `#cced00` | (204, 237, 0) |
| 8 | | `#00f344` | (0, 243, 68) |
| 9 | | `#bd00ff` | (189, 0, 255) |
| 10 | | `#00b4ff` | (0, 180, 255) |
| 11 | | `#dd00ba` | (221, 0, 186) |
| 12 | | `#00ffff` | (0, 255, 255) |
| 13 | | `#26c000` | (38, 192, 0) |
| 14 | | `#01ffb3` | (1, 255, 179) |
| 15 | | `#7d24ff` | (125, 36, 255) |
| 16 | | `#7b0068` | (123, 0, 104) |
| 17 | | `#ff1b6c` | (255, 27, 108) |
| 18 | | `#fc6d2f` | (252, 109, 47) |
| 19 | | `#a2ff0b` | (162, 255, 11) |
## Pose Color Palette
| Index | Color | HEX | RGB |
|-------|-------------------------------------------------------------------|-----------|-------------------|
| 0 | | `#ff8000` | (255, 128, 0) |
| 1 | | `#ff9933` | (255, 153, 51) |
| 2 | | `#ffb266` | (255, 178, 102) |
| 3 | | `#e6e600` | (230, 230, 0) |
| 4 | | `#ff99ff` | (255, 153, 255) |
| 5 | | `#99ccff` | (153, 204, 255) |
| 6 | | `#ff66ff` | (255, 102, 255) |
| 7 | | `#ff33ff` | (255, 51, 255) |
| 8 | | `#66b2ff` | (102, 178, 255) |
| 9 | | `#3399ff` | (51, 153, 255) |
| 10 | | `#ff9999` | (255, 153, 153) |
| 11 | | `#ff6666` | (255, 102, 102) |
| 12 | | `#ff3333` | (255, 51, 51) |
| 13 | | `#99ff99` | (153, 255, 153) |
| 14 | | `#66ff66` | (102, 255, 102) |
| 15 | | `#33ff33` | (51, 255, 51) |
| 16 | | `#00ff00` | (0, 255, 0) |
| 17 | | `#0000ff` | (0, 0, 255) |
| 18 | | `#ff0000` | (255, 0, 0) |
| 19 | | `#ffffff` | (255, 255, 255) |
!!! note "Ultralytics Brand Colors"
For Ultralytics brand colors see [https://www.ultralytics.com/brand](https://www.ultralytics.com/brand).
Please use the official Ultralytics colors for all marketing materials.
Attributes:
palette (list[tuple]): List of RGB color tuples for general use.
n (int): The number of colors in the palette.
pose_palette (np.ndarray): A specific color palette array for pose estimation with dtype np.uint8.
Examples:
>>> from ultralytics.utils.plotting import Colors
>>> colors = Colors()
>>> colors(5, True) # Returns BGR format: (221, 111, 255)
>>> colors(5, False) # Returns RGB format: (255, 111, 221)
c & d} fd|D _ t j _ t j g dg dg dg dg dg dg d g d
g d g d g d
g dg dg dg dg dg dg dg dg dgt j _ dS )zEInitialize colors as hex = matplotlib.colors.TABLEAU_COLORS.values().)042AFF0BDBEBF3F3F300DFB7111F68FF6FDDFF444FCCED0000F344BD00FF00B4FFDD00BA00FFFF26C00001FFB37D24FF7B0068FF1B6CFC6D2FA2FF0Bc @ g | ]} d | S )#)hex2rgb).0cselfs _/home/longshao/multi-rider-rag/.venv/lib/python3.11/site-packages/ultralytics/utils/plotting.py
z#Colors.__init__..v s+ <<z!Colors.hex2rgb.. sC FFqS1q51q519,-r22FFFFFFr5 )r rQ rO )rU s `r3 r/ zColors.hex2rgb s( FFFFIFFFFFFr5 NF)rJ rK rL rM rN rO )rU rV rN rO )__name__
__module__ __qualname____doc__rI rT staticmethodr/ r5 r3 r r sp F FP2
2
2
h 0 0 0 0 0 G G G \G G Gr5 r c e Zd ZdZ d?d@dZdAdBdZdCdDdZdEdFd Z dGdHd)ZdIdJd-Z dKdLd3Z
d4 Z dMd5Z dNdOd8Z
dPdQd;ZedRd> ZdS )S Annotatora Ultralytics Annotator for train/val mosaics and JPGs and predictions annotations.
Attributes:
im (Image.Image | np.ndarray): The image to annotate.
pil (bool): Whether to use PIL or cv2 for drawing annotations.
font (ImageFont.truetype | ImageFont.load_default): Font used for text annotations.
lw (int): Line width for drawing.
skeleton (list[list[int]]): Skeleton structure for keypoints.
limb_color (np.ndarray): Color palette for limbs.
kpt_color (np.ndarray): Color palette for keypoints.
dark_colors (set): Set of colors considered dark for text contrast.
light_colors (set): Set of colors considered light for text contrast.
Examples:
>>> from ultralytics.utils.plotting import Annotator
>>> im0 = cv2.imread("test.png")
>>> annotator = Annotator(im0, line_width=10)
>>> annotator.box_label([10, 10, 100, 100], "person", (255, 0, 0))
N Arial.ttfFabc
line_width
int | None font_sizefontrV pilrM examplec t | }t |t j }|p|p| _ |p=t t t
|r|j n|j dz dz d _ |s|j d dk r t j |t j }n|j d dk rEt j t j |t j |dddf f }n/|j d dk r t j |dddf } j r.|r|nt j | _ j j dvr j d _ t+ j j d _ t1 |rd
n| }|p9t t t
j j dz d z d } t3 j t7 | | _ n(# t: $ r t3 j _ Y nw xY wt? t@ d
r fd j _! ni|j" j# s
J d |j$ j% r|n|& _ t j dz
d _' j dz _( ddgdd gddgddgd dgdd gddgddgddgddgddgddgddgddgddgddgdd gddgd dgg _) tT j+ g d _, tT j+ g d _- h d _. h d _/ dS )!zjInitialize the Annotator class with image and line width along with color palette for keypoints and limbs.rQ g~jth?rR .N > RGBRGBArq rr zArial.Unicode.ttfgQ ? z9.2.0c H j | dd S )NrQ r\ )rl getbbox)xr2 s r3 z$Annotator.__init__.. s di.?.?.B.B1Q3.G r5 zOImage not contiguous. Apply np.ascontiguousarray(im) to Annotator input images.rY
r\ )r r r r r} r} r} r r r r r rY rY rY rY rY rY rY )rY rY rY rY rY r r r r r r r r r r r r > r r= r r6 D r r6 rR r o r6 r r r r r6 r6 r > r & / m O r r6 h r { l r6 r r r6 r r6 $ } r6 * r\ r6 r r ry )0r
isinstancer rm maxroundsumsizeshapelwcv2cvtColorCOLOR_GRAY2BGRrD ascontiguousarraydstack
zeros_like fromarrayimmodeconvertr Drawdrawr r truetyperV rl Exception load_defaultr pil_versiongetsizedata
contiguousflags writeablecopytfsfskeletoncolorsrG
limb_color kpt_color dark_colors light_colors)
r2 r ri rk rl rm rn non_ascii input_is_pilr s
` r3 rI zAnnotator.__init__ s !))) !"ek22 3)3| eE# .Sbgg28*T*TWX*X[`*`$a$acd e e 7x{a \"c&899!!!)")R r#rPQr'{9S9S4T*U*UVV!q )"S"1"W+66 8 " (Abbeob.A.ADGw|?22 '//%00!tw77DI
5!"L"5"5MM QCc$',.?.?!.Ce.K(L(Lb$Q$Q % .s4yy$ ? ?
5
5
5 % 2 4 4
5 ['22
H$G$G$G$G !7% x x'x x x% H .=bbBGGIIDG$'A+q))DGgkDG H
H
H
H
H
G
G
F
F
F
G
G
F
F
F
F
F
F
F'
, !-.n.n.no ,-e-e-ef
s &A6H "IIr7 r7 r7 r> colorrO txt_colorrN c 2 || j v rdS || j v rdS |S )a1 Assign text color based on background color.
Args:
color (tuple, optional): The background color of the rectangle for text.
txt_color (tuple, optional): The fallback color of the text.
Returns:
(tuple): Text color for label.
Examples:
>>> from ultralytics.utils.plotting import Annotator
>>> im0 = cv2.imread("test.png")
>>> annotator = Annotator(im0, line_width=10)
>>> annotator.get_txt_color(color=(104, 31, 17)) # return (255, 255, 255)
r r> )r r )r2 r r s r3
get_txt_colorzAnnotator.get_txt_color s0 D$ $ $ ;
d'
'
' = r5 labelc
d | || }t |t j r| }t |d t
}|rd |d D n)t
|d t
|d f}| j rX|r,| j d |D | j
| n!| j || j
| |r| j
| \ }}|d |k } |d | j j d |z
k r | j j d |z
|d f}| j |d | r |d |z
n|d |d |z dz | r |d dz n
|d |z dz f| | j |d | r |d |z
n|d f||| j dS dS |r>> from ultralytics.utils.plotting import Annotator
>>> im0 = cv2.imread("test.png")
>>> annotator = Annotator(im0, line_width=10)
>>> annotator.box_label(box=[10, 20, 30, 40], label="person")
r c , g | ]}t | S rd rZ r0 bs r3 r4 z'Annotator.box_label..B s
%
%
%c!ff
%
%
%r5 rR c , g | ]}t | S rd r] r s r3 r4 z'Annotator.box_label..E s '''aq'''r5 widthoutlinefillr rl r? TrQ rp thicknesslineType fontScaler N)r r torchTensortolistlistrS rm r polygonr rectanglerl r r r textr polylinesrD asarrayLINE_AA getTextSizer r r putText) r2 boxr r r multi_pointsp1wrU outsidep2s r3 box_labelzAnnotator.box_label. s &&ui88 c5< ( ( **,,C!#a&$// )5
U
%
%c!f
%
%
%
%CAKKSQRV;U 8 &
ZDI ''3'''tw
#'9#6#6s$'SX#6#Y#Y
py((//1 Q%1*a547<?Q... a 1,be3B ##U ;BqEAIIbeRUQY]Y`LsBqETUIIfhijfknoforsfst $
1G'Fr!uqyyA GU^eienooooo
p
p
CM"*S4445tUDG
#&=c#a&kk3s1v;; 7$'\_\g$ $ $
ua47dgVVVWXY1Q Q%1*a547=+a/// q)A-r!u4BUQYW C1 "Q%!)C
dgr2ub#+FFF GU CBqEAIIbeai!mDG "g [
r5 ?im_gpu torch.Tensoralphafloat retina_masksc H | j r0t j | j | _ |t |t j s
J d | j }t | D ](\ }}|| || t < )t j | j d|z
||d | _ nt |t j
s
J d t | dk r\| ddd dz | j dd< dS |j |j k r| |j }| j j dd \ } }
|st- j |d | |
f d dk }t j | j |j ddd d d z }t j ||j t j
d z }|ddddf }| d }|||z z } d||z z
d } | d j }
| dg
ddd }|| d z |
z }|dz ! | j dd< | j r | " | j dS dS )a Plot masks on image.
Args:
masks (torch.Tensor | np.ndarray): Predicted masks with shape [n, h, w].
colors (list[list[int]]): Colors for predicted masks, [[r, g, b] * n].
im_gpu (torch.Tensor | None): Image on GPU with shape [3, h, w], range [0, 1].
alpha (float, optional): Mask transparency: 0.0 fully transparent, 1.0 opaque.
retina_masks (bool, optional): Whether to use high resolution masks or not.
Nz9`masks` must be a np.ndarray if `im_gpu` is not provided.rR r z7'masks' must be a torch.Tensor if 'im_gpu' is provided.rQ r6 r g o@)devicer@ rp dim)dimsr )#rm rD r r r r ndarray enumerateastyperM r addWeightedr r rB permuter cpunumpyr tor r scale_masksr
from_numpyfliptensorfloat32 unsqueezecumprodr valuesbyter )r2 masksr r r r
overlayrJ maskihiw masks_colorinv_alpha_masksmcss r3 r! zAnnotator.masksk sA 8 1j))..00DG > eRZ00 m m2m m m0gllnnG$U++
7
74-3AY D))**odgq5y'5!LLDGG eU\22 m m4m m m25zzQ #^^Aq! 4 4 ? ? A A E E G G M M O ORU U
} ,, 5<00W]2A2&FB
d (9(9(;(;b"XFFqICO $TW--00 >>FFq!QOOTTUVWWbbddjjllott \& U]SSSV[[FAAAtTM*FOOA&&E 6E>2K 55= 0 9 9! < rQ rp r rR rp rQ r )r r )r rm rD r r r r r r r r rB r circlerS r r liner ceilr )r2 kptsr r, r- r. r nkptndimis_poserJ kcolor_kx_coordy_coordconfskpos1pos2conf1conf2s r3 r4 zAnnotator.kpts sl 0 "-47 8 1j))..00DGZ
d"*/ G dOO m mDAq Y'$XDN1$5$<$<$>$>$>vVWyyG tQqTWGq!Q&&7U1X+=+B+Bq66Q;; Q4Dj((
47S\\3w<<$@&'SU`c`kllll :b>D"4=11
2D"Q%!)a 0113tRUQYN7K3L3LMD"Q%!)a 0113tRUQYN7K3L3LM199 "Q%!)a 0E "Q%!)a 0E z))UZ-?-? 7U1X%**d1ga.@A.E.EaSTX\]^X_bcXcXc 7U1X%**d1ga.@A.E.EaSTX\]^X_bcXcXc G < !3!:!:!>B image.jpgfilenamec ^ t j |t j | j dS )z'Save the annotated image to 'filename'.N)r imwriterD r r )r2 rW s r3 savezAnnotator.save s& Hbj 1 122222r5 bbox tuple | listc 4 | \ }}}}||z
}||z
}||||z fS )an Calculate the dimensions and area of a bounding box.
Args:
bbox (tuple | list): Bounding box coordinates in the format (x_min, y_min, x_max, y_max).
Returns:
width (float): Width of the bounding box.
height (float): Height of the bounding box.
area (float): Area enclosed by the bounding box.
Examples:
>>> from ultralytics.utils.plotting import Annotator
>>> im0 = cv2.imread("test.png")
>>> annotator = Annotator(im0, line_width=10)
>>> annotator.get_bbox_dimension(bbox=[10, 20, 30, 40])
rd )r[ x_miny_minx_maxy_maxr heights r3 get_bbox_dimensionz Annotator.get_bbox_dimension s5 $ &*"ueU
fefn,,r5 )NNrg Frh )
ri rj rk rj rl rV rm rM rn rV )r r> )r rO r rO rN rO )r r r> )r rV r rO r rO )Nr F)r r r r r
rM )r) NTr+ N)
r rO r, rj r- rM r. r r r/ )NNrR )r rS )r> rD rd )r rV r rO rE rV rF rO r^ N)rN rO )rV )rW rV )r[ r\ )r_ r` ra rb rI r r r! r4 r r r rM rT rZ rc rc rd r5 r3 rf rf sw . "& $ X
X
X
X
X
t .; ; ; ; ;z0$ 0$ 0$ 0$ 0$j " ! "&A$ A$ A$ A$ A$F6 6 6 6 6 k k k k k<, , ,
= = = =
! ! ! ! !3 3 3 3 3 - - - \- - -r5 rf rd r c ddl m} ddl}ddlm} t j d|dz d t | dz }| dd } | | g d
} |
d d d
g }
| dddd d } | d
|t j d||dz dz
d } t! | D ]?}
| d j |
d t' |
D @| d d dt+ | cxk rdk rn n| d t! t+ | | d t1 | dd | d | d n| d d t j d| dddd f dz z
d| dddd f dz z g d z } t; j t j d t j d z }tC |dd! | dd! D ]N\ }}tE j# | $ |% dt' | " O| d & | | d ' d# | d ( | d$ | d% d&|
' | d d$ | d d% | d( ( | d) | d* d&|
' | d( d) | d( d* d+D ]-}d,D ](}| | j) | * d- ).|dz }|+ |d./ |, |r
|| dS dS )0a Plot training labels including class histograms and box statistics.
Args:
boxes (np.ndarray): Bounding box coordinates in format [x, y, width, height].
cls (np.ndarray): Class indices.
names (dict, optional): Dictionary mapping class indices to class names.
save_dir (Path, optional): Directory to save the plot.
on_plot (Callable, optional): Function to call after plot is saved.
r N)LinearSegmentedColormapzPlotting labels to z
labels.jpgz... rR i@B )rv yr rb )schema
white_bluewhitebluerQ )r~ r~ Tfigsize tight_layoutr 皙?)binsrwidthc g | ]}|d z S )r6 rd r0 rv s r3 r4 z plot_labels..N s ">">">q1s7">">">r5 instances Z r )rotationfontsizeclassesr\ )rz rz rp r? r6 i r offrv rg 2 )rp cmaprp r rb > r rR rQ rp > rD leftrightrH F dpi)-matplotlib.pyplotpyplotpolarsmatplotlib.colorsrf r
inforS r DataFrame from_listsubplotsravelhistrD linspacerangepatches set_colorr
set_ylabelrB
set_xticksset_xticklabelsr r bar_label
set_xlabel column_stackr r onesrF zipr r r r imshowaxishist2dspines set_visiblesavefigclose)boxesclsnamessave_diron_plotpltr rf ncrv subplot_3_4_coloraxrg rJ imgclass_idr asfnames r3 plot_labelsr 3 st $#####MMM999999 KCh &=CCCDDD SWWYY] B (7(OE'D'D'DEEA 099,RXHYZZ aF > >q A G G I IB
1
3R[BQ 7 7# =c
JJA
2YY @ @ ! Q!!">">F1II">">">????qE[!!!3u::
1s5zz**+++
1 d5<<>> 2 2R" MMM
1!
1### OS5AaC=1#4 4cE!!!QqS&MA>> from ultralytics.utils.plotting import save_one_box
>>> xyxy = [50, 50, 150, 150]
>>> im = cv2.imread("image.jpg")
>>> cropped_im = save_one_box(xyxy, im, file="cropped.jpg", square=True)
r r\ NrQ rR r )r rR )r rp )r r )r rQ T)parentsexist_okz.jpg._ )quality subsampling)r r r stackr xyxy2xywhviewr r xywh2xyxylong
clip_boxesr rS parentmkdirrV r with_suffixsqueezer r rZ ) xyxyr r r r r r rZ r grayscalecropfs r3 save_one_boxr n s F dEL ) ) !{4
diiA&&''A
3QQQU8<<??1%//22!!!QRR%ABBx$$AaaaeH = " "D >$ ) )D q I
c$t*ooDJ/T$Z 3tDz??1RTvTv]`XudmXuXYXYsuTvv wD A $666 t$$0088 9 9#,Rt||B S2R$sDDbDy//d
""1ba"@@@ Kr5 )r rp r* r* r? z
images.jpgi rY r+ labelsdict[str, Any]imagestorch.Tensor | np.ndarraypathslist[str] | Noner rV r dict[int, str] | Noner Callable | Nonemax_size max_subplotsr. rN np.ndarray | Nonec
/ dD ]}
|
| vr|
dk r/| |
j dk r | |
d | |
< t | |
t j r/| |
| |
< | dt j dt j
} | dt j | j t j
} | dt j dt j }
| d d
}| d t j dt j
}| d t j dt j }| d
| }t | rRt |t j r8| }|j d }|dk r9t j |d
d
d
df }t j ||fd }n|dk r|d
d
d
df }|j \ }}}}t% || }t j |dz /t j |d dk r|dz }t j t- /|z t- /|z dfdt j
}t/ | D ][}t- ||/z z t- ||/z z }}|| ddd ||||z |||z d
d
f< \|/z t) || z }|dk r^t3 j ||z }t3 j ||z }t5 j |t9 /fd||fD }t- ||z /z dz } t) | d } t; |t= | dz | dt? | } t/ | D ]}t- ||/z z t- ||/z z }}| ||||z ||z gd
dd |r@| ! |dz |dz gtE || j# d
d d t | dk ru| |k } | | $ d } |d
u } ||| nd
} t |
r|
| }!t |! rg|!d
d
d
d f d k r)|!d!ddgfxx |z cc< |!d!ddgfxx |z cc< n|dk r|!d!d
d fxx |z cc< |!d"xx |z
cc< |!d#xx |z
cc< |!j d$ dk }"|"rtK j& |! ntK j' |! }!tQ |!$ t j
) D ]o\ }#}$| |# }tU | }%|r| || n|}| s | |# | k r+| r| n
| d%| |# d&}&| + |$|&|%' pnkt | r\| D ]Y}tU | }%|r| || n|}| r| n
| d%| d d&}&| ! ||g|&|%d() Zt | r|| , }'t |' rh|'d" d*k s |'d# d*k r!|'d"xx |z cc< |'d#xx |z cc< n |dk r|'|z }'|'d"xx |z
cc< |'d#xx |z
cc< t/ t |' D ]-}#| s | |# | k r | - |'|# | + .t | r'| j d |j d k r!| dk r || }(nn||g }(| . })t j/ d|)dz 0 |)ddf }*|(|*k $ t j }(t j1 | j2 , }+t/ t |( D ] }#| s
| |# | k r tU | |# }%|(|# j \ },}-|,|k s|-|k rW|(|# $ t j
}.t5 j |.||f }.|.$ tf }.n |(|# $ tf }. |+|||z |||z d
d
f |. d,z t j4 |% d-z z |+|||z |||z d
d
f |.<
# tj $ r Y w xY w | 6 |+ |st j1 | j2 S | j2 7 | |r
|| d
S d
S ).a Plot image grid with labels, bounding boxes, masks, and keypoints.
Args:
labels (dict[str, Any]): Dictionary containing detection data with keys like 'cls', 'bboxes', 'conf', 'masks',
'keypoints', 'batch_idx', 'img'.
images (torch.Tensor | np.ndarray): Batch of images to plot. Shape: (batch_size, channels, height, width).
paths (list[str] | None): List of file paths for each image in the batch.
fname (str): Output filename for the plotted image grid.
names (dict[int, str] | None): Dictionary mapping class indices to class names.
on_plot (Callable | None): Callback function to be called after saving the plot.
max_size (int): Maximum size of the output image grid.
max_subplots (int): Maximum number of subplots in the image grid.
save (bool): Whether to save the plotted image grid to a file.
conf_thres (float): Confidence threshold for displaying detections.
Returns:
(np.ndarray | None): Plotted image grid as a numpy array if save is False, None otherwise.
Notes:
This function supports both tensor and numpy array inputs. It will automatically
convert tensor inputs to numpy arrays for processing.
Channel Support:
- 1 channel: Grayscale
- 2 channels: Third channel added as zeros
- 3 channels: Used as-is (standard RGB)
- 4+ channels: Cropped to first 3 channels
> r r< r! bboxesr batch_idx keypointsr rQ rR r r? r r r< Nr! r r )r rp r r6 c 3 < K | ]}t |z V d S rd rZ )r0 rv nss r3 r[ z plot_images.. s- )F)F!#a"f++)F)F)F)F)F)Fr5 g{Gz? r T)ri rk rm rn r> )r r ( ) r r )r r rS r\ g?.).r ).rR r z.1f)r )@ r r r7 )r rF g)\(?)r. g?g333333?)8r6 r r r r r r getrD zerosint64r r rF rB r r concatenateminr3 r fullrS r transposemathr resizerO rf r rV r r r namer r xywhr2xyxyxyxyr r r r r r r4 r arangereshaper r rM rE r r rZ )0r r r r r r r r rZ r. r8 r r r confsr! r4 r1 zerobs_rU r mosaicrJ rv rg scalefs annotatoridxry r< r is_obbjr r r kpts_ image_masksnlindexr mhmwr# r s0 @r3 plot_imagesr s R T 0 0 F?? ::&).A-- q ))!,,F1I fQi . . 0 q
--//F1I
**UBHQbh 7 7 7
8
8C
;"((K(K(KLLI
ZZ"(1BJ"?"?"?
@
@F JJvt $ $E JJw"( ; ; ; < U1X0CCRC0HTcN d d d s88a<<q.C#hooe,,Gd]F!&!25::D6{{
` s u:: 0 QQQU|''))S00 cAq6k***a/*** cAq6k***a/**** c2A2g%/f
"
f
"
R A-5;U*5111 uAUAU ' RX(>(>(E(E(G(G H H E EFAs
A "1IIE+07 !QaA Ea:!5!5*0 J16J6JT!W6J6J6J!++Ce+DDD
E W
` ` `A "1IIE+07 !QaA&, FqFFQ2F2Fa2F2F2FE NNAq65EM^N____ 4yy
H S ((u:: ' V}((**d22eFm6G6G6I6IT6Q6Q f
*
f
*
f
"
f
"
s5zz** H HA Ha:!5!5!uQxJGGG 5zz
(9Q<5;q>11eiikkQ6F6F"'*KK"'*K B Iaa 0 0 8 8"a D DE#.%#7"?"?
"K"KKZ --2244 s; / /00 ! !A !a:!5!5 &wqz 2 2!,Q !5B 77bAgg#.q>#8#8#B#BD#&:dQF#;#;D#';;t#4#4DD#.q>#8#8#>#>D! "1q1u9a!a%i#: ;D AC G"(SX//\_J_ _ q1q5y!a!e)QQQ 6 7 = = ) ! ! ! D! "6 ##B''' (z),'''
Le s Ai
i.-i.path/to/results.csvdirc
| ddl m} ddl}ddlm} | rt | j nt | }t | d }t | s J d|
d g g } }t | D ]G\ }
} | | d } |
dk r| j
D ]5}
d|
v r| |
d |
v r| |
6t | d
z t | d
z }}|d| | d| z ||d z | |d z }| d
t | d
z t | d
z d fd
\ }}| }| | j
d }t | D ]\ }
}| | d }||
||d| j d
d ||
| ||d ddd
||
|d # t0 $ r%}t3 j d| d| Y d}~Ad}~ww xY w|d |d z }| |d | |r
|| dS dS ) a Plot training results from a results CSV file. The function supports various types of data including
segmentation, pose estimation, and classification. Plots are saved as 'results.png' in the directory where the
CSV is located.
Args:
file (str, optional): Path to the CSV file containing the training results.
dir (str, optional): Directory where the CSV file is located if 'file' is not provided.
on_plot (Callable, optional): Callback function to be executed after plotting. Takes filename as an argument.
Examples:
>>> from ultralytics.utils.plotting import plot_results
>>> plot_results("path/to/results.csv")
r Ngaussian_filter1dz results*.csvz No results.csv files found in z, nothing to plot.infer_schema_lengthlossmetricrQ r| Trl r .r~ )markerr linewidth
markersizerp sigma:smoothr r rs )rx zPlotting error for z: rR z results.pngr r ) r r r
scipy.ndimager r r r globrB resolver read_csvcolumnsappendr r selectto_numpyflattenr plotstem set_titler r
errorlegendr r )r r r r plr r files loss_keys metric_keysrJ r r r1 loss_mid
metric_midr figr rv r rg rU r s r3 plot_resultsr% W s $#####//////$(7tDzz d3iiH ~.. / /E u::^^^8H8H8J8J^^^^^: {I% 9 91 9;;qd;;;DAvv . .A {{!((++++!Q #**1---'*9~~':C >wGG1
1a16QST
UUU1
1 / / ; ; ;S\]
^^^1B////
0
9 9 9 L7q77A77 8 8 8 8 8 8 8 8 9qELLNNN } $EKK3K IIKKK s !HJ11
K ;KK viridisro nonerp r} r
edgecolorsc
ddl m} t j | \
fdt t D }| |||| dS )a) Plot a scatter plot with points colored based on a 2D histogram.
Args:
v (array-like): Values for the x-axis.
f (array-like): Values for the y-axis.
bins (int, optional): Number of bins for the histogram.
cmap (str, optional): Colormap for the scatter plot.
alpha (float, optional): Alpha for the scatter plot.
edgecolors (str, optional): Edge colors for the scatter plot.
Examples:
>>> v = np.random.rand(100)
>>> f = np.random.rand(100)
>>> plt_color_scatter(v, f)
r N)rp c g | ]}t t j | d dz
j d dz
t t j | d dz
j d dz
f S )T)r rR r )r rD digitizer )r0 rJ r r vxedgesyedgess r3 r4 z%plt_color_scatter.. s
AaD&55594:a=1;L M M AaD&55594:a=1;L M M
O
r5 )r1 r} r r) )r r rD histogram2dr rB scatter) r- r rp r} r r) r r r r. r/ s `` @@@r3 plt_color_scatterr2 s $##### >!QT:::D&&
s1vv F KK1T:KNNNNNr5 tune_results.csvcsv_fileexclude_zero_fitness_pointsc ddl m ddl}ddlm} fd}t | } | | d }d}d |j D |d }| }|dddf } |r| dk }
||
| |
} }t | dk rt j d dS t d D ]^} |
| }
} | d |
z z
}| |k }
|
r n||
| |
} }_t! j | }t% j t | d
z } d d
t+ | D ]\ }}|dd||z f }|| } |||dz t/ || ddd || dd | d|dddi dd ||z dk r g || d t dt | dz } d d
|| d dd ! | || d " d#d$d%& d' d( d) d ! || d* dS )+a Plot the evolution results stored in a 'tune_results.csv' file. The function generates a scatter plot for each
key in the CSV, color-coded based on fitness scores. The best-performing configurations are highlighted on
the plots.
Args:
csv_file (str, optional): Path to the CSV file containing the tuning results.
exclude_zero_fitness_points (bool, optional): Don't include points with zero fitness in tuning plots.
Examples:
>>> plot_tune_results("path/to/tune_results.csv")
r Nr c | d t j d| dS )z#Save one matplotlib plot to 'file'.r r zSaved N)r r r
r )r r s r3 _save_one_filez)plot_tune_results.._save_one_file sB Dc """ OTOO$$$$$r5 r rR c 6 g | ]}| S rd )striprs s r3 r4 z%plot_tune_results.. s , , ,!AGGII , , ,r5 z@No valid fitness values to plot (all iterations may have failed)rp r )r r Trl r' ro r( )r} r r) zk+rz )r
z = z.3gr r )fontdictbothr~ )r labelsizeztune_scatter_plots.png)r r| ofitness)r linestyler r r
smoothedrQ r zFitness vs Iteration IterationFitnessztune_fitness.png)"r r r r r r r r r rB r
rS r meanstdallrD argmaxr r3 figurer subplotr2 r r rN tick_paramsyticks with_namexlabelylabelgridr )r4 r5 r r r8 r num_metrics_columnskeysrv r? r# r rD rE lower_boundr rC rJ r8 r- mur s @r3 plot_tune_resultsrT s $#####//////% % % % % H~~H
;;xT; : :D , ,t| , , ,-@-A-A BD
A1gG" ,{tWgdm7
7||qYZZZ
1XX , ,LLNNGKKMMcQWn +% 88:: EtWgdm7
'A #d))s"##AJJxdJ333$ 1
aaa((( )
qT Aq!a% !W9CFSSSS W[[]]DR888 Q##2###vqk ::: Vq111 q5A:: JJrNNNN8%%&>??@@@ aW !""AJJwTJ222HHQvYHGGGHHQ!!'333S
VWHXXXII$%%%JJ{JJyHHTNNNJJLLLN8%%&899:::::r5 zruns/detect/exp module_typestagerC r c 2 ddl m} dD ] }||v r dS
t | t j r| j \ }}} }
| dk r|
dk r|d| d| dd d d z } t j | d |d
} t || }|
t j |d z d d
\ }}
|
}
| dd t | D ]P}|
| | | |
| d Qt' j d| d| d| d | | dd | t/ j t3 | d | d dS dS dS dS )ab Visualize feature maps of a given model module during inference.
Args:
x (torch.Tensor): Features to be visualized.
module_type (str): Module type.
stage (int): Module stage within the model.
n (int, optional): Maximum number of feature maps to plot.
save_dir (Path, optional): Directory to save results.
r N> OBBPoseDetectSegmentClassify
RTDETRDecoderrR rW r r r z
_features.pngr
r~ T)rn g?)wspacehspacer{ zSaving z... (/)i, tight)r bbox_inchesz.npy) r r r r r r rsplitchunkr r r r r3 r subplots_adjustr r r r r
r r r rD rZ rV r r )rv rV rW rC r r mr channelsrb r r blocksr rJ s r3 feature_visualizationrk s# $#####
N FF !U\"" D%&W"8VU A::%!))X5XX;+=+=c1+E+Eb+IXXXXA[1X1===FAx ALL1q5!1!114LHHEArB tD 9 9 91XX
"
"1 VAY . . 0 01111
5!!!! K9!99!99h999 : : : KKsK 8 8 8 IIKKK GC
f--..!
0@0@0B0B C C C C C#D D :))r5 ) r r r r r rS r rM r rM rZ rM )r r r r r r r rV r r r r r rS r rS rZ rM r. r rN r )r r N)r rV r rV r r )r& r' ro r( )rp rS r} rV r r r) rV )r3 T)r4 rV r5 rM )rV rV rW rS rC rS r r )-
__future__r r collections.abcr pathlibr typingr r r rD r PILr r r r
r ultralytics.utilsr r r
r r r r ultralytics.utils.checksr r r ultralytics.utils.filesr r r rf r r r r r r% r2 rT rk rd r5 r3 rt s% # " " " " " $ $ $ $ $ $
+ + + + + + + + + + * * * * * * a a a a a a a a a a a a a a a a a a H H H H H H H H H H 2 2 2 2 2 2MG MG MG MG MG MG MG MG`
H- H- H- H- H- H- H- H-V
"$ttBxx 6 6 6
6x h 3 3 3 3 3l
)11A(T(T(T " #' # o o o o
od 3 3 3 3 3l O O O O O@ D; D; D; D; D;N DFY]Y]^oYpYp D D D D D D Dr5