You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
319 lines
14 KiB
319 lines
14 KiB
# Ultralytics YOLO 🚀, GPL-3.0 license |
|
|
|
import contextlib |
|
import math |
|
from pathlib import Path |
|
from urllib.error import URLError |
|
|
|
import cv2 |
|
import matplotlib.pyplot as plt |
|
import numpy as np |
|
import pandas as pd |
|
import torch |
|
from PIL import Image, ImageDraw, ImageFont |
|
|
|
from ultralytics.yolo.utils import FONT, USER_CONFIG_DIR, threaded |
|
|
|
from .checks import check_font, check_requirements, is_ascii |
|
from .files import increment_path |
|
from .ops import clip_coords, scale_image, xywh2xyxy, xyxy2xywh |
|
|
|
|
|
class Colors: |
|
# Ultralytics color palette https://ultralytics.com/ |
|
def __init__(self): |
|
# hex = matplotlib.colors.TABLEAU_COLORS.values() |
|
hexs = ('FF3838', 'FF9D97', 'FF701F', 'FFB21D', 'CFD231', '48F90A', '92CC17', '3DDB86', '1A9334', '00D4BB', |
|
'2C99A8', '00C2FF', '344593', '6473FF', '0018EC', '8438FF', '520085', 'CB38FF', 'FF95C8', 'FF37C7') |
|
self.palette = [self.hex2rgb(f'#{c}') for c in hexs] |
|
self.n = len(self.palette) |
|
|
|
def __call__(self, i, bgr=False): |
|
c = self.palette[int(i) % self.n] |
|
return (c[2], c[1], c[0]) if bgr else c |
|
|
|
@staticmethod |
|
def hex2rgb(h): # rgb order (PIL) |
|
return tuple(int(h[1 + i:1 + i + 2], 16) for i in (0, 2, 4)) |
|
|
|
|
|
colors = Colors() # create instance for 'from utils.plots import colors' |
|
|
|
|
|
class Annotator: |
|
# YOLOv8 Annotator for train/val mosaics and jpgs and detect/hub inference annotations |
|
def __init__(self, im, line_width=None, font_size=None, font='Arial.ttf', pil=False, example='abc'): |
|
assert im.data.contiguous, 'Image not contiguous. Apply np.ascontiguousarray(im) to Annotator() input images.' |
|
non_ascii = not is_ascii(example) # non-latin labels, i.e. asian, arabic, cyrillic |
|
self.pil = pil or non_ascii |
|
if self.pil: # use PIL |
|
self.im = im if isinstance(im, Image.Image) else Image.fromarray(im) |
|
self.draw = ImageDraw.Draw(self.im) |
|
self.font = check_pil_font(font='Arial.Unicode.ttf' if non_ascii else font, |
|
size=font_size or max(round(sum(self.im.size) / 2 * 0.035), 12)) |
|
else: # use cv2 |
|
self.im = im |
|
self.lw = line_width or max(round(sum(im.shape) / 2 * 0.003), 2) # line width |
|
|
|
def box_label(self, box, label='', color=(128, 128, 128), txt_color=(255, 255, 255)): |
|
# Add one xyxy box to image with label |
|
if self.pil or not is_ascii(label): |
|
self.draw.rectangle(box, width=self.lw, outline=color) # box |
|
if label: |
|
w, h = self.font.getsize(label) # text width, height |
|
outside = box[1] - h >= 0 # label fits outside box |
|
self.draw.rectangle( |
|
(box[0], box[1] - h if outside else box[1], box[0] + w + 1, |
|
box[1] + 1 if outside else box[1] + h + 1), |
|
fill=color, |
|
) |
|
# self.draw.text((box[0], box[1]), label, fill=txt_color, font=self.font, anchor='ls') # for PIL>8.0 |
|
self.draw.text((box[0], box[1] - h if outside else box[1]), label, fill=txt_color, font=self.font) |
|
else: # cv2 |
|
p1, p2 = (int(box[0]), int(box[1])), (int(box[2]), int(box[3])) |
|
cv2.rectangle(self.im, p1, p2, color, thickness=self.lw, lineType=cv2.LINE_AA) |
|
if label: |
|
tf = max(self.lw - 1, 1) # font thickness |
|
w, h = cv2.getTextSize(label, 0, fontScale=self.lw / 3, thickness=tf)[0] # text width, height |
|
outside = p1[1] - h >= 3 |
|
p2 = p1[0] + w, p1[1] - h - 3 if outside else p1[1] + h + 3 |
|
cv2.rectangle(self.im, p1, p2, color, -1, cv2.LINE_AA) # filled |
|
cv2.putText(self.im, |
|
label, (p1[0], p1[1] - 2 if outside else p1[1] + h + 2), |
|
0, |
|
self.lw / 3, |
|
txt_color, |
|
thickness=tf, |
|
lineType=cv2.LINE_AA) |
|
|
|
def masks(self, masks, colors, im_gpu, alpha=0.5, retina_masks=False): |
|
"""Plot masks at once. |
|
Args: |
|
masks (tensor): predicted masks on cuda, shape: [n, h, w] |
|
colors (List[List[Int]]): colors for predicted masks, [[r, g, b] * n] |
|
im_gpu (tensor): img is in cuda, shape: [3, h, w], range: [0, 1] |
|
alpha (float): mask transparency: 0.0 fully transparent, 1.0 opaque |
|
""" |
|
if self.pil: |
|
# convert to numpy first |
|
self.im = np.asarray(self.im).copy() |
|
if len(masks) == 0: |
|
self.im[:] = im_gpu.permute(1, 2, 0).contiguous().cpu().numpy() * 255 |
|
colors = torch.tensor(colors, device=im_gpu.device, dtype=torch.float32) / 255.0 |
|
colors = colors[:, None, None] # shape(n,1,1,3) |
|
masks = masks.unsqueeze(3) # shape(n,h,w,1) |
|
masks_color = masks * (colors * alpha) # shape(n,h,w,3) |
|
|
|
inv_alph_masks = (1 - masks * alpha).cumprod(0) # shape(n,h,w,1) |
|
mcs = (masks_color * inv_alph_masks).sum(0) * 2 # mask color summand shape(n,h,w,3) |
|
|
|
im_gpu = im_gpu.flip(dims=[0]) # flip channel |
|
im_gpu = im_gpu.permute(1, 2, 0).contiguous() # shape(h,w,3) |
|
im_gpu = im_gpu * inv_alph_masks[-1] + mcs |
|
im_mask = (im_gpu * 255) |
|
im_mask_np = im_mask.byte().cpu().numpy() |
|
self.im[:] = im_mask_np if retina_masks else scale_image(im_gpu.shape, im_mask_np, self.im.shape) |
|
if self.pil: |
|
# convert im back to PIL and update draw |
|
self.fromarray(self.im) |
|
|
|
def rectangle(self, xy, fill=None, outline=None, width=1): |
|
# Add rectangle to image (PIL-only) |
|
self.draw.rectangle(xy, fill, outline, width) |
|
|
|
def text(self, xy, text, txt_color=(255, 255, 255), anchor='top'): |
|
# Add text to image (PIL-only) |
|
if anchor == 'bottom': # start y from font bottom |
|
w, h = self.font.getsize(text) # text width, height |
|
xy[1] += 1 - h |
|
self.draw.text(xy, text, fill=txt_color, font=self.font) |
|
|
|
def fromarray(self, im): |
|
# Update self.im from a numpy array |
|
self.im = im if isinstance(im, Image.Image) else Image.fromarray(im) |
|
self.draw = ImageDraw.Draw(self.im) |
|
|
|
def result(self): |
|
# Return annotated image as array |
|
return np.asarray(self.im) |
|
|
|
|
|
def check_pil_font(font=FONT, size=10): |
|
# Return a PIL TrueType Font, downloading to CONFIG_DIR if necessary |
|
font = Path(font) |
|
font = font if font.exists() else (USER_CONFIG_DIR / font.name) |
|
try: |
|
return ImageFont.truetype(str(font) if font.exists() else font.name, size) |
|
except Exception: # download if missing |
|
try: |
|
check_font(font) |
|
return ImageFont.truetype(str(font), size) |
|
except TypeError: |
|
check_requirements('Pillow>=8.4.0') # known issue https://github.com/ultralytics/yolov5/issues/5374 |
|
except URLError: # not online |
|
return ImageFont.load_default() |
|
|
|
|
|
def save_one_box(xyxy, im, file=Path('im.jpg'), gain=1.02, pad=10, square=False, BGR=False, save=True): |
|
# Save image crop as {file} with crop size multiple {gain} and {pad} pixels. Save and/or return crop |
|
xyxy = torch.tensor(xyxy).view(-1, 4) |
|
b = xyxy2xywh(xyxy) # boxes |
|
if square: |
|
b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1) # attempt rectangle to square |
|
b[:, 2:] = b[:, 2:] * gain + pad # box wh * gain + pad |
|
xyxy = xywh2xyxy(b).long() |
|
clip_coords(xyxy, im.shape) |
|
crop = im[int(xyxy[0, 1]):int(xyxy[0, 3]), int(xyxy[0, 0]):int(xyxy[0, 2]), ::(1 if BGR else -1)] |
|
if save: |
|
file.parent.mkdir(parents=True, exist_ok=True) # make directory |
|
f = str(increment_path(file).with_suffix('.jpg')) |
|
# cv2.imwrite(f, crop) # save BGR, https://github.com/ultralytics/yolov5/issues/7007 chroma subsampling issue |
|
Image.fromarray(crop[..., ::-1]).save(f, quality=95, subsampling=0) # save RGB |
|
return crop |
|
|
|
|
|
@threaded |
|
def plot_images(images, |
|
batch_idx, |
|
cls, |
|
bboxes, |
|
masks=np.zeros(0, dtype=np.uint8), |
|
paths=None, |
|
fname='images.jpg', |
|
names=None): |
|
# Plot image grid with labels |
|
if isinstance(images, torch.Tensor): |
|
images = images.cpu().float().numpy() |
|
if isinstance(cls, torch.Tensor): |
|
cls = cls.cpu().numpy() |
|
if isinstance(bboxes, torch.Tensor): |
|
bboxes = bboxes.cpu().numpy() |
|
if isinstance(masks, torch.Tensor): |
|
masks = masks.cpu().numpy().astype(int) |
|
if isinstance(batch_idx, torch.Tensor): |
|
batch_idx = batch_idx.cpu().numpy() |
|
|
|
max_size = 1920 # max image size |
|
max_subplots = 16 # max image subplots, i.e. 4x4 |
|
bs, _, h, w = images.shape # batch size, _, height, width |
|
bs = min(bs, max_subplots) # limit plot images |
|
ns = np.ceil(bs ** 0.5) # number of subplots (square) |
|
if np.max(images[0]) <= 1: |
|
images *= 255 # de-normalise (optional) |
|
|
|
# Build Image |
|
mosaic = np.full((int(ns * h), int(ns * w), 3), 255, dtype=np.uint8) # init |
|
for i, im in enumerate(images): |
|
if i == max_subplots: # if last batch has fewer images than we expect |
|
break |
|
x, y = int(w * (i // ns)), int(h * (i % ns)) # block origin |
|
im = im.transpose(1, 2, 0) |
|
mosaic[y:y + h, x:x + w, :] = im |
|
|
|
# Resize (optional) |
|
scale = max_size / ns / max(h, w) |
|
if scale < 1: |
|
h = math.ceil(scale * h) |
|
w = math.ceil(scale * w) |
|
mosaic = cv2.resize(mosaic, tuple(int(x * ns) for x in (w, h))) |
|
|
|
# Annotate |
|
fs = int((h + w) * ns * 0.01) # font size |
|
annotator = Annotator(mosaic, line_width=round(fs / 10), font_size=fs, pil=True, example=names) |
|
for i in range(i + 1): |
|
x, y = int(w * (i // ns)), int(h * (i % ns)) # block origin |
|
annotator.rectangle([x, y, x + w, y + h], None, (255, 255, 255), width=2) # borders |
|
if paths: |
|
annotator.text((x + 5, y + 5 + h), text=Path(paths[i]).name[:40], txt_color=(220, 220, 220)) # filenames |
|
if len(cls) > 0: |
|
idx = batch_idx == i |
|
|
|
boxes = xywh2xyxy(bboxes[idx, :4]).T |
|
classes = cls[idx].astype('int') |
|
labels = bboxes.shape[1] == 4 # labels if no conf column |
|
conf = None if labels else bboxes[idx, 4] # check for confidence presence (label vs pred) |
|
|
|
if boxes.shape[1]: |
|
if boxes.max() <= 1.01: # if normalized with tolerance 0.01 |
|
boxes[[0, 2]] *= w # scale to pixels |
|
boxes[[1, 3]] *= h |
|
elif scale < 1: # absolute coords need scale if image scales |
|
boxes *= scale |
|
boxes[[0, 2]] += x |
|
boxes[[1, 3]] += y |
|
for j, box in enumerate(boxes.T.tolist()): |
|
c = classes[j] |
|
color = colors(c) |
|
c = names[c] if names else c |
|
if labels or conf[j] > 0.25: # 0.25 conf thresh |
|
label = f'{c}' if labels else f'{c} {conf[j]:.1f}' |
|
annotator.box_label(box, label, color=color) |
|
|
|
# Plot masks |
|
if len(masks): |
|
if masks.max() > 1.0: # mean that masks are overlap |
|
image_masks = masks[[i]] # (1, 640, 640) |
|
nl = idx.sum() |
|
index = np.arange(nl).reshape(nl, 1, 1) + 1 |
|
image_masks = np.repeat(image_masks, nl, axis=0) |
|
image_masks = np.where(image_masks == index, 1.0, 0.0) |
|
else: |
|
image_masks = masks[idx] |
|
|
|
im = np.asarray(annotator.im).copy() |
|
for j, box in enumerate(boxes.T.tolist()): |
|
if labels or conf[j] > 0.25: # 0.25 conf thresh |
|
color = colors(classes[j]) |
|
mh, mw = image_masks[j].shape |
|
if mh != h or mw != w: |
|
mask = image_masks[j].astype(np.uint8) |
|
mask = cv2.resize(mask, (w, h)) |
|
mask = mask.astype(bool) |
|
else: |
|
mask = image_masks[j].astype(bool) |
|
with contextlib.suppress(Exception): |
|
im[y:y + h, x:x + w, :][mask] = im[y:y + h, x:x + w, :][mask] * 0.4 + np.array(color) * 0.6 |
|
annotator.fromarray(im) |
|
annotator.im.save(fname) # save |
|
|
|
|
|
def plot_results(file='path/to/results.csv', dir='', segment=False): |
|
# Plot training results.csv. Usage: from utils.plots import *; plot_results('path/to/results.csv') |
|
save_dir = Path(file).parent if file else Path(dir) |
|
if segment: |
|
fig, ax = plt.subplots(2, 8, figsize=(18, 6), tight_layout=True) |
|
index = [1, 2, 3, 4, 5, 6, 9, 10, 13, 14, 15, 16, 7, 8, 11, 12] |
|
else: |
|
fig, ax = plt.subplots(2, 5, figsize=(12, 6), tight_layout=True) |
|
index = [1, 2, 3, 4, 5, 8, 9, 10, 6, 7] |
|
ax = ax.ravel() |
|
files = list(save_dir.glob('results*.csv')) |
|
assert len(files), f'No results.csv files found in {save_dir.resolve()}, nothing to plot.' |
|
for f in files: |
|
try: |
|
data = pd.read_csv(f) |
|
s = [x.strip() for x in data.columns] |
|
x = data.values[:, 0] |
|
for i, j in enumerate(index): |
|
y = data.values[:, j].astype('float') |
|
# y[y == 0] = np.nan # don't show zero values |
|
ax[i].plot(x, y, marker='.', label=f.stem, linewidth=2, markersize=8) |
|
ax[i].set_title(s[j], fontsize=12) |
|
# if j in [8, 9, 10]: # share train and val loss y axes |
|
# ax[i].get_shared_y_axes().join(ax[i], ax[i - 5]) |
|
except Exception as e: |
|
print(f'Warning: Plotting error for {f}: {e}') |
|
ax[1].legend() |
|
fig.savefig(save_dir / 'results.png', dpi=200) |
|
plt.close() |
|
|
|
|
|
def output_to_target(output, max_det=300): |
|
# Convert model output to target format [batch_id, class_id, x, y, w, h, conf] for plotting |
|
targets = [] |
|
for i, o in enumerate(output): |
|
box, conf, cls = o[:max_det, :6].cpu().split((4, 1, 1), 1) |
|
j = torch.full((conf.shape[0], 1), i) |
|
targets.append(torch.cat((j, cls, xyxy2xywh(box), conf), 1)) |
|
targets = torch.cat(targets, 0).numpy() |
|
return targets[:, 0], targets[:, 1], targets[:, 2:]
|
|
|