xdobro23/YOLOv8-16bit
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Fix dataloader (#32)

Browse Source 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Laughing
2022-11-04 03:00:40 -05:00
committed by GitHub
parent 92c60758dd
commit 2e9b18ce4e
8 changed files with 404 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
ultralytics/tests/data/dataloader/hyp_test.yaml Normal file
View File

@ -0,0 +1,29 @@
lr0: 0.001 # initial learning rate (SGD=1E-2, Adam=1E-3)
lrf: 0.01 # final OneCycleLR learning rate (lr0 * lrf)
momentum: 0.937 # SGD momentum/Adam beta1
weight_decay: 0.0005 # optimizer weight decay 5e-4
warmup_epochs: 3.0 # warmup epochs (fractions ok)
warmup_momentum: 0.8 # warmup initial momentum
warmup_bias_lr: 0.1 # warmup initial bias lr
box: 0.05 # box loss gain
cls: 0.5 # cls loss gain
cls_pw: 1.0 # cls BCELoss positive_weight
obj: 1.0 # obj loss gain (scale with pixels)
obj_pw: 1.0 # obj BCELoss positive_weight
iou_t: 0.20 # IoU training threshold
anchor_t: 4.0 # anchor-multiple threshold
# anchors: 3 # anchors per output layer (0 to ignore)
fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5)
hsv_h: 0.015 # image HSV-Hue augmentation (fraction)
hsv_s: 0.7 # image HSV-Saturation augmentation (fraction)
hsv_v: 0.4 # image HSV-Value augmentation (fraction)
degrees: 0.0 # image rotation (+/- deg)
translate: 0.1 # image translation (+/- fraction)
scale: 0.5 # image scale (+/- gain)
shear: 0.0 # image shear (+/- deg)
perspective: 0.0 # image perspective (+/- fraction), range 0-0.001
flipud: 0.0 # image flip up-down (probability)
fliplr: 0.5 # image flip left-right (probability)
mosaic: 1.0 # image mosaic (probability)
mixup: 0.0 # image mixup (probability)
copy_paste: 0.0 # segment copy-paste (probability)

97
ultralytics/tests/data/dataloader/yolodetection.py Normal file
View File

@ -0,0 +1,97 @@
import cv2
import numpy as np
from omegaconf import OmegaConf
from ultralytics.yolo.data import build_dataloader
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'
def plot_one_box(x, img, color=None, label=None, line_thickness=None):
import random
# Plots one bounding box on image img
tl = line_thickness or round(0.002 * (img.shape[0] + img.shape[1]) / 2) + 1 # line/font thickness
color = color or [random.randint(0, 255) for _ in range(3)]
c1, c2 = (int(x[0]), int(x[1])), (int(x[2]), int(x[3]))
cv2.rectangle(img, c1, c2, color, thickness=tl, lineType=cv2.LINE_AA)
if label:
tf = max(tl - 1, 1) # font thickness
t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0]
c2 = c1[0] + t_size[0], c1[1] - t_size[1] - 3
cv2.rectangle(img, c1, c2, color, -1, cv2.LINE_AA) # filled
cv2.putText(
img,
label,
(c1[0], c1[1] - 2),
0,
tl / 3,
[225, 255, 255],
thickness=tf,
lineType=cv2.LINE_AA,
)
with open("ultralytics/tests/data/dataloader/hyp_test.yaml") as f:
hyp = OmegaConf.load(f)
dataloader, dataset = build_dataloader(
img_path="/d/dataset/COCO/coco128-seg/images",
img_size=640,
label_path=None,
cache=False,
hyp=hyp,
augment=False,
prefix="",
rect=False,
batch_size=4,
stride=32,
pad=0.5,
use_segments=True,
use_keypoints=False,
)
for d in dataloader:
idx = 1 # show which image inside one batch
img = d["img"][idx].numpy()
img = np.ascontiguousarray(img.transpose(1, 2, 0))
ih, iw = img.shape[:2]
# print(img.shape)
bidx = d["batch_idx"]
cls = d["cls"][bidx == idx].numpy()
bboxes = d["bboxes"][bidx == idx].numpy()
print(bboxes.shape)
bboxes[:, [0, 2]] *= iw
bboxes[:, [1, 3]] *= ih
nl = len(cls)
for i, b in enumerate(bboxes):
x, y, w, h = b
x1 = x - w / 2
x2 = x + w / 2
y1 = y - h / 2
y2 = y + h / 2
c = int(cls[i][0])
plot_one_box([int(x1), int(y1), int(x2), int(y2)], img, label=f"{c}", color=colors(c))
cv2.imshow("p", img)
if cv2.waitKey(0) == ord("q"):
break

114
ultralytics/tests/data/dataloader/yolopose.py Normal file
View File

@ -0,0 +1,114 @@
import cv2
import numpy as np
import torch
from omegaconf import OmegaConf
from ultralytics.yolo.data import build_dataloader
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'
def plot_one_box(x, img, keypoints=None, color=None, label=None, line_thickness=None):
import random
# Plots one bounding box on image img
tl = line_thickness or round(0.002 * (img.shape[0] + img.shape[1]) / 2) + 1 # line/font thickness
color = color or [random.randint(0, 255) for _ in range(3)]
c1, c2 = (int(x[0]), int(x[1])), (int(x[2]), int(x[3]))
cv2.rectangle(img, c1, c2, color, thickness=tl, lineType=cv2.LINE_AA)
if label:
tf = max(tl - 1, 1) # font thickness
t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0]
c2 = c1[0] + t_size[0], c1[1] - t_size[1] - 3
cv2.rectangle(img, c1, c2, color, -1, cv2.LINE_AA) # filled
cv2.putText(
img,
label,
(c1[0], c1[1] - 2),
0,
tl / 3,
[225, 255, 255],
thickness=tf,
lineType=cv2.LINE_AA,
)
if keypoints is not None:
plot_keypoint(img, keypoints, color, tl)
def plot_keypoint(img, keypoints, color, tl):
num_l = len(keypoints)
# clors = [(255, 0, 0),(0, 255, 0),(0, 0, 255),(255, 255, 0),(0, 255, 255)]
# clors = [[random.randint(0, 255) for _ in range(3)] for _ in range(num_l)]
for i in range(num_l):
point_x = int(keypoints[i][0])
point_y = int(keypoints[i][1])
cv2.circle(img, (point_x, point_y), tl + 3, color, -1)
with open("ultralytics/tests/data/dataloader/hyp_test.yaml") as f:
hyp = OmegaConf.load(f)
dataloader, dataset = build_dataloader(
img_path="/d/dataset/COCO/images/val2017",
img_size=640,
label_path=None,
cache=False,
hyp=hyp,
augment=False,
prefix="",
rect=False,
batch_size=4,
stride=32,
pad=0.5,
use_segments=False,
use_keypoints=True,
)
for d in dataloader:
idx = 1 # show which image inside one batch
img = d["img"][idx].numpy()
img = np.ascontiguousarray(img.transpose(1, 2, 0))
ih, iw = img.shape[:2]
# print(img.shape)
bidx = d["batch_idx"]
cls = d["cls"][bidx == idx].numpy()
bboxes = d["bboxes"][bidx == idx].numpy()
bboxes[:, [0, 2]] *= iw
bboxes[:, [1, 3]] *= ih
keypoints = d["keypoints"][bidx == idx]
keypoints[..., 0] *= iw
keypoints[..., 1] *= ih
# print(keypoints, keypoints.shape)
# print(d["im_file"])
for i, b in enumerate(bboxes):
x, y, w, h = b
x1 = x - w / 2
x2 = x + w / 2
y1 = y - h / 2
y2 = y + h / 2
c = int(cls[i][0])
# print(x1, y1, x2, y2)
plot_one_box([int(x1), int(y1), int(x2), int(y2)], img, keypoints=keypoints[i], label=f"{c}", color=colors(c))
cv2.imshow("p", img)
if cv2.waitKey(0) == ord("q"):
break

112
ultralytics/tests/data/dataloader/yolosegment.py Normal file
View File

@ -0,0 +1,112 @@
import cv2
import numpy as np
import torch
from omegaconf import OmegaConf
from ultralytics.yolo.data import build_dataloader
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'
def plot_one_box(x, img, color=None, label=None, line_thickness=None):
import random
# Plots one bounding box on image img
tl = line_thickness or round(0.002 * (img.shape[0] + img.shape[1]) / 2) + 1 # line/font thickness
color = color or [random.randint(0, 255) for _ in range(3)]
c1, c2 = (int(x[0]), int(x[1])), (int(x[2]), int(x[3]))
cv2.rectangle(img, c1, c2, color, thickness=tl, lineType=cv2.LINE_AA)
if label:
tf = max(tl - 1, 1) # font thickness
t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0]
c2 = c1[0] + t_size[0], c1[1] - t_size[1] - 3
cv2.rectangle(img, c1, c2, color, -1, cv2.LINE_AA) # filled
cv2.putText(
img,
label,
(c1[0], c1[1] - 2),
0,
tl / 3,
[225, 255, 255],
thickness=tf,
lineType=cv2.LINE_AA,
)
with open("ultralytics/tests/data/dataloader/hyp_test.yaml") as f:
hyp = OmegaConf.load(f)
dataloader, dataset = build_dataloader(
img_path="/d/dataset/COCO/coco128-seg/images",
img_size=640,
label_path=None,
cache=False,
hyp=hyp,
augment=False,
prefix="",
rect=False,
batch_size=4,
stride=32,
pad=0.5,
use_segments=True,
use_keypoints=False,
)
for d in dataloader:
idx = 1 # show which image inside one batch
img = d["img"][idx].numpy()
img = np.ascontiguousarray(img.transpose(1, 2, 0))
ih, iw = img.shape[:2]
# print(img.shape)
bidx = d["batch_idx"]
cls = d["cls"][bidx == idx].numpy()
bboxes = d["bboxes"][bidx == idx].numpy()
masks = d["masks"][idx]
print(bboxes.shape)
bboxes[:, [0, 2]] *= iw
bboxes[:, [1, 3]] *= ih
nl = len(cls)
index = torch.arange(nl).view(nl, 1, 1) + 1
masks = masks.repeat(nl, 1, 1)
# print(masks.shape, index.shape)
masks = torch.where(masks == index, 1, 0)
masks = masks.numpy().astype(np.uint8)
print(masks.shape)
# keypoints = d["keypoints"]
for i, b in enumerate(bboxes):
x, y, w, h = b
x1 = x - w / 2
x2 = x + w / 2
y1 = y - h / 2
y2 = y + h / 2
c = int(cls[i][0])
# print(x1, y1, x2, y2)
plot_one_box([int(x1), int(y1), int(x2), int(y2)], img, label=f"{c}", color=colors(c))
mask = masks[i]
mask = cv2.resize(mask, (iw, ih))
mask = mask.astype(bool)
img[mask] = img[mask] * 0.5 + np.array(colors(c)) * 0.5
cv2.imshow("p", img)
if cv2.waitKey(0) == ord("q"):
break