285 lines
10 KiB
Python
Executable File
285 lines
10 KiB
Python
Executable File
import glob
|
|
import math
|
|
import os
|
|
import random
|
|
|
|
import cv2
|
|
import numpy as np
|
|
import torch
|
|
from torch.utils.data import Dataset
|
|
|
|
from utils.utils import xyxy2xywh
|
|
|
|
|
|
class LoadImages: # for inference
|
|
def __init__(self, path, img_size=416):
|
|
if os.path.isdir(path):
|
|
image_format = ['.jpg', '.jpeg', '.png', '.tif']
|
|
self.files = sorted(glob.glob('%s/*.*' % path))
|
|
self.files = list(filter(lambda x: os.path.splitext(x)[1].lower() in image_format, self.files))
|
|
elif os.path.isfile(path):
|
|
self.files = [path]
|
|
|
|
self.nF = len(self.files) # number of image files
|
|
self.height = img_size
|
|
|
|
assert self.nF > 0, 'No images found in ' + path
|
|
|
|
def __iter__(self):
|
|
self.count = -1
|
|
return self
|
|
|
|
def __next__(self):
|
|
self.count += 1
|
|
if self.count == self.nF:
|
|
raise StopIteration
|
|
img_path = self.files[self.count]
|
|
|
|
# Read image
|
|
img0 = cv2.imread(img_path) # BGR
|
|
assert img0 is not None, 'File Not Found ' + img_path
|
|
|
|
# Padded resize
|
|
img, _, _, _ = letterbox(img0, height=self.height)
|
|
|
|
# Normalize RGB
|
|
img = img[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB
|
|
img = np.ascontiguousarray(img, dtype=np.float32) # uint8 to float32
|
|
img /= 255.0 # 0 - 255 to 0.0 - 1.0
|
|
|
|
# cv2.imwrite(img_path + '.letterbox.jpg', 255 * img.transpose((1, 2, 0))[:, :, ::-1]) # save letterbox image
|
|
return img_path, img, img0
|
|
|
|
def __len__(self):
|
|
return self.nF # number of files
|
|
|
|
|
|
class LoadWebcam: # for inference
|
|
def __init__(self, img_size=416):
|
|
self.cam = cv2.VideoCapture(0)
|
|
self.height = img_size
|
|
|
|
def __iter__(self):
|
|
self.count = -1
|
|
return self
|
|
|
|
def __next__(self):
|
|
self.count += 1
|
|
if cv2.waitKey(1) == 27: # esc to quit
|
|
cv2.destroyAllWindows()
|
|
raise StopIteration
|
|
|
|
# Read image
|
|
ret_val, img0 = self.cam.read()
|
|
assert ret_val, 'Webcam Error'
|
|
img_path = 'webcam_%g.jpg' % self.count
|
|
img0 = cv2.flip(img0, 1) # flip left-right
|
|
|
|
# Padded resize
|
|
img, _, _, _ = letterbox(img0, height=self.height)
|
|
|
|
# Normalize RGB
|
|
img = img[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB
|
|
img = np.ascontiguousarray(img, dtype=np.float32) # uint8 to float32
|
|
img /= 255.0 # 0 - 255 to 0.0 - 1.0
|
|
|
|
return img_path, img, img0
|
|
|
|
def __len__(self):
|
|
return 0
|
|
|
|
|
|
class LoadImagesAndLabels(Dataset): # for training/testing
|
|
def __init__(self, path, img_size=416, augment=False):
|
|
with open(path, 'r') as file:
|
|
self.img_files = file.read().splitlines()
|
|
self.img_files = list(filter(lambda x: len(x) > 0, self.img_files))
|
|
assert len(self.img_files) > 0, 'No images found in %s' % path
|
|
self.img_size = img_size
|
|
self.augment = augment
|
|
self.label_files = [x.replace('images', 'labels').replace('.png', '.txt').replace('.jpg', '.txt')
|
|
for x in self.img_files]
|
|
|
|
def __len__(self):
|
|
return len(self.img_files)
|
|
|
|
def __getitem__(self, index):
|
|
img_path = self.img_files[index]
|
|
label_path = self.label_files[index]
|
|
|
|
img = cv2.imread(img_path) # BGR
|
|
assert img is not None, 'File Not Found ' + img_path
|
|
|
|
augment_hsv = True
|
|
if self.augment and augment_hsv:
|
|
# SV augmentation by 50%
|
|
fraction = 0.50
|
|
img_hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
|
|
S = img_hsv[:, :, 1].astype(np.float32)
|
|
V = img_hsv[:, :, 2].astype(np.float32)
|
|
|
|
a = (random.random() * 2 - 1) * fraction + 1
|
|
S *= a
|
|
if a > 1:
|
|
np.clip(S, a_min=0, a_max=255, out=S)
|
|
|
|
a = (random.random() * 2 - 1) * fraction + 1
|
|
V *= a
|
|
if a > 1:
|
|
np.clip(V, a_min=0, a_max=255, out=V)
|
|
|
|
img_hsv[:, :, 1] = S.astype(np.uint8)
|
|
img_hsv[:, :, 2] = V.astype(np.uint8)
|
|
cv2.cvtColor(img_hsv, cv2.COLOR_HSV2BGR, dst=img)
|
|
|
|
h, w, _ = img.shape
|
|
img, ratio, padw, padh = letterbox(img, height=self.img_size)
|
|
|
|
# Load labels
|
|
if os.path.isfile(label_path):
|
|
with open(label_path, 'r') as file:
|
|
lines = file.read().splitlines()
|
|
|
|
x = np.array([x.split() for x in lines], dtype=np.float32)
|
|
if x.size is 0:
|
|
# Empty labels file
|
|
labels = np.array([])
|
|
else:
|
|
# Normalized xywh to pixel xyxy format
|
|
labels = x.copy()
|
|
labels[:, 1] = ratio * w * (x[:, 1] - x[:, 3] / 2) + padw
|
|
labels[:, 2] = ratio * h * (x[:, 2] - x[:, 4] / 2) + padh
|
|
labels[:, 3] = ratio * w * (x[:, 1] + x[:, 3] / 2) + padw
|
|
labels[:, 4] = ratio * h * (x[:, 2] + x[:, 4] / 2) + padh
|
|
else:
|
|
labels = np.array([])
|
|
|
|
# Augment image and labels
|
|
if self.augment:
|
|
img, labels, M = random_affine(img, labels, degrees=(-5, 5), translate=(0.10, 0.10), scale=(0.90, 1.10))
|
|
|
|
nL = len(labels)
|
|
if nL > 0:
|
|
# convert xyxy to xywh
|
|
labels[:, 1:5] = xyxy2xywh(labels[:, 1:5]) / self.img_size
|
|
|
|
if self.augment:
|
|
# random left-right flip
|
|
lr_flip = True
|
|
if lr_flip & (random.random() > 0.5):
|
|
img = np.fliplr(img)
|
|
if nL > 0:
|
|
labels[:, 1] = 1 - labels[:, 1]
|
|
|
|
# random up-down flip
|
|
ud_flip = False
|
|
if ud_flip & (random.random() > 0.5):
|
|
img = np.flipud(img)
|
|
if nL > 0:
|
|
labels[:, 2] = 1 - labels[:, 2]
|
|
|
|
labels_out = np.zeros((100, 6), dtype=np.float32)
|
|
if nL > 0:
|
|
labels_out[:nL, 1:] = labels # max 100 labels per image
|
|
|
|
# Normalize
|
|
img = img[:, :, ::-1].transpose(2, 0, 1) # list to np.array and BGR to RGB
|
|
img = np.ascontiguousarray(img, dtype=np.float32) # uint8 to float32
|
|
img /= 255.0 # 0 - 255 to 0.0 - 1.0
|
|
|
|
return torch.from_numpy(img), torch.from_numpy(labels_out), img_path, (h, w)
|
|
|
|
|
|
def letterbox(img, height=416, color=(127.5, 127.5, 127.5)): # resize a rectangular image to a padded square
|
|
shape = img.shape[:2] # shape = [height, width]
|
|
ratio = float(height) / max(shape) # ratio = old / new
|
|
new_shape = (round(shape[1] * ratio), round(shape[0] * ratio))
|
|
dw = (height - new_shape[0]) / 2 # width padding
|
|
dh = (height - new_shape[1]) / 2 # height padding
|
|
top, bottom = round(dh - 0.1), round(dh + 0.1)
|
|
left, right = round(dw - 0.1), round(dw + 0.1)
|
|
img = cv2.resize(img, new_shape, interpolation=cv2.INTER_AREA) # resized, no border
|
|
img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # padded square
|
|
return img, ratio, dw, dh
|
|
|
|
|
|
def random_affine(img, targets=None, degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-2, 2),
|
|
borderValue=(127.5, 127.5, 127.5)):
|
|
# torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-10, 10))
|
|
# https://medium.com/uruvideo/dataset-augmentation-with-random-homographies-a8f4b44830d4
|
|
|
|
border = 0 # width of added border (optional)
|
|
height = max(img.shape[0], img.shape[1]) + border * 2
|
|
|
|
# Rotation and Scale
|
|
R = np.eye(3)
|
|
a = random.random() * (degrees[1] - degrees[0]) + degrees[0]
|
|
# a += random.choice([-180, -90, 0, 90]) # 90deg rotations added to small rotations
|
|
s = random.random() * (scale[1] - scale[0]) + scale[0]
|
|
R[:2] = cv2.getRotationMatrix2D(angle=a, center=(img.shape[1] / 2, img.shape[0] / 2), scale=s)
|
|
|
|
# Translation
|
|
T = np.eye(3)
|
|
T[0, 2] = (random.random() * 2 - 1) * translate[0] * img.shape[0] + border # x translation (pixels)
|
|
T[1, 2] = (random.random() * 2 - 1) * translate[1] * img.shape[1] + border # y translation (pixels)
|
|
|
|
# Shear
|
|
S = np.eye(3)
|
|
S[0, 1] = math.tan((random.random() * (shear[1] - shear[0]) + shear[0]) * math.pi / 180) # x shear (deg)
|
|
S[1, 0] = math.tan((random.random() * (shear[1] - shear[0]) + shear[0]) * math.pi / 180) # y shear (deg)
|
|
|
|
M = S @ T @ R # Combined rotation matrix. ORDER IS IMPORTANT HERE!!
|
|
imw = cv2.warpPerspective(img, M, dsize=(height, height), flags=cv2.INTER_LINEAR,
|
|
borderValue=borderValue) # BGR order borderValue
|
|
|
|
# Return warped points also
|
|
if targets is not None:
|
|
if len(targets) > 0:
|
|
n = targets.shape[0]
|
|
points = targets[:, 1:5].copy()
|
|
area0 = (points[:, 2] - points[:, 0]) * (points[:, 3] - points[:, 1])
|
|
|
|
# warp points
|
|
xy = np.ones((n * 4, 3))
|
|
xy[:, :2] = points[:, [0, 1, 2, 3, 0, 3, 2, 1]].reshape(n * 4, 2) # x1y1, x2y2, x1y2, x2y1
|
|
xy = (xy @ M.T)[:, :2].reshape(n, 8)
|
|
|
|
# create new boxes
|
|
x = xy[:, [0, 2, 4, 6]]
|
|
y = xy[:, [1, 3, 5, 7]]
|
|
xy = np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1))).reshape(4, n).T
|
|
|
|
# apply angle-based reduction
|
|
radians = a * math.pi / 180
|
|
reduction = max(abs(math.sin(radians)), abs(math.cos(radians))) ** 0.5
|
|
x = (xy[:, 2] + xy[:, 0]) / 2
|
|
y = (xy[:, 3] + xy[:, 1]) / 2
|
|
w = (xy[:, 2] - xy[:, 0]) * reduction
|
|
h = (xy[:, 3] - xy[:, 1]) * reduction
|
|
xy = np.concatenate((x - w / 2, y - h / 2, x + w / 2, y + h / 2)).reshape(4, n).T
|
|
|
|
# reject warped points outside of image
|
|
np.clip(xy, 0, height, out=xy)
|
|
w = xy[:, 2] - xy[:, 0]
|
|
h = xy[:, 3] - xy[:, 1]
|
|
area = w * h
|
|
ar = np.maximum(w / (h + 1e-16), h / (w + 1e-16))
|
|
i = (w > 4) & (h > 4) & (area / (area0 + 1e-16) > 0.1) & (ar < 10)
|
|
|
|
targets = targets[i]
|
|
targets[:, 1:5] = xy[i]
|
|
|
|
return imw, targets, M
|
|
else:
|
|
return imw
|
|
|
|
|
|
def convert_tif2bmp(p='../xview/val_images_bmp'):
|
|
import glob
|
|
import cv2
|
|
files = sorted(glob.glob('%s/*.tif' % p))
|
|
for i, f in enumerate(files):
|
|
print('%g/%g' % (i + 1, len(files)))
|
|
cv2.imwrite(f.replace('.tif', '.bmp'), cv2.imread(f))
|
|
os.system('rm -rf ' + f)
|