jasder
/
yolov5
1
0
Fork 0
Code Issues Pull Requests 1 Releases Wiki Activity

update mosaic border

Browse Source
pull/1/head
Glenn Jocher 5 years ago
parent 77fb8ee082
commit 93a6765806
1 changed files with 17 additions and 13 deletions
Show Stats Download Patch File Download Diff File

30
utils/datasets.py
Unescape View File

@ -62,7 +62,7 @@ def create_dataloader(path, imgsz, batch_size, stride, opt, hyp=None, augment=Fa
class LoadImages: # for inference class LoadImages: # for inference
def __init__(self, path, img_size=416): def __init__(self, path, img_size=640):
path = str(Path(path)) # os-agnostic path = str(Path(path)) # os-agnostic
files = [] files = []
if os.path.isdir(path): if os.path.isdir(path):
@ -139,7 +139,7 @@ class LoadImages: # for inference
class LoadWebcam: # for inference class LoadWebcam: # for inference
def __init__(self, pipe=0, img_size=416): def __init__(self, pipe=0, img_size=640):
self.img_size = img_size self.img_size = img_size
if pipe == '0': if pipe == '0':
@ -204,7 +204,7 @@ class LoadWebcam: # for inference
class LoadStreams: # multiple IP or RTSP cameras class LoadStreams: # multiple IP or RTSP cameras
def __init__(self, sources='streams.txt', img_size=416): def __init__(self, sources='streams.txt', img_size=640):
self.mode = 'images' self.mode = 'images'
self.img_size = img_size self.img_size = img_size
@ -277,7 +277,7 @@ class LoadStreams: # multiple IP or RTSP cameras
class LoadImagesAndLabels(Dataset): # for training/testing class LoadImagesAndLabels(Dataset): # for training/testing
def __init__(self, path, img_size=416, batch_size=16, augment=False, hyp=None, rect=False, image_weights=False, def __init__(self, path, img_size=640, batch_size=16, augment=False, hyp=None, rect=False, image_weights=False,
cache_images=False, single_cls=False, stride=32, pad=0.0): cache_images=False, single_cls=False, stride=32, pad=0.0):
try: try:
path = str(Path(path)) # os-agnostic path = str(Path(path)) # os-agnostic
@ -307,6 +307,9 @@ class LoadImagesAndLabels(Dataset): # for training/testing
self.image_weights = image_weights self.image_weights = image_weights
self.rect = False if image_weights else rect self.rect = False if image_weights else rect
self.mosaic = self.augment and not self.rect # load 4 images at a time into a mosaic (only during training) self.mosaic = self.augment and not self.rect # load 4 images at a time into a mosaic (only during training)
self.mosaic_border = None
self.stride = stride
# Define labels # Define labels
self.label_files = [x.replace('images', 'labels').replace(os.path.splitext(x)[-1], '.txt') self.label_files = [x.replace('images', 'labels').replace(os.path.splitext(x)[-1], '.txt')
@ -585,7 +588,8 @@ def load_mosaic(self, index):
labels4 = [] labels4 = []
s = self.img_size s = self.img_size
xc, yc = [int(random.uniform(s * 0.5, s * 1.5)) for _ in range(2)] # mosaic center x, y border = [-s // 2, -s // 2] # self.mosaic_border
yc, xc = [int(random.uniform(-x, 2 * s + x)) for x in border] # mosaic center x, y
indices = [index] + [random.randint(0, len(self.labels) - 1) for _ in range(3)] # 3 additional image indices indices = [index] + [random.randint(0, len(self.labels) - 1) for _ in range(3)] # 3 additional image indices
for i, index in enumerate(indices): for i, index in enumerate(indices):
# Load image # Load image
@ -633,12 +637,12 @@ def load_mosaic(self, index):
translate=self.hyp['translate'], translate=self.hyp['translate'],
scale=self.hyp['scale'], scale=self.hyp['scale'],
shear=self.hyp['shear'], shear=self.hyp['shear'],
border=-s // 2) # border to remove border=border) # border to remove
return img4, labels4 return img4, labels4
def letterbox(img, new_shape=(416, 416), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True): def letterbox(img, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True):
# Resize image to a 32-pixel-multiple rectangle https://github.com/ultralytics/yolov3/issues/232 # Resize image to a 32-pixel-multiple rectangle https://github.com/ultralytics/yolov3/issues/232
shape = img.shape[:2] # current shape [height, width] shape = img.shape[:2] # current shape [height, width]
if isinstance(new_shape, int): if isinstance(new_shape, int):
@ -671,13 +675,13 @@ def letterbox(img, new_shape=(416, 416), color=(114, 114, 114), auto=True, scale
return img, ratio, (dw, dh) return img, ratio, (dw, dh)
def random_affine(img, targets=(), degrees=10, translate=.1, scale=.1, shear=10, border=0): def random_affine(img, targets=(), degrees=10, translate=.1, scale=.1, shear=10, border=(0, 0)):
# torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-10, 10)) # 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 # https://medium.com/uruvideo/dataset-augmentation-with-random-homographies-a8f4b44830d4
# targets = [cls, xyxy] # targets = [cls, xyxy]
height = img.shape[0] + border * 2 height = img.shape[0] + border[0] * 2 # shape(h,w,c)
width = img.shape[1] + border * 2 width = img.shape[1] + border[1] * 2
# Rotation and Scale # Rotation and Scale
R = np.eye(3) R = np.eye(3)
@ -689,8 +693,8 @@ def random_affine(img, targets=(), degrees=10, translate=.1, scale=.1, shear=10,
# Translation # Translation
T = np.eye(3) T = np.eye(3)
T[0, 2] = random.uniform(-translate, translate) * img.shape[0] + border # x translation (pixels) T[0, 2] = random.uniform(-translate, translate) * img.shape[1] + border[1] # x translation (pixels)
T[1, 2] = random.uniform(-translate, translate) * img.shape[1] + border # y translation (pixels) T[1, 2] = random.uniform(-translate, translate) * img.shape[0] + border[0] # y translation (pixels)
# Shear # Shear
S = np.eye(3) S = np.eye(3)
@ -699,7 +703,7 @@ def random_affine(img, targets=(), degrees=10, translate=.1, scale=.1, shear=10,
# Combined rotation matrix # Combined rotation matrix
M = S @ T @ R # ORDER IS IMPORTANT HERE!! M = S @ T @ R # ORDER IS IMPORTANT HERE!!
if (border != 0) or (M != np.eye(3)).any(): # image changed if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any(): # image changed
img = cv2.warpAffine(img, M[:2], dsize=(width, height), flags=cv2.INTER_LINEAR, borderValue=(114, 114, 114)) img = cv2.warpAffine(img, M[:2], dsize=(width, height), flags=cv2.INTER_LINEAR, borderValue=(114, 114, 114))
# Transform label coordinates # Transform label coordinates

Write Preview
Loading…
Cancel
Save