Bienqq
/
car-detection-bayes
2
1
Fork 0
Code Issues Pull Requests Releases Wiki Activity

updates

This commit is contained in:
Glenn Jocher 2019-06-21 21:27:50 +02:00
parent 5f6c2b3d12
commit 4f7fee45ff
2 changed files with 13 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
train.py
View File

@ -315,7 +315,7 @@ if __name__ == '__main__':
parser.add_argument('--batch-size', type=int, default=8, help='batch size') parser.add_argument('--batch-size', type=int, default=8, help='batch size')
parser.add_argument('--accumulate', type=int, default=8, help='number of batches to accumulate before optimizing') parser.add_argument('--accumulate', type=int, default=8, help='number of batches to accumulate before optimizing')
parser.add_argument('--cfg', type=str, default='cfg/yolov3-spp.cfg', help='cfg file path') parser.add_argument('--cfg', type=str, default='cfg/yolov3-spp.cfg', help='cfg file path')
parser.add_argument('--data-cfg', type=str, default='data/coco.data', help='coco.data file path') parser.add_argument('--data-cfg', type=str, default='data/coco_64img.data', help='coco.data file path')
parser.add_argument('--single-scale', action='store_true', help='train at fixed size (no multi-scale)') parser.add_argument('--single-scale', action='store_true', help='train at fixed size (no multi-scale)')
parser.add_argument('--img-size', type=int, default=416, help='inference size (pixels)') parser.add_argument('--img-size', type=int, default=416, help='inference size (pixels)')
parser.add_argument('--resume', action='store_true', help='resume training flag') parser.add_argument('--resume', action='store_true', help='resume training flag')

19
utils/datasets.py
View File

@ -266,10 +266,10 @@ class LoadImagesAndLabels(Dataset): # for training/testing
h, w, _ = img.shape h, w, _ = img.shape
if self.rect: if self.rect:
shape = self.batch_shapes[self.batch[index]] shape = self.batch_shapes[self.batch[index]]
img, ratio, padw, padh = letterbox(img, new_shape=shape, mode='rect') img, ratiow, ratioh, padw, padh = letterbox(img, new_shape=shape, mode='rect')
else: else:
shape = self.img_size shape = self.img_size
img, ratio, padw, padh = letterbox(img, new_shape=shape, mode='square') img, ratiow, ratioh, padw, padh = letterbox(img, new_shape=shape, mode='scaleFill')
# Load labels # Load labels
labels = [] labels = []
@ -280,10 +280,10 @@ class LoadImagesAndLabels(Dataset): # for training/testing
if x.size > 0: if x.size > 0:
# Normalized xywh to pixel xyxy format # Normalized xywh to pixel xyxy format
labels = x.copy() labels = x.copy()
labels[:, 1] = ratio * w * (x[:, 1] - x[:, 3] / 2) + padw labels[:, 1] = ratiow * w * (x[:, 1] - x[:, 3] / 2) + padw
labels[:, 2] = ratio * h * (x[:, 2] - x[:, 4] / 2) + padh labels[:, 2] = ratioh * h * (x[:, 2] - x[:, 4] / 2) + padh
labels[:, 3] = ratio * w * (x[:, 1] + x[:, 3] / 2) + padw labels[:, 3] = ratiow * w * (x[:, 1] + x[:, 3] / 2) + padw
labels[:, 4] = ratio * h * (x[:, 2] + x[:, 4] / 2) + padh labels[:, 4] = ratioh * h * (x[:, 2] + x[:, 4] / 2) + padh
# Augment image and labels # Augment image and labels
if self.augment: if self.augment:
@ -340,6 +340,7 @@ def letterbox(img, new_shape=416, color=(127.5, 127.5, 127.5), mode='auto'):
ratio = float(new_shape) / max(shape) ratio = float(new_shape) / max(shape)
else: else:
ratio = max(new_shape) / max(shape) # ratio = new / old ratio = max(new_shape) / max(shape) # ratio = new / old
ratiow, ratioh = ratio, ratio
new_unpad = (int(round(shape[1] * ratio)), int(round(shape[0] * ratio))) new_unpad = (int(round(shape[1] * ratio)), int(round(shape[0] * ratio)))
# Compute padding https://github.com/ultralytics/yolov3/issues/232 # Compute padding https://github.com/ultralytics/yolov3/issues/232
@ -352,12 +353,16 @@ def letterbox(img, new_shape=416, color=(127.5, 127.5, 127.5), mode='auto'):
elif mode is 'rect': # square elif mode is 'rect': # square
dw = (new_shape[1] - new_unpad[0]) / 2 # width padding dw = (new_shape[1] - new_unpad[0]) / 2 # width padding
dh = (new_shape[0] - new_unpad[1]) / 2 # height padding dh = (new_shape[0] - new_unpad[1]) / 2 # height padding
elif mode is 'scaleFill':
dw, dh = 0.0, 0.0
new_unpad = (new_shape, new_shape)
ratiow, ratioh = new_shape/shape[1], new_shape/shape[0]
top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1)) top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
left, right = int(round(dw - 0.1)), int(round(dw + 0.1)) left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR) # resized, no border img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR) # resized, no border
img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # padded square img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # padded square
return img, ratio, dw, dh return img, ratiow, ratioh, dw, dh
def random_affine(img, targets=(), degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-2, 2), def random_affine(img, targets=(), degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-2, 2),