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

update multi-scale training

This commit is contained in:
Glenn Jocher 2018-11-05 23:17:53 +01:00
parent 587097affb
commit 77469a5268
2 changed files with 10 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
train.py
View File

@ -7,12 +7,11 @@ from utils.utils import *
parser = argparse.ArgumentParser() parser = argparse.ArgumentParser()
parser.add_argument('-epochs', type=int, default=100, help='number of epochs') parser.add_argument('-epochs', type=int, default=100, help='number of epochs')
parser.add_argument('-batch_size', type=int, default=16, help='size of each image batch') parser.add_argument('-batch_size', type=int, default=2, help='size of each image batch')
parser.add_argument('-data_config_path', type=str, default='cfg/coco.data', help='data config file path') parser.add_argument('-data_config_path', type=str, default='cfg/coco.data', help='data config file path')
parser.add_argument('-cfg', type=str, default='cfg/yolov3.cfg', help='cfg file path') parser.add_argument('-cfg', type=str, default='cfg/yolov3.cfg', help='cfg file path')
parser.add_argument('-img_size', type=int, default=32 * 13, help='size of each image dimension') parser.add_argument('-img_size', type=int, default=32 * 19, help='size of each image dimension')
parser.add_argument('-resume', default=False, help='resume training flag') parser.add_argument('-resume', default=False, help='resume training flag')
parser.add_argument('-multi_scale', default=True, help='train at random img_size 320-608') # ensure memory for 608 size
opt = parser.parse_args() opt = parser.parse_args()
print(opt) print(opt)
@ -40,7 +39,7 @@ def main(opt):
train_path = '../coco/trainvalno5k.part' train_path = '../coco/trainvalno5k.part'
# Initialize model # Initialize model
model = Darknet(opt.cfg, opt.img_size if opt.multi_scale is False else 608) model = Darknet(opt.cfg, opt.img_size)
# Get dataloader # Get dataloader
dataloader = load_images_and_labels(train_path, batch_size=opt.batch_size, img_size=opt.img_size, augment=True) dataloader = load_images_and_labels(train_path, batch_size=opt.batch_size, img_size=opt.img_size, augment=True)
@ -100,12 +99,6 @@ def main(opt):
for epoch in range(opt.epochs): for epoch in range(opt.epochs):
epoch += start_epoch epoch += start_epoch
# Multi-Scale YOLO Training
if opt.multi_scale:
img_size = random.choice(range(10, 20)) * 32 # 320 - 608 pixels
dataloader = load_images_and_labels(train_path, batch_size=opt.batch_size, img_size=img_size, augment=True)
print('Running Epoch %g at multi_scale img_size %g' % (epoch, img_size))
# Update scheduler (automatic) # Update scheduler (automatic)
# scheduler.step() # scheduler.step()

6
utils/datasets.py
View File

@ -100,7 +100,13 @@ class load_images_and_labels(): # for training
ia = self.count * self.batch_size ia = self.count * self.batch_size
ib = min((self.count + 1) * self.batch_size, self.nF) ib = min((self.count + 1) * self.batch_size, self.nF)
if self.augment is True:
# Multi-Scale YOLO Training
height = random.choice(range(10, 20)) * 32 # 320 - 608 pixels
else:
# Fixed-Scale YOLO Training
height = self.height height = self.height
print(height)
img_all = [] img_all = []
labels_all = [] labels_all = []