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

create step lr schedule

This commit is contained in:
Glenn Jocher 2018-10-05 17:01:07 +02:00
parent c01b8e6b7c
commit 07ac4fef8d
3 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
models.py
View File

@ -170,8 +170,8 @@ class YOLOLayer(nn.Module):
# lconf = k * BCEWithLogitsLoss(pred_conf[mask], mask[mask].float())
lconf = k * BCEWithLogitsLoss(pred_conf, mask.float())
lcls = k * CrossEntropyLoss(pred_cls[mask], torch.argmax(tcls, 1))
# lcls = k * BCEWithLogitsLoss(pred_cls[mask], tcls.float())
# lcls = k * CrossEntropyLoss(pred_cls[mask], torch.argmax(tcls, 1))
lcls = k * BCEWithLogitsLoss(pred_cls[mask], tcls.float())
else:
lx, ly, lw, lh, lcls, lconf = FT([0]), FT([0]), FT([0]), FT([0]), FT([0]), FT([0])

2
test.py
View File

@ -7,7 +7,7 @@ parser = argparse.ArgumentParser()
parser.add_argument('-batch_size', type=int, default=32, help='size of each image batch')
parser.add_argument('-cfg', type=str, default='cfg/yolov3.cfg', help='path to model config file')
parser.add_argument('-data_config_path', type=str, default='cfg/coco.data', help='path to data config file')
parser.add_argument('-weights_path', type=str, default='checkpoints/yolov3.pt', help='path to weights file')
parser.add_argument('-weights_path', type=str, default='checkpoints/latest.pt', help='path to weights file')
parser.add_argument('-class_path', type=str, default='data/coco.names', help='path to class label file')
parser.add_argument('-iou_thres', type=float, default=0.5, help='iou threshold required to qualify as detected')
parser.add_argument('-conf_thres', type=float, default=0.5, help='object confidence threshold')

4
utils/utils.py
View File

@ -264,8 +264,8 @@ def build_targets(pred_boxes, pred_conf, pred_cls, target, anchor_wh, nA, nC, nG
ty[b, a, gj, gi] = gy - gj.float()
# Width and height (yolo method)
tw[b, a, gj, gi] = torch.log(gw / anchor_wh[a, 0] + 1e-16)
th[b, a, gj, gi] = torch.log(gh / anchor_wh[a, 1] + 1e-16)
tw[b, a, gj, gi] = torch.log(gw / anchor_wh[a, 0])
th[b, a, gj, gi] = torch.log(gh / anchor_wh[a, 1])
# Width and height (power method)
# tw[b, a, gj, gi] = torch.sqrt(gw / anchor_wh[a, 0]) / 2