You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
when i am training yolov2 for single class i am getting following error.
" net_utils.load_net(args.model, net)
File "/home/ubuntu/projects/lesiondetectlong/utils/network.py", line 63, in load_net
v.copy_(param)
RuntimeError: The expanded size of the tensor (30) must match the existing size (60) at non-singleton dimension 0
"
when i printed out the output channels of conv5 layers it has to show "out_channels = num_anchors * (num_classes + 5) "
for single class it must be 30 .
but i am getting 60 output channels
The text was updated successfully, but these errors were encountered:
when i am training yolov2 for single class i am getting following error.
" net_utils.load_net(args.model, net)
File "/home/ubuntu/projects/lesiondetectlong/utils/network.py", line 63, in load_net
v.copy_(param)
RuntimeError: The expanded size of the tensor (30) must match the existing size (60) at non-singleton dimension 0
"
when i printed out the output channels of conv5 layers it has to show "out_channels = num_anchors * (num_classes + 5) "
for single class it must be 30 .
but i am getting 60 output channels
The text was updated successfully, but these errors were encountered: