Skip to content
This repository has been archived by the owner on Jun 13, 2024. It is now read-only.

multiple object using custom dataset #169

Open
mimi616888 opened this issue Nov 11, 2021 · 0 comments
Open

multiple object using custom dataset #169

mimi616888 opened this issue Nov 11, 2021 · 0 comments

Comments

@mimi616888
Copy link

hello, I want to use two classes of my custom dataset to training the multiple objects model.
However, I met this problem when compile the "train_multi.py"
Traceback (most recent call last):
File "train_multi.py", line 413, in
niter = train(epoch)
File "train_multi.py", line 87, in train
loss = region_loss(output, target, epoch)
File "/home/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(input, **kwargs)
File "/media/DATA/YOLO6D/multi_obj_pose_estimation/region_loss_multi.py", line 122, in forward
output = output.view(nB, nA, (2
self.num_keypoints+1+nC), nH, nW)
RuntimeError: shape '[32, 5, 21, 13, 13]' is invalid for input of size 865280

Is there anyone can assist me? Thank you first!

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant