Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Support several convnets #11

Open
3 of 4 tasks
AOS55 opened this issue Mar 31, 2021 · 2 comments
Open
3 of 4 tasks

Support several convnets #11

AOS55 opened this issue Mar 31, 2021 · 2 comments
Assignees
@AOS55

Comments

@AOS55
Copy link
Owner

AOS55 commented Mar 31, 2021 •
edited
Loading

Support for the following ConvNets to compare the performance of each in various tasks:

  • deeplabV3
  • deeplabV3+
  • Unet++
  • HRNet
@AOS55
Copy link
Owner Author

AOS55 commented Mar 31, 2021

Have added support for all but HRNet,
HRNet is proving to be a pain, the repo is available with a model. But no support on hub or segmentation models so manual download is required. Not necessary for now but still worth investigating.

@AOS55
Copy link
Owner Author

AOS55 commented Mar 31, 2021

Might need to change the input_tensor shape or not use segmentation_models as currently getting RuntimeError:

concat_features = torch.cat([aspp_features, high_res_features], dim=1)
RuntimeError: Sizes of tensors must match except in dimension 3. Got 213 and 216 (The offending index is 0)

@AOS55 AOS55 self-assigned this Apr 1, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@AOS55 AOS55

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@AOS55