feat: enhance prediction handling by validating output channels and a…#188
feat: enhance prediction handling by validating output channels and a…#188rhoadesScholar merged 33 commits intomainfrom
Conversation
…djusting target array shapes
There was a problem hiding this comment.
Pull request overview
This PR enhances the prediction pipeline to better handle models whose outputs don’t map 1:1 to the configured class list, by inferring/validating output channel counts and reshaping target array specs accordingly.
Changes:
- Adds a preflight forward pass to infer the model’s output channel count and (optionally) adjust
target_arrays[*]["shape"]. - Updates per-batch prediction handling to support “multiple channels per class” by splitting the output tensor into per-class tensors.
- Adds (intended) validation/erroring for output-channel/class-count mismatches during prediction.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
|
@rhoadesScholar I've opened a new pull request, #189, to work on those changes. Once the pull request is ready, I'll request review from you. |
Co-authored-by: Copilot <[email protected]>
Co-authored-by: Copilot <[email protected]>
There was a problem hiding this comment.
Pull request overview
Copilot reviewed 5 out of 5 changed files in this pull request and generated 5 comments.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
|
@rhoadesScholar I've opened a new pull request, #191, to work on those changes. Once the pull request is ready, I'll request review from you. |
|
@rhoadesScholar I've opened a new pull request, #192, to work on those changes. Once the pull request is ready, I'll request review from you. |
|
@rhoadesScholar I've opened a new pull request, #193, to work on those changes. Once the pull request is ready, I'll request review from you. |
Co-authored-by: Copilot <[email protected]>
|
@rhoadesScholar I've opened a new pull request, #194, to work on those changes. Once the pull request is ready, I'll request review from you. |
Co-authored-by: rhoadesScholar <[email protected]>
…tput Co-authored-by: rhoadesScholar <[email protected]>
Co-authored-by: rhoadesScholar <[email protected]>
There was a problem hiding this comment.
Pull request overview
Copilot reviewed 5 out of 5 changed files in this pull request and generated 3 comments.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Co-authored-by: Copilot <[email protected]>
There was a problem hiding this comment.
Pull request overview
Copilot reviewed 5 out of 5 changed files in this pull request and generated 5 comments.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
There was a problem hiding this comment.
Pull request overview
Copilot reviewed 8 out of 8 changed files in this pull request and generated 3 comments.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Co-authored-by: Copilot <[email protected]>
|
@rhoadesScholar I've opened a new pull request, #196, to work on those changes. Once the pull request is ready, I'll request review from you. |
…ehavior Co-authored-by: rhoadesScholar <[email protected]>
Fix num_channels_per_class=1 behavior in structure_model_output
There was a problem hiding this comment.
Pull request overview
Copilot reviewed 8 out of 8 changed files in this pull request and generated no new comments.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
…djusting target array shapes