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
Is your feature request related to a problem? Please describe.
The "Segment Image" scenario currently contains a sample that specifically segments streetscapes. I would not want anyone to come to this scenario trying to segment any type of image and get bad results.
Describe the solution you'd like
Include the model description in the sample page. Model description should include model use cases and constraints/limitations.
Describe alternatives you've considered
We could use more specific scenario names but I don't think that's a good solution. I like the idea of seeking out broad scenarios and then narrowing in on your specific use case.
Additional context
Example:
FFNet model description: "A fuss-free network that segments street scene images with per-pixel classes like road, sidewalk, and pedestrian. Trained on the Cityscapes dataset."
Currently unclear that this only works on cityscapes. Including the above description somewhere would provide the needed clarity.
The text was updated successfully, but these errors were encountered:
Is your feature request related to a problem? Please describe.
The "Segment Image" scenario currently contains a sample that specifically segments streetscapes. I would not want anyone to come to this scenario trying to segment any type of image and get bad results.
Describe the solution you'd like
Include the model description in the sample page. Model description should include model use cases and constraints/limitations.
Describe alternatives you've considered
We could use more specific scenario names but I don't think that's a good solution. I like the idea of seeking out broad scenarios and then narrowing in on your specific use case.
Additional context
Example:
FFNet model description: "A fuss-free network that segments street scene images with per-pixel classes like road, sidewalk, and pedestrian. Trained on the Cityscapes dataset."
Currently unclear that this only works on cityscapes. Including the above description somewhere would provide the needed clarity.
The text was updated successfully, but these errors were encountered: