A fast, easy-to-use, production-ready inference server for computer vision supporting deployment of many popular model architectures and fine-tuned models.
We had a bug in the following setup:
object detection -> crop -> classification -> [downstream step],
for any downstream block we could not correctly construct empty Batches of inputs whenever nothing was detected by primary model. Turned out to be stupid bug.
Type of change
Please delete options that are not relevant.
[x] Bug fix (non-breaking change which fixes an issue)
[ ] New feature (non-breaking change which adds functionality)
[ ] This change requires a documentation update
How has this change been tested, please provide a testcase or example of how you tested the change?
new tests
old tests still 🟢
Any specific deployment considerations
For example, documentation changes, usability, usage/costs, secrets, etc.
Description
We had a bug in the following setup:
object detection -> crop -> classification -> [downstream step], for any downstream block we could not correctly construct empty Batches of inputs whenever nothing was detected by primary model. Turned out to be stupid bug.Type of change
Please delete options that are not relevant.
How has this change been tested, please provide a testcase or example of how you tested the change?
Any specific deployment considerations
For example, documentation changes, usability, usage/costs, secrets, etc.
Docs