Author here, if you have any questions/comments I'll check back in periodically and answer them here!
How does this work in production? I'm especially curious about the stuff that isn't part of the TensorFlow graph like anchor generation and post-processing. Is your service running the graph directly or does it run some Python script that executes the graph?
What that means is that when it comes to inference in a production environment, we only need our Tensorflow python package, as the metagraph is defined in terms that the base Tensorflow package can decypher.
Although as I'm not an author of the object detection API, there is probably a more nuanced answer here.
2. Why would someone run this on Algorithmia instead of their own hosted NC/P2/P3 instance?
3. Have you tried open image with any other DNNs like Shang's implementation of FastMaskRCNN?
2) Scaling is hard, Cross-language Interoperability is hard, And bringing your product to market is hard. Algorithmia solves all of those problems with grace and has a development experience that is second-to-none. Don't take my word for it, compare it against tensorflow-serving other competitor technologies.
3) I haven't yet but I could certainly see an improvement in performance, we did notice a dramatic difference between our SSD and faster-rcnn model as was expected. This was only an intro, but if you create a model that performs better than ours, we'd love to host it on Algorithmia.
On this demo image [0], why isn't "text" found as well since there is clearly text in the image. Is it because "text" isn't considered an object? If so, what would it take (based on your article) to also train for text?
Thanks!