On a different topic, I can't seem to use my OVH ID for OVH AI Mktplace, which might be fro a reason, BUT I cannot create an account either (login gets registered, but chosen password is not accepted and there IS NO RESET PASSWORD option on login. Tried twice. What gives?) And I cannot seem to be able to leverage the models offered there (but for sentiment analysis) on prescience, so I wanted to try and use them directly through the exposed API, but no obvious way to do so without a key, which I guess might be linked to having an account ? Sorry if this is not the correct venue for those complaints
hello, the marketplace is fully autonomous and not linked to OVH credentials
Once done, you will be able to create token (what you call a « key ») directly in the marketplace
So far, we added Sentiment Analysis in OVHcloud serving
if you have requests, don’t hesitate to explain your use cases here :)
Yeah all those points were indeed what I surmised (different credentials, getting a key from marketplace, and using those models this way). So am stuck at the registration which fails to accept my chosen password (and no reset option). Will try different options, thanks for taking the time to validate my questions. Re: use cases will do once i can see compared to what our exploratory process produces.
(and today password seems to be accepted, maybe a refresh backend issue)
Hello guys! I wanted to use the serving engine with a tensorflow saved model (.pb) but it can't even deploy it. In the documentation it says it accepts "Tensorflow serialized through SavedModel or HDF5" but in the console it's written "Select the pathway for your model’s file in Object Storage. Your file must have the extension: h5 / pmml or onnx". Does it means that I have to convert my model to a hdf5, onnx or pmml format? Thanks in advance.
Hello, to use .pb, you need to choose the directory option and not the single file option. In fact, you should have some other file among your .pb (the weights), so the single file won't work.
Don't hesitate if you need any help
poke @XciD ?
Hi. With different trys, the DeOldify AI seems to not respond. Anyone to confirm ?
Some collegue worked on https://ia-flash.fr which seem to be quite better for car recognition (~20 millions of cars images for training de kernel) - how are the API integrated to the catalogue ? Would be interested aussi to integrate https://deces.matchid.io which relies on a API which allow bulk matching (still in construction but will be stable for bulk in 1 month) - usefull for liberal workers and large administration (banking, retirements payment, etc.)
(this last one will have an ML base rescoring feature soon but is not fully ML, the first one in is pytorch)
hello @rhanka ! for the marketplace new models are integrated by OVH on demand
recently we also launched a service to deploy yourself model : ML serving
it’s like this marketplace but integrated in OVh control panel
We allow customers to deploy their own models but also allow customers to select rpetrained models like AI Flash from a catalog
I see that IAflash is in Apache 2 licence, cool !
i’ll check with our team
Hello, I wonder how to setup an environnment with jupyter or whatever
The idea is to just launch this instance when I need.
hello @slamer59 , so you want an instance with jupyter installed and be able to stop/start it ?
Yes! Like an on demand
It's Ok I found where to setup this. (y)
public cloud VM + snapshot (i’ll do it like that)
i have a jupyter running like this for 3 euros per month (VM S1-2)