Thomas Delteil
Thomas Delteil
Thanks for the great implementation, the performance is impressive. I was wondering what it would take to add the ability to delete an element from the graph without degrading too...
Hey @ilkarman there is mention of an incompatibility with keras >2.1.4, can this be fixed? I'd like to try with the keras-mxnet backend to see if there is any difference....
Just wanted to make sure my understanding is right. Looking at the formulas, on the edge case, maximizing the probability for `x=-1` is maximizing this function: `logProb(μ, σ) = (-1...
Jetsons do not use nvidia-smi, hence inaccurate gpu count, 0 instead of one.
It would be great to have a swagger client UI to manage the number of workers etc. It is fairly easy to integrate. See: https://swagger.io/tools/swagger-ui/
For certain use-cases, for example when you prefer to have docker image as artefact rather than relying only on the `.mar` format. (That can be the case when your models...
Feel free to close if you disagree but since MMS is running in the background as daemon, I think it would be clearer if it followed the more common usage:...
When building models it would be nice to have a field to add a version of the model in the `signature.json` file, this model version would be available in the...
Here is my signature.json ``` { "inputs": [ { "data_name": "data", "data_shape": [0, 3, 224, 224] } ], "input_type": "application/json", "outputs": [ { "data_name": "relu6", "data_shape": [0, 512] } ],...
Hi, Is there a way right now to support attribution for a pre-generated input / output pair. (Without relying on the generation of a model). For example, let's say I...