-
> [!NOTE]
> If you have a request to support a specific method, or would like to see priority of one of the listed methods, please open a separate issue, so it won't get buried in this thread. Base…
-
@seabbs put together a to do list - adding a copy here for reference/easier access.
Direct copy of text but I have reorganised into chunks.
#### Maintain week-to-week code
- [x] Review current…
-
I see we need to do pre and post process on the client side. And I couldn't see any custom python backend and ensemble scheduling for pre and post process on server side like Triton Inference Server. …
-
It is commonly known that ensembling produces better models. I saw this done in another paper where they used AutoSKLearn, but turned off ensembling to have a fairer comparison. Should we do the same?
-
**Describe your proposed solution**
I am trying to deploy ensemble model to Triton with ModelMesh. In order to do this I need a mechanism to ensure that all the sub models have to be in a same pod.…
-
**Description**
Implementing BLS in python backend to send in-flight inference request to another model using c_python_backend_utils.InferenceRequest() and passing in a list of c_python_backend_uti…
-
Currently up at ISI and need a version up and available at TACC
-
chat gpt: https://chatgpt.com/c/670d825c-5b44-8008-af85-dac1ffbaae92
R&D: training and prediction flow
- [x] research on picking look back period within same day for all window size
- [x] revisit nom…
-
In your paper 《Path Aggregation Network for Instance Segmentation》， you said that "we use 3ResNeXt-101(64*4d), 2SE-ResNeXt-101(32*4d), 1 ResNet-269 and 1 SENet as ensemble for bounding box and mask ge…
-
current "mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis" model, gives us a sentiment score for a headline.
in this example, the score of 0.99 tells us about the probability of th…