-
# Description
The scenario will request offers based on the parameters set in the Trip file (Date hour of departure, O&D, Passenger type, etc..;)
Not knowing the type of offer sent back, the scenario …
-
We have a SPA that uses pop-ups to establish web sessions (tracked in first-party cookies) to other user-defined domains and then uses CORS XHR/Fetch POST requests to execute queries on those remote s…
-
Because DistDGL and by extension GraphStorm has an assumption of a shared filesystem to function properly, in our SageMaker implementations need to implement various downloads and uploads to "fake" th…
-
Hi, I have two questions of setting eval_batch_size:
i) In FullSortEvalDataLoader, why the eval_batch_size is set differently for sequential models and other models. Per my understanding, it seems …
-
In our weekly data sets we currently show the *most recent* 7 days for the user regardless of whether they have sequential data.
-
# Summary of problem
Applying tfp.stats.histogram on the data in a tf keras model breaks XLA compilation. The example code (see below) works on CPU/GPU but with TPU strategy raises:
```
InvalidArgu…
-
With Native Keras Sequential model, I could do model.fit(..., validation_data=(test_x, test_y)...)
after implementing SciKeras's KerasRegressor() wrapper, where should I enter validation syntax?
-
@willwerscheid was wondering about a scenario where for a large data-set we can load the data once, and subsample from it many times to simulate smaller data. This boils down to some sequential execut…
-
As we move from images to videos, it seems imperative to feed sequential data into common image layers. However, the problem of dealing sequential data with such layers is not clears on Pytorch. I sug…
-
### 🚀 The feature, motivation and pitch
https://arxiv.org/pdf/2403.11421.pdf
This paper might be interesting.
> Cost of serving large language models (LLM) is high, but the
expensive and scarc…