-
From my understanding, all four of these methods: `predict`, `predict_on_batch`, `predict_step`, and a direct forward pass through the model (e.g. `model(x, training=False)` or `__call__()`) should al…
-
Hi there,
I've encountered some strange behaviour around the extend_idata parameter which feeds `predict`, `predict_posterior` and `sample_posterior_predictive`.
I've attached code and screensho…
-
Hello,
While using the pretrained model, I've observed that many queries in pred_logits are predicting class 1, which corresponds to cars. For each output I examined, a significant number of querie…
-
Internal: b/242216228
### Use case
Several popular pub packages ([local_auth](https://pub.dev/packages/local_auth#android-integration), [health](https://pub.dev/packages/health#android-14)) requir…
-
- PyTorch-Forecasting version: 1.0.0
I have a DeepAR model that I have built from the [sample](https://pytorch-forecasting.readthedocs.io/en/stable/tutorials/deepar.html). I am not really sure how …
-
Hi,
Very nice work. Thank you for your contribution.
At the step where we feed in "Custom" covariate models, I am interested in providing custom fit and predict functions. I see from the source co…
-
I'd love to see predictive back gesture animations in this app.
I found this "guide" for adding these: https://docs.flutter.dev/platform-integration/android/predictive-back
I have no experience wi…
-
-
Hi Chai team,
I encountered an issue when predicting protein-ligand structures using the Chai-1 web server. It appears that all ligands in the predicted structures are renamed to “LIG”, which preve…
-
How does the init score work for the classifier?
When not passing a model, do you need to pass the result of model.predict_proba(X) ? or model.predict(X)?
Kind Regards