-
### đź“š Documentation
The following sentence in the save_top_k flag is slightly confusing because this behavior is not outlined anywhere else in the ModelCheckpoint documentation.
"if save_top_k >= …
-
### Description & Motivation
If your model has layers with `torch.nn.parameter.UninitializedParameter`, the parameter count can't be known before `forward()` runs.
The model summary will show a…
-
I converted some Pytorch code to Lightning. The dataset is loaded lazily by the train & eval dataloaders.
However, when moving the code to Lightning, I noticed a huge slowdown. After digging around…
-
### đź“š Documentation
I initialize two processes. The first process is the one that creates the data inside prepare_data.
The second process waits for the first process.
The problem is that when…
-
The goal of this segment is to create meaningful benchmark subsets with a minimal set of tasks.
I believe the steps are as follows:
1) construct an experimental subset. If people agree I can con…
-
Seleção de hosts com padrões de hostExercĂcio orientado: Seleção de hosts com padrões de hostGerenciamento de inventários dinâmicosExercĂcio orientado: Gerenciamento de inventários dinâmicosConfigur…
-
Falta añadir el selector del tipo de post procesado al crear un nuevo voting
-
### Objetivo
Mudar o método de inserção para ao invés de inserir e então procurar pelo nó desbalanceado (`self.insert(data) + self.searchUnbalancedNode()`) fazer com que a função de inserir retorne o…
-
Basically, I'm thinking of a method that says that the winner is the candidate who wins under the most other methods already listed (not sure if there's already a name for this?)
-
To create a Verifiable Credential you "Issue a Verifiable Credential".
To create a Verifiable Presentation you "??? a Verifiable Presentation".
What is the verb that the WG would like to use for…