lukaszdz
lukaszdz
When I tried to utilize MCC in my LSTM, it was always returning zero. Model definition: ``` model = Sequential() model.add(Embedding(voc_size, embedding_vector_features, input_length=25)) model.add(Dropout(0.4)) # reduce overfitting model.add(LSTM(100)) model.add(Dropout(0.4)) model.add(Dense(1,...
If you add the following snippet to `current_platfrom()`, i think it should do the trick, no? ``` elif sys.platform.startswith( "linux" ) and platform.uname().machine.startswith("aarch64"): return "arm_linux" ```
@timetheoretical want to add in the above code for aarch64 and get this merged?
@danielbeltejar @timetheoretical Bumping this.
@NeroOkwa This is almost there. Ideally, we would want to see the dataset sizes in the graph view so we can view any issues with the pipeline without having to...
can be viewed directly on the node in the graph view: can use abbreviations with up to 3 digits to show the rough size/number of rows. If empty - then...
1. I dont understand the question 2. I'm not sure what that screen is, but seeing something in the CLI is not as useful as seeing it visually 3. I'm...
1. I would like to be able to easily create a kedro data pipeline and call that from within a function that already exists in my code base. I installed...
it's important to show, directly on the graph, the size of the data (number of rows) before+after each step, so cases where the pipeline only runs on partial data can...