Of the three examples here only hash correctly reports if an executable is in the PATH. type -p and command -v both report success on aliases, builtins, etc.

type -P (capital P) does correctly report if an executable is in the PATH.

Perhaps this section could

The diagram in documentation suggest yes, but num_fc_layers and fc_layers are not listed as available parameters as they are for e.g., parallel cnn or stacked cnn.

It does not seem like it is supported based on a few experiments however I am using the RNN encoder inside a sequence combiner, so possibly this is causing problems.

for example, this does not seem to add any fc_layers:

co

Description

When downloading a library, a mode, a tool, or an example, the downloading mechanism tries to do that in one go. So if the computer gets suspended or something interrupts the download process, the whole thing has to be downloaded again altogether. This is a hassle for people with slow or spotty internet connections.

Expected Behavior

The downloader should cache what it alrea

In machine_learning_workflow_abalone.ipynb , the section "Building a machine learning workflow" starts with the text "e2e_pipeline.png" . This looks like a formatting error; the image is in the source code but is not displayed.

Reproduction Steps

1. Set deck description to <script>a=1</script>
2. View deck description

Expected Result

Deck description should be blank, instead of a=1

Actual Result

Deck description is shown as a=1. Only <script> and </script> gets removed

Debug info

AnkiDroid Version = 2.9.2beta4

Android Version = 4.4.2

ACRA UUID = 34141f01-8