FragLegs

TOTAL DISK SIZE

WITH sizes AS (SELECT nspname || '.' || relname AS "relation",
    pg_total_relation_size(C.oid) AS "total_size"
  FROM pg_class C
  LEFT JOIN pg_namespace N ON (N.oid = C.relnamespace)
  WHERE nspname NOT IN ('pg_catalog', 'information_schema')
    AND C.relkind <> 'i'
    AND nspname !~ '^pg_toast'
) SELECT pg_size_pretty(SUM(total_size)) FROM sizes;

FragLegs

class AttentionLSTM(LSTM):
    """LSTM with attention mechanism

    This is an LSTM incorporating an attention mechanism into its hidden states.
    Currently, the context vector calculated from the attended vector is fed
    into the model's internal states, closely following the model by Xu et al.
    (2016, Sec. 3.1.2), using a soft attention model following
    Bahdanau et al. (2014).

    The layer expects two inputs instead of the usual one:

FragLegs

# start a new virtualenv
git clone git@github.com:FragLegs/learning2ski.git .
pip install -r requirements.txt
python eval.py -e 150 --monitor --seed 42 l2s
# If you leave off the --monitor flag, the results are a little better