“RNN test”版本间的差异
来自cslt Wiki
(→wsj_data) |
|||
| 第2行: | 第2行: | ||
=== wsj_data === | === wsj_data === | ||
| − | * | + | *Data |
| + | :* size:200M | ||
*parameter | *parameter | ||
rand_seed=1 | rand_seed=1 | ||
2014年9月5日 (五) 02:47的版本
140901
wsj_data
- Data
- size:200M
- parameter
rand_seed=1
nwords=10000 # This is how many words we're putting in the vocab of the RNNLM.
hidden=320
class=300 # Num-classes... should be somewhat larger than sqrt of nwords.
direct=2000 # Number of weights that are used for "direct" connections, in millions.
rnnlm_ver=rnnlm-0.3e # version of RNNLM to use
threads=1 # for RNNLM-HS
bptt=2 # length of BPTT unfolding in RNNLM
bptt_block=20 # length of BPTT unfolding in RNNLM
| Parameters | hidden | class | direct | bbt | bptt_block | threads | direct-order | rand_seed | nwords | time(min) |
|---|---|---|---|---|---|---|---|---|---|---|
| set1 | 320 | 300 | 2000 | 2 | 20 | 1 | 4 | 1 | 10000 | 3380(56h) |