“RNN test”版本间的差异
来自cslt Wiki
(→140901) |
(→wsj_data) |
||
第14行: | 第14行: | ||
bptt=2 # length of BPTT unfolding in RNNLM | bptt=2 # length of BPTT unfolding in RNNLM | ||
bptt_block=20 # length of BPTT unfolding in RNNLM | bptt_block=20 # length of BPTT unfolding in RNNLM | ||
+ | *Train RNNLM set | ||
{| border="2px" | {| border="2px" |
2014年9月7日 (日) 13:51的版本
wsj Test
wsj_data
- Data
- size:200M,npdata
- 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
- Train RNNLM set
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) |