“RNN TEST”版本间的差异
来自cslt Wiki
| 第1行： | 第1行： | ||
==140901== | ==140901== | ||
wsj_data: | wsj_data: | ||
| − | 1. | + | 一： |
| − | rand_seed= | + | 1. parameter |
| − | + | rand_seed=1 | |
nwords=10000 # This is how many words we're putting in the vocab of the RNNLM. | nwords=10000 # This is how many words we're putting in the vocab of the RNNLM. | ||
hidden=30 | hidden=30 | ||
| 第15行： | 第15行： | ||
3.data_size:200M | 3.data_size:200M | ||
4.data:np_data | 4.data:np_data | ||
| + | 二： | ||
| + | 1.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 | ||
2014年9月2日 (二) 06:59的版本
140901
wsj_data: 一：
1. parameter
rand_seed=1
nwords=10000 # This is how many words we're putting in the vocab of the RNNLM.
hidden=30
class=200 # Num-classes... should be somewhat larger than sqrt of nwords.
direct=1000 # 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
2.time:3-hour
3.data_size:200M
4.data:np_data
二：
1.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
