-
-
Save tokestermw/27ba700cb482bd59210ae99b285175a3 to your computer and use it in GitHub Desktop.
setup for ptb language model w/ keras (not a working example; missing personal libraries)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
B = self.igor.batch_size | |
R = self.igor.rnn_size | |
S = self.igor.max_sequence_len | |
V = self.igor.vocab_size | |
E = self.igor.embedding_size | |
### loaded from glove | |
emb_W = self.igor.embeddings.astype(theano.config.floatX) | |
## dropout parameters | |
p_emb = self.igor.p_emb_dropout | |
p_W = self.igor.p_W_dropout | |
p_U = self.igor.p_U_dropout | |
p_dense = self.igor.p_dense_dropout | |
w_decay = self.igor.weight_decay | |
M = Sequential() | |
M.add(Embedding(V, E, batch_input_shape=(B,S), input_length=S, | |
W_regularizer=l2(w_decay), | |
weights=[emb_W], mask_zero=True, dropout=p_emb)) | |
#for i in range(self.igor.num_lstms): | |
M.add(LSTM(R, return_sequences=True, dropout_W=p_W, dropout_U=p_U, | |
U_regularizer=l2(w_decay), W_regularizer=l2(w_decay))) | |
M.add(Dropout(p_dense)) | |
## from dropout rnn paper: keep same # of active connections as early layer, hence the scaling of R | |
M.add(LSTM(R*int(1/p_dense), return_sequences=True, dropout_W=p_W, dropout_U=p_U)) | |
M.add(Dropout(p_dense)) | |
M.add(TimeDistributed(Dense(V, activation='softmax', | |
W_regularizer=l2(w_decay), b_regularizer=l2(w_decay)))) | |
optimizer = Adam(self.igor.LR, clipnorm=self.igor.max_grad_norm, | |
clipvalue=5.0) | |
M.compile(loss='categorical_crossentropy', optimizer=optimizer, | |
metrics=['accuracy', 'perplexity']) | |
""" | |
configuration used (yaml file): | |
########### │·········· | |
## set in training │·········· | |
########### │·········· | |
max_sequence_len: -1 │·········· | |
vocab_size: 0 │·········· | |
###### │·········· | |
## training parameters │·········· | |
##### │·········· | |
num_epochs: 1500 │·········· | |
max_grad_norm: 10 │·········· | |
LR: 0.0005 │·········· | |
max_sentence_length: 100 │·········· | |
frequency_cutoff: null │·········· | |
size_cutoff: 10000 │·········· | |
#### ############### │·········· | |
## model parameters │·········· | |
######### │·········· | |
embedding_size: 300 │·········· | |
rnn_size: 368 │·········· | |
batch_size: 32 │·········· | |
p_emb_dropout: 0.5 │·········· | |
p_W_dropout: 0.5 │·········· | |
p_U_dropout: 0.5 │·········· | |
p_dense_dropout: 0.5 │·········· | |
weight_decay: 1e-8 │·········· | |
############## │·········· | |
## file stuff │·········· | |
############# │·········· | |
saving_prefix: ptb_april15 │·········· | |
from_checkpoint: False │·········· | |
train_filepath: data/ptb.train.txt │·········· | |
dev_fp: data/ptb.valid.txt │·········· | |
test_fp: data/ptb.test.txt │·········· | |
glove_fp: /research/data/glove/glove.840B.300d.txt │·········· | |
embeddings_file: data/ptb_embeddings_april15.pkl │·········· | |
vocab_file: data/ptb_april15.vocab │·········· | |
######### │·········· | |
## logger stuff │·········· | |
########## │·········· | |
disable_logger: False | |
""" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment