Skip to content

Remove max_review_length aggregate from sentiment_dnn #50

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Apr 5, 2019
Merged

Remove max_review_length aggregate from sentiment_dnn #50

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 1 addition & 2 deletions examples/reviews/implementations/models/sentiment_dnn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,11 +5,9 @@
def create_estimator(run_config, model_config):
hparams = model_config["hparams"]
vocab_size = len(model_config["aggregates"]["reviews_vocab"])
max_review_length = model_config["aggregates"]["max_review_length"]

def model_fn(features, labels, mode, params):
embedding_input = features["embedding_input"]
embedding_input = tf.reshape(embedding_input, [-1, max_review_length])
model = keras.Sequential()
model.add(keras.layers.Embedding(vocab_size, 16))
model.add(keras.layers.GlobalAveragePooling1D())
Expand All @@ -36,6 +34,7 @@ def model_fn(features, labels, mode, params):
loss=loss,
train_op=optimizer.minimize(loss, tf.train.get_or_create_global_step()),
)

if mode is tf.estimator.ModeKeys.EVAL:
logits = model(embedding_input, training=False)
loss = tf.losses.sparse_softmax_cross_entropy(labels=labels, logits=logits)
Expand Down
1 change: 0 additions & 1 deletion examples/reviews/resources/models.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,6 @@
- embedding_input
aggregates:
- reviews_vocab
- max_review_length
hparams:
learning_rate: 0.01
data_partition_ratio:
Expand Down