Training fails with small data set

jiegzhan / multi-class-text-classification-cnn-rnn

Classify Kaggle San Francisco Crime Description into 39 classes. Build the model with CNN, RNN (GRU and LSTM) and Word Embeddings on Tensorflow.

https://www.kaggle.com/c/sf-crime/data

Apache License 2.0

599 stars 262 forks source link

Closed andrew-sipes closed 6 years ago

andrew-sipes commented 7 years ago

I only have a small training data set (less than 20k). The training fails to learn, because it never completes a cycle of training.

What parameters could I change in the 'training_config.json' to resolve this issue?

JenningsL commented 7 years ago

Increase num_epochs or decrease batch_size.