-
bob@bob-OptiPlex-3020:~/workspace/github/cnn-text-classification-tf$ tensorboard --logdir ./runs/1484553815/summaries/
Starting TensorBoard b'39' on port 6006
(You can navigate to http://127.0.1.1:6006) -
https://github.com/tensorflow/tensorflow/blob/master/tensorflow/tensorboard/README.md
bob@bob-OptiPlex-3020:~/workspace/github/cnn-text-classification-tf$ python3 train.py
Evaluation:
2017-01-16T18:17:26.303447: step 30000, loss 10.7655, acc 0.711069
Saved model checkpoint to /home/bob/workspace/github/cnn-text-classification-tf/runs/1484553815/checkpoints/model-30000
This code belongs to the "Implementing a CNN for Text Classification in Tensorflow" blog post.
It is slightly simplified implementation of Kim's Convolutional Neural Networks for Sentence Classification paper in Tensorflow.
- Python 3
- Tensorflow > 0.12
- Numpy
Print parameters:
./train.py --help
optional arguments:
-h, --help show this help message and exit
--embedding_dim EMBEDDING_DIM
Dimensionality of character embedding (default: 128)
--filter_sizes FILTER_SIZES
Comma-separated filter sizes (default: '3,4,5')
--num_filters NUM_FILTERS
Number of filters per filter size (default: 128)
--l2_reg_lambda L2_REG_LAMBDA
L2 regularizaion lambda (default: 0.0)
--dropout_keep_prob DROPOUT_KEEP_PROB
Dropout keep probability (default: 0.5)
--batch_size BATCH_SIZE
Batch Size (default: 64)
--num_epochs NUM_EPOCHS
Number of training epochs (default: 100)
--evaluate_every EVALUATE_EVERY
Evaluate model on dev set after this many steps
(default: 100)
--checkpoint_every CHECKPOINT_EVERY
Save model after this many steps (default: 100)
--allow_soft_placement ALLOW_SOFT_PLACEMENT
Allow device soft device placement
--noallow_soft_placement
--log_device_placement LOG_DEVICE_PLACEMENT
Log placement of ops on devices
--nolog_device_placement
Train:
./train.py
./eval.py --eval_train --checkpoint_dir="./runs/1459637919/checkpoints/"
Replace the checkpoint dir with the output from the training. To use your own data, change the eval.py
script to load your data.