KO
|
EN
gitlite โ search
Search
#python
#java
#python3
#arduino
#golang
#machine-learning
#rust
#html
#flask
#javascript
#seismology
#nodejs
cnn-text-classification-tf
โ 20
Open GitHub โ
No description available.
Download README (.md)
Explore Similar Repositories
Python3.6.2-tutorial-zh-CN
:
๐ฆPython3.6.2 ๅฎๆนๆๆกฃ ไธญๆ็ฟป่ฏ
Gibbed.MT
:
Tools & code for use with MT Framework-based games (a variety of games from Capcom).
accountbook
:
ไธไธชweb app๏ผ้ๅไธไธช็พคไฝไฝฟ็จ็็พค่ดฆๆฌ
GPS-Receiver
:
This repository consists of the processing of the recieved GPS signals at the receiver side. MATLAB has been put to use. MATLAB to HDL may be used for running it on an FPGA.
Web-Scraping-Machine-Learning
:
Hackmageddon
// repository documentation
Was this content helpful?
โ 0
(0 ratings)
Select Rating:
โ
โ
โ
โ
โ
Submit Feedback
Recent Feedback
×
Download README
Do you want to download the
README.md
file for
cnn-text-classification-tf
?
Download (.md)
# cnn-text-classification-tf The base project is **[dennybritz/cnn-text-classification-tf](https://github.com/dennybritz/cnn-text-classification-tf)**. It can classify the positive and negative movie reviews. I modified it to have 5 labels(0,1,2,3,4). It is slightly simplified implementation of Kim's [Convolutional Neural Networks for Sentence Classification](http://arxiv.org/abs/1408.5882) paper in Tensorflow. ## Requirements - Python 3 - Tensorflow > 0.12 - Numpy ## Install tensorflow Please see the [install guide](https://www.tensorflow.org/install/) in tensorflow website. ## Training Print parameters: ```bash ./train.py --help ``` ``` optional arguments: -h, --help show this help message and exit --data_file DATA_FILE File for training or evaluation (default: /data/train.txt for training, /data/dev.txt for evaluation) --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: ```bash ./train.py ``` Train, including the Kaggle dataset: ```bash ./train.py --data_file ./data/train-all.txt ``` ## Evaluating ```bash ./eval.py --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. ## References - [Convolutional Neural Networks for Sentence Classification](http://arxiv.org/abs/1408.5882) - [A Sensitivity Analysis of (and Practitioners' Guide to) Convolutional Neural Networks for Sentence Classification](http://arxiv.org/abs/1510.03820)
