Convolutional Neural Network for Text Classification in Tensorflow

Last update: Jan 02, 2023

Overview

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.

Requirements

Python 3
Tensorflow > 0.12
Numpy

Training

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

Evaluating

./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.

Convolutional Neural Network for Text Classification in Tensorflow

Related tags

Overview

Requirements

Training

Evaluating

References

Owner

Denny Britz

TorchMD-Net provides state-of-the-art graph neural networks and equivariant transformer neural networks potentials for learning molecular potentials

Code for the paper "Jukebox: A Generative Model for Music"

Denoising Diffusion Probabilistic Models

This package proposes simplified exporting pytorch models to ONNX and TensorRT, and also gives some base interface for model inference.

CPU inference engine that delivers unprecedented performance for sparse models

Implement of "Training deep neural networks via direct loss minimization" in PyTorch for 0-1 loss

Official repository for the NeurIPS 2021 paper Get Fooled for the Right Reason: Improving Adversarial Robustness through a Teacher-guided curriculum Learning Approach

An experiment on the performance of homemade Q-learning AIs in Agar.io depending on their state representation and available actions

Contrastive Learning of Structured World Models

Seeing Dynamic Scene in the Dark: High-Quality Video Dataset with Mechatronic Alignment (ICCV2021)

Pytorch implementation of NEGEV method. Paper: "Negative Evidence Matters in Interpretable Histology Image Classification".

PCGNN - Procedural Content Generation with NEAT and Novelty

This PyTorch package implements MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation (NAACL 2022).

Semantic Segmentation for Aerial Imagery using Convolutional Neural Network

[NeurIPS 2021] ORL: Unsupervised Object-Level Representation Learning from Scene Images

Segmentation models with pretrained backbones. Keras and TensorFlow Keras.

Pcos-prediction - Predicts the likelihood of Polycystic Ovary Syndrome based on patient attributes and symptoms

Keras implementation of Real-Time Semantic Segmentation on High-Resolution Images

Deploy a ML inference service on a budget in less than 10 lines of code.

A Transformer-Based Feature Segmentation and Region Alignment Method For UAV-View Geo-Localization