https://github.com/tirthasheshpatel/tensorflow2.0-models

Semester 4 Project: Creating and Exporting TensorFlow2.0 Models for Sentiment Analysis
https://github.com/tirthasheshpatel/tensorflow2.0-models

Last synced: 13 days ago
JSON representation

Semester 4 Project: Creating and Exporting TensorFlow2.0 Models for Sentiment Analysis

• Host: GitHub
• URL: https://github.com/tirthasheshpatel/tensorflow2.0-models
• Owner: tirthasheshpatel
• Created: 2020-03-25T09:14:02.000Z (almost 5 years ago)
• Default Branch: master
• Last Pushed: 2020-04-18T17:10:23.000Z (over 4 years ago)
• Last Synced: 2024-11-08T00:52:46.248Z (2 months ago)
• Language: Jupyter Notebook
• Size: 29.9 MB
• Stars: 2
• Watchers: 2
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# TensorFlow2.0-Models

Semester 4 PSC Project: Creating and Exporting TensorFlow2.0 Models for Sentiment Analysis

## Sentiment Analysis Model

We have created a bidirectional LSTM model for sentiment analysis on IMDB dataset of 8000 words. This achieves an accuracy of about 95\% on training set and 86\% on test set. **The training notebook can be found [here](TensorFlow_2_0_Sentiment_Analysis.ipynb).** You can run a GUI based app locally by running ``python gui.py``. This will automatically load all the required models and you are ready to predict the results!!

### Explanatory video can be found [here](explanatory_video.mp4)

## Usage

#### Linux

```shell

git clone https://github.com/tirthasheshpatel/TensorFlow2.0-Models.git

cd TensorFlow2.0-Models

python3 -m venv env

source env/bin/activate

pip install --upgrade pip

pip install -r requirements.txt

python gui.py

```

#### Windows

```bash

git clone https://github.com/tirthasheshpatel/TensorFlow2.0-Models.git

cd TensorFlow2.0-Models

python -m venv env

.\env\Scripts\activate

pip install --upgrade pip

pip install -r requirements.txt

python gui.py

```

### Frameworks Used

1. Tensorflow

2. Tkinter

3. Tensorflow Hub

4. Keras

5. Tensorflow Datasets

### GUI

![gui](images/gui_1.png)

![gui](images/gui_2.png)

![gui](images/gui_3.png)

![gui](images/gui_4.png)

![gui](images/gui_5.png)