File size: 1,970 Bytes
3a3c68a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 |
# Import all of the dependencies
import streamlit as st
import os
import imageio
import tensorflow as tf
from utils import load_data, num_to_char
from modelutil import load_model
# Set the layout to the streamlit app as wide
st.set_page_config(layout='wide')
# Setup the sidebar
with st.sidebar:
st.image('https://www.onepointltd.com/wp-content/uploads/2020/03/inno2.png')
st.title('LipBuddy')
st.info('This application is originally developed from the LipNet deep learning model.')
st.title('LipNet Full Stack App')
# Generating a list of options or videos
options = os.listdir(os.path.join('..', 'data', 's1'))
selected_video = st.selectbox('Choose video', options)
# Generate two columns
col1, col2 = st.columns(2)
if options:
# Rendering the video
with col1:
st.info('The video below displays the converted video in mp4 format')
file_path = os.path.join('..','data','s1', selected_video)
os.system(f'ffmpeg -i {file_path} -vcodec libx264 test_video.mp4 -y')
# Rendering inside of the app
video = open('test_video.mp4', 'rb')
video_bytes = video.read()
st.video(video_bytes)
with col2:
st.info('This is all the machine learning model sees when making a prediction')
video, annotations = load_data(tf.convert_to_tensor(file_path))
imageio.mimsave('animation.gif', video, fps=10)
st.image('animation.gif', width=400)
st.info('This is the output of the machine learning model as tokens')
model = load_model()
yhat = model.predict(tf.expand_dims(video, axis=0))
decoder = tf.keras.backend.ctc_decode(yhat, [75], greedy=True)[0][0].numpy()
st.text(decoder)
# Convert prediction to text
st.info('Decode the raw tokens into words')
converted_prediction = tf.strings.reduce_join(num_to_char(decoder)).numpy().decode('utf-8')
st.text(converted_prediction)
|