Python framework for Speech and Music Detection using Keras.
-
Updated
Mar 24, 2023 - Python
Python framework for Speech and Music Detection using Keras.
Deep Convolutional Q learning based Self learning implementation for Subway Surfers game
Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM.
Implementation of Convolutional Encoder Decoder Network for short term (0 - 2 hours) weather forecasting.
In this project we have explored the use of imaging time series to enhance forecasting results with Neural Networks. The approach has revealed itself to be extremely promising as, both in combination with an LSTM architecture and without, it has out-performed the pure LSTM architecture by a solid margin within our test datasets.
This is a solution to Cinnamon AI Challenge (https://drive.google.com/drive/folders/1Qa2YA6w6V5MaNV-qxqhsHHoYFRK5JB39) using convolutional, attention, bidirectional LSTM, achieving CER 0.081 WER 0.188 and SER 0.89
Tracking and Detection of the Soccer Ball
This repository introduces Deep Particulate Matter Network with a Separated Input model based on deep learning by using ConvGRU, which can simultaneously analyze spatiotemporal information to consider the diffusion of particulate matter.
Training a neural network to play Rivals of Aether
This is an implementation of DenseNet Architecture combined with LSTM for sequence modeling.
This repo includes Zhang2019's CLSTM implemented using keras(tensorflow2). Zhang2019:Zhang, Haokui, et al. "Exploiting temporal consistency for real-time video depth estimation." Proceedings of the IEEE International Conference on Computer Vision. 2019.
GASP: Gated Attention for Saliency Prediction (IJCAI-21)
LSTM Pose Machines for Video Human Pose Estimation - Implemented by PyTorch
This repository includes sample codes for machine learning and deep learning projects.
Next-Frame Prediction Using Convolutional LSTM
his is a Speech Emotion Recognition system that classifies emotions from speech samples using deep learning models. The project uses four datasets: CREMAD, RAVDESS, SAVEE, and TESS. The model achieves an accuracy of 96% by combining CNN, LSTM, and CLSTM architectures, along with data augmentation techniques and feature extraction methods.
Identifying text in images in different fonts using deep neural network techniques.
Add a description, image, and links to the convolutional-lstm topic page so that developers can more easily learn about it.
To associate your repository with the convolutional-lstm topic, visit your repo's landing page and select "manage topics."