Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

A framework for using LSTMs to detect anomalies in multivariate time series data. Includes spacecraft anomaly data and experiments from the Mars Science Laboratory and SMAP missions.

Stars: ✭ 589 (+3364.71%)

Mutual labels: jupyter-notebook, lstm

Video Classification

Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101

Stars: ✭ 543 (+3094.12%)

Mutual labels: jupyter-notebook, lstm

Thesemicolon

This repository contains Ipython notebooks and datasets for the data analytics youtube tutorials on The Semicolon.

Stars: ✭ 345 (+1929.41%)

Mutual labels: jupyter-notebook, lstm

Getting Things Done With Pytorch

Jupyter Notebook tutorials on solving real-world problems with Machine Learning & Deep Learning using PyTorch. Topics: Face detection with Detectron 2, Time Series anomaly detection with LSTM Autoencoders, Object Detection with YOLO v5, Build your first Neural Network, Time Series forecasting for Coronavirus daily cases, Sentiment Analysis with BERT.

Stars: ✭ 738 (+4241.18%)

Mutual labels: jupyter-notebook, lstm

Image Captioning

Image Captioning using InceptionV3 and beam search

Stars: ✭ 290 (+1605.88%)

Mutual labels: jupyter-notebook, lstm

Zhihu Text Classification

[2017知乎看山杯多标签文本分类] ye组(第六名) 解题方案

Stars: ✭ 392 (+2205.88%)

Mutual labels: jupyter-notebook, lstm

Cryptocurrency Price Prediction

Cryptocurrency Price Prediction Using LSTM neural network

Stars: ✭ 271 (+1494.12%)

Mutual labels: jupyter-notebook, lstm

Pytorch Ntm

Neural Turing Machines (NTM) - PyTorch Implementation

Stars: ✭ 453 (+2564.71%)

Mutual labels: jupyter-notebook, lstm

Pytorch Seq2seq

Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.

Stars: ✭ 3,418 (+20005.88%)

Mutual labels: jupyter-notebook, lstm

Lstm Human Activity Recognition

Human Activity Recognition example using TensorFlow on smartphone sensors dataset and an LSTM RNN. Classifying the type of movement amongst six activity categories - Guillaume Chevalier

Stars: ✭ 2,943 (+17211.76%)

Mutual labels: jupyter-notebook, lstm

Attention Networks For Classification

Hierarchical Attention Networks for Document Classification in PyTorch

Stars: ✭ 540 (+3076.47%)

Mutual labels: jupyter-notebook, lstm

Stockpriceprediction

Stock Price Prediction using Machine Learning Techniques

Stars: ✭ 700 (+4017.65%)

Mutual labels: jupyter-notebook, lstm

View All Similar Projects ➔

👯 Music2Dance 💃

Generating Dance steps for given music (CNN + LSTM + MDN)

Execution Steps:

1. Installing
    * sudo pip3 install torch torchvision tensorboardX tensorflow numpy scipy imageio opencv-python

2. Creating dataset from videos (Preprocessing videos)
    * python PoseNet/converter/tfjs2python.py
    * python index2_video_shot_processing.py
    * python index3_create_Only_in_out_dataset.py

3. Training
    * python index4_train_mdn_simple_rnn_bnc.py

4. Testing (works directly as pretrained weights included in repo)
    * run jupyter notebook in root directory
    * open index5_test_trained_model_simplernn_for_bnc.ipynb and run all cells
    * use some software(may be windows 10 photos app) to combine generated video and input audio

Results:

Classical	Western	Mixed

Directory Structure:

Music2Dance(project root)
|
│   index2_video_shot_processing.py            - Process mp4 video files present in data directory
│   index3_create_Only_in_out_dataset.py       - Creating input/output bundles for training the model
│   index4_train_mdn_simple_rnn.py             - Process and train with training data
│   index4_train_mdn_simple_rnn_for_bnc.py     - Same as above but if training data has two types of dances (like western and classical)
│   index5_test_trained_model_simplernn.ipynb  - Testing trained model with random audio file
│   index5_test_trained_model_simplernn_for_bnc.ipynb
│   ReadMe.md
│
├───custom_utils                  - Utilities
│       datastft.py
│       mobilenet.py
│       video_shot_processing_utils.py
│
├───data
│   ├───test_audio
│   |       test_audio.wav
|   ├───audio_wav_indexed
|   |       audio (1).wav
|   └───video_wav_indexed
|           video (1).mp4
│
├───Object_detection              - Object Detection model to detect human bounding box before finding the pose 
│   │   mscoco_label_map.pbtxt
│   │   string_int_label_map.proto
│   │   visualization_utils.py
│   │
│   └───ssd_mobilenet_v1_coco_2018_01_28
│       │   checkpoint
│       │   frozen_inference_graph.pb
│       │   model.ckpt.data-00000-of-00001
│       │   model.ckpt.index
│       │   model.ckpt.meta
│       │   pipeline.config
│       │
│       └───saved_model
│           │   saved_model.pb
│           │
│           └───variables
├───output
│   ├───motiondance_simplernn     - Saved weights
│   │   └───checkpoints
│   │           epoch_{num}.pth.tar
│   │
│   ├───motiondance_simplernn_bnc
│   │   └───checkpoints
│   │           epoch_bnc_{num}.pth.tar
│   │
│   ├───Result                    - Test result video files are saved here
│   ├───Result_Audio
│   └───Result_Video
└───PoseNet
    └───converter
        │   config.yaml
        │   manifest.json
        │   tfjs2python.py        - Converting TensorflowJs model to python tensorflow understandable model
        │   wget.py
        │
        └───checkpoints
                checkpoint
                model.ckpt.data-00000-of-00001
                model.ckpt.index
                model.ckpt.meta

References:

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].

Stars: ✭ 17

Visit Git Page 🔗Visit User Page 🔗Visit Issues Page (1) 🔗