Static Features Classifier - A static features classifier for Point-Could clusters using an Attention-RNN model

Last update: Jan 25, 2022

Overview

Static Features Classifier

This is a static features classifier for Point-Could clusters using an Attention-RNN model

Installation

$ git clone https://github.com/Mohtasib/Static_Features_Classifier.git
$ cd Static_Features_Classifier
$ conda create -n sfc_env python==3.6.10
$ conda activate sfc_env
$ pip install -e .

Example Code

You can simple run the following command to run a sample code

$ python examples/train_and_evaluate.py

Usage

1. Import Libraries:

import numpy as np
from sfc.util import create_dataset
from sfc.models.Attention_RNN import Attention_RNN

2. Define the constants:

NUM_FEATURES = ...

3. Define the directories:

DATA_PATH = ...
My_Model_Logs_DIR = ...
My_Model_Weights = My_Model_Logs_DIR + 'Best_Attention_RNN_ckpt.h5'

4. Create the dataset:

features, labels = create_dataset(DATA_PATH, NUM_FEATURES)

5. Create the model:

My_Model = Attention_RNN(Logs_DIR=My_Model_Logs_DIR)

6. Load the data into the model:

My_Model.x_train = features
My_Model.y_train = labels
My_Model.x_test = ...
My_Model.y_test = ...

7. Train the model:

My_Model.Fit()

8. Evaluate the model:

My_Model.Evaluate()

9. Predict using the model:

predictions = My_Model.Predict(data)

Static Features Classifier - A static features classifier for Point-Could clusters using an Attention-RNN model

Related tags

Overview

Static Features Classifier

Installation

Example Code

Usage

1. Import Libraries:

2. Define the constants:

3. Define the directories:

4. Create the dataset:

5. Create the model:

6. Load the data into the model:

7. Train the model:

8. Evaluate the model:

9. Predict using the model:

NOTE: More details will be available soon!!!

Owner

ABDALKARIM MOHTASIB

This repository contains the code needed to train Mega-NeRF models and generate the sparse voxel octrees

Accuracy Aligned. Concise Implementation of Swin Transformer

Official implementation of NeurIPS'21: Implicit SVD for Graph Representation Learning

Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds (Local-Lip)

Projects for AI/ML and IoT integration for games and other presented at re:Invent 2021.

CAMoE + Dual SoftMax Loss (DSL): Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss

PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems

Danfeng Hong, Lianru Gao, Jing Yao, Bing Zhang, Antonio Plaza, Jocelyn Chanussot. Graph Convolutional Networks for Hyperspectral Image Classification, IEEE TGRS, 2021.

An open source Jetson Nano baseboard and tools to design your own.

OpenPCDet Toolbox for LiDAR-based 3D Object Detection.

Photo2cartoon - 人像卡通化探索项目 (photo-to-cartoon translation project)

[CVPR 2020] Transform and Tell: Entity-Aware News Image Captioning

Physics-informed convolutional-recurrent neural networks for solving spatiotemporal PDEs

Gradient Step Denoiser for convergent Plug-and-Play

Multi-modal Vision Transformers Excel at Class-agnostic Object Detection

LOFO (Leave One Feature Out) Importance calculates the importances of a set of features based on a metric of choice,

Detecting drunk people through thermal images using Deep Learning (CNN)

Proximal Backpropagation - a neural network training algorithm that takes implicit instead of explicit gradient steps

Deep Learning agent of Starcraft2, similar to AlphaStar of DeepMind except size of network.

Learning to Predict Gradients for Semi-Supervised Continual Learning