🤖 Models - Guide

What are Models?

Fluxus External works on AI. The AI collects images that will help the Aim Aligner be more accurate. Models can be manually created by users, shared or modified to improve it's capability. Esentially, the more images that are trained of enemy player skins, the more efficient the model configuration will be. We also have an option 'Collect Data While Playing' to automatically train images too.

Terminology:

Image Training - In AI the term "Trained Images" refers to the process a computer has learned from to understand things like recognizing objects or patterns.

Labelling Images - In AI the term "Labelling images" refers to the process of adding meaningful information to images specifically to train machine learning models.

Creating Models - An ONNX model file is like a ready-to-use cookbook for teaching computers to understand images. It contains all the instructions and knowledge needed for an AI to recognize things in pictures. This file can be easily shared and used by different AI systems, making it convenient for developers to build image-related applications. In the case of Fluxus External, .onnx files are used for recognizing images that Fluxus External needs for it's Aim Aligner to function.

This guide will explain step by step on how to create your own models.

Collecting Images:

1) Manual Method - Download images online such as skins of enemy players. You can find model packs, screenshoting manually from in-game or videos and find other resources.

2) Auto Train Method (Fastest) - Use Fluxus External's 'Collect Data While Playing' feature with 'Aim Only On Trigger Button' enabled. When the Trigger Button is clicked, a screenshot is snapshotted. These images can be found inside the bin > images folder from Fluxus External.

Tip: When training images- whether it's manual or automated. It's important to get high quality images, different skins with added cosmetics, and to get as much detail as possible.

Such as; different positions of the body (Running, jumping, crouching etc). It's also recommended to snapshot images with different distances and to remove images that are irrelevent. Collect and use images that will help train the Aim Aligner to be more accurate in locking onto enemies.

Labelling Images:

Step 1) Visit https://www.makesense.ai and click 'Get Started'

Step 2) Click 'Drop an image' (The more Collected Images the better).

Step 3) Click 'Object detection'

Step 4) Click 'Start project'

Step 5) In the top left corner under 'Actions' click 'Run AI Locally'

Step 6) Select the 'YoloV5' option and click 'Use model!'

Step 7) Click the down arrow and select 'Yolov5n/COCO' then click 'Use model!'

Step 8) Click 'Select all' and Accept. Deselect any model that's not relevent.

Step 9) Under 'Actions' click 'Export Annotations' and choose the first option.

Step 10) Save the Model onto your desktop for easier access.

Training Images

Required:

Step 1) - Install Python.

Step 2) Install Ultralytics

Run CMD as Administrator

Copy and paste the below command into CMD to install Ultralytics (Must have Python first)

pip install ultralytics

Note: If you load up CMD and get this error 'pip' is not recognized as an internal or external command, operable program or batch file.' Watch the tutorial here to fix the path error.

Step 3) - Install PyTorch (Optional)

(This will train images from your GPU instead of CPU, making the process 10X quicker).

To install PyTorch check the following page here. Choose the CUDA option.

To check if PyTorch is installed open Python and run these two commands:

import torch

print(torch.cuda.is_available())

If the result outputs as True then PyTorch is succesfully installed and running.

Tutorial of Training Images

Step 1) Download Image Training Pack.

(The pack contains a ready made folder structure and the tool required for training images).

Step 2) Open the the data.yaml file and set the correct paths.

Train Path - Go to images > train > Copy Path

Example - C:\Users\User\Desktop\Image Training\images\train

Val Path - Go to images > val > Copy path

Example - C:\Users\User\Desktop\Image Training\images\val

Step 3) Upload the collected images inside the images folder under train.

Step 4) Upload the labelled images inside the labels folder under train.

Step 5) Run the following commands in CMD to train the images.

Train Command

yolo task-detect modestrain ingsz=640 data-data.yaml epochs=100 batch-16 name putyourmodelnamehere

Replace the 'putyourmodelnamehere' part with the name of the folder. On default this should be 'Image Training' make sure there aren't any added spaces or that the name is different.

Note: If you increase the epochs number it will increase the speed of the model.

After running this command- it will start training images in 'runs' folder that it creates.

Export Model Command

yolo export model-best.pt format-onnx

Boom! That's it. You've now created your own model from scratch and ready to use.

How to use Model:

Upload the Model File you've exported inside the bin > models folder (From Fluxus External) then drag and drop. You'll then have this saved under 'Local Models' under the Model Selector.

Fluxus External works on 'Hot Swapping' no reload of the app is required for the model to show.

Use Models made by other users:

Join our Discord Server, we have channels where users can request for models or share models within the community. We'll also post models ourselves under the '#✅verified-models' channel.

Use Models made by Aimmy:

Aimmy's public Model directory can be used on Fluxus External.

Link - https://github.com/Babyhamsta/Aimmy/tree/master/models

Note: These models may have their own recommended configs, which can be found here.

We don't own the models or configs so we're not able to verify it's accuracy. It's recommended to make your own or to find directly from our Discord Server shared between community members.