Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/justsecret123/one-piece-characters-detector

An object detector trained with a Kaggle GPU, using Tensorflow and a fine-tuned ssd resnet50.
https://github.com/justsecret123/one-piece-characters-detector

artificial-intelligence computer-vision convolutional-neural-networks deep-learning deep-neural-networks docker fine-tuning jupyter kaggle kaggle-dataset matplotlib numpy object-detection python single-shot-detector tensorflow tensorflow-object-detection tensorflow-serving transfer-learning

Last synced: about 2 months ago
JSON representation

An object detector trained with a Kaggle GPU, using Tensorflow and a fine-tuned ssd resnet50.

Host: GitHub
URL: https://github.com/justsecret123/one-piece-characters-detector
Owner: Justsecret123
License: gpl-3.0
Created: 2021-11-05T17:10:34.000Z (over 3 years ago)
Default Branch: main
Last Pushed: 2022-04-23T06:51:22.000Z (almost 3 years ago)
Last Synced: 2024-11-05T18:34:11.979Z (3 months ago)
Topics: artificial-intelligence, computer-vision, convolutional-neural-networks, deep-learning, deep-neural-networks, docker, fine-tuning, jupyter, kaggle, kaggle-dataset, matplotlib, numpy, object-detection, python, single-shot-detector, tensorflow, tensorflow-object-detection, tensorflow-serving, transfer-learning
Language: Jupyter Notebook
Homepage:
Size: 61.9 MB
Stars: 1
Watchers: 1
Forks: 0
Open Issues: 0
Metadata Files:
- Readme: README.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md

Awesome Lists containing this project

README

        # One Piece characters detector ![Language_support](https://img.shields.io/pypi/pyversions/Tensorflow) ![Last_commit](https://img.shields.io/github/last-commit/JustSecret123/Human-pose-estimation) ![Workflow](https://img.shields.io/github/workflow/status/JustSecret123/Human-pose-estimation/Pylint/main) ![Tensorflow_version](https://img.shields.io/badge/Tensorflow%20version-2.6.2-orange)

An object detector trained with a Kaggle GPU on One Piece images, using Tensorflow and a fine-tuned ssd resnet50. 

> **Deployed on my [personal Docker Hub repository](https://hub.docker.com/repository/docker/ibrahimserouis/my-tensorflow-models)

> **Kaggle Notebook link:  [Kaggle notebook](https://www.kaggle.com/ibrahimserouis99/custom-object-detector-one-piece-characters)

> **One Piece Detector SavedModel : [Drive](https://drive.google.com/drive/folders/11FVvs6Z7yRLAlJgoclrUEnzlsX8uzfkB?usp=sharing)



  



# Model and configuration summary 

- Class count : 1

- Labels : ["character"]

- Model type : detection 

- Base model : ssd_resnet50_v1_fpn_640x640_coco17_tpu-8 

# Results : screenshots

## Sample video

![Test1](/Screenshots/results_detector_1.gif)

## Test with 4 characters

![First test](Screenshots/Results_4_characters.png)

# Useful links 

## How to run inferences on a video : [commnand line runner](https://github.com/Justsecret123/One-Piece-characters-detector/blob/main/Scripts/op_detector_video.py)

> Note : Before running the script, you must first download the One Piece object detector model [here](https://drive.google.com/drive/folders/11FVvs6Z7yRLAlJgoclrUEnzlsX8uzfkB?usp=sharing).

### Args

![Command line runner](Screenshots/command_line_video_args.PNG)

### Execution example

![Execution](/Screenshots/command_line_runner.PNG)

Check the [sample command for executing the command line runner](/Scripts/op_detector_video.bat)

## Tensorflow Serving container test script 

- [On GitHub](Scripts/Prediction_OP_detection_model.py)

- [Label map](Scripts/tf_label_map.pbtxt)

## Training notebook 

- [Kaggle](https://www.kaggle.com/ibrahimserouis99/custom-object-detector-one-piece-characters)

- [GitHub](Notebooks/custom-object-detector-one-piece-characters.ipynb)

## How to concatenate mutliple TFRecord files into the Training and Validation sets 

- [Kaggle](https://www.kaggle.com/ibrahimserouis99/generate-training-and-validation-records)

- [GitHub](Notebooks/generate-the-training-and-validation-tfrecords.ipynb)

## Training pipeline configuration file : [Here](Config/pipeline_batch_size_8.config)

## Prerequisites 

- Python 3.7 or higher 

- Tensorflow 2.6 or higher 

- Tensorflow Object Detection API

- NumPy

- Matplotlib