https://github.com/mystic123/tensorflow-yolo-v3

Implementation of YOLO v3 object detector in Tensorflow (TF-Slim)
https://github.com/mystic123/tensorflow-yolo-v3

deep-learning detector object-detection tensorflow tensorflow-yolo yolo yolov3

Last synced: about 2 months ago
JSON representation

Implementation of YOLO v3 object detector in Tensorflow (TF-Slim)

• Host: GitHub
• URL: https://github.com/mystic123/tensorflow-yolo-v3
• Owner: mystic123
• License: apache-2.0
• Created: 2018-05-30T07:48:05.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2023-05-15T12:29:48.000Z (over 1 year ago)
• Last Synced: 2024-08-02T16:03:38.812Z (5 months ago)
• Topics: deep-learning, detector, object-detection, tensorflow, tensorflow-yolo, yolo, yolov3
• Language: Python
• Homepage: https://medium.com/@pawekapica_31302/implementing-yolo-v3-in-tensorflow-tf-slim-c3c55ff59dbe
• Size: 69.3 KB
• Stars: 894
• Watchers: 44
• Forks: 353
• Open Issues: 66
• Metadata Files:
  • Readme: README.md
  • License: LICENSE
  • Code of conduct: CODE_OF_CONDUCT.md

Awesome Lists containing this project

• awesome-yolo-object-detection - mystic123/tensorflow-yolo-v3 - yolo-v3?style=social"/> : Implementation of YOLO v3 object detector in Tensorflow (TF-Slim). (Other Versions of YOLO)
• awesome-yolo-object-detection - mystic123/tensorflow-yolo-v3 - yolo-v3?style=social"/> : Implementation of YOLO v3 object detector in Tensorflow (TF-Slim). (Other Versions of YOLO)

README

        
# tensorflow-yolo-v3

Implementation of YOLO v3 object detector in Tensorflow (TF-Slim). Full tutorial can be found [here](https://medium.com/@pawekapica_31302/implementing-yolo-v3-in-tensorflow-tf-slim-c3c55ff59dbe).

Tested on Python 3.5, Tensorflow 1.11.0 on Ubuntu 16.04.

## Todo list:

- [x] YOLO v3 architecture

- [x] Basic working demo

- [x] Weights converter (util for exporting loaded COCO weights as TF checkpoint)

- [ ] Training pipeline

- [ ] More backends

## How to run the demo:

To run demo type this in the command line:

1. Download COCO class names file: `wget https://raw.githubusercontent.com/pjreddie/darknet/master/data/coco.names`

2. Download and convert model weights:    

    1. Download binary file with desired weights: 

        1. Full weights: `wget https://pjreddie.com/media/files/yolov3.weights`

        1. Tiny weights: `wget https://pjreddie.com/media/files/yolov3-tiny.weights` 

        1. SPP weights: `wget https://pjreddie.com/media/files/yolov3-spp.weights` 

    2. Run `python ./convert_weights.py` and `python ./convert_weights_pb.py`        

3. Run `python ./demo.py --input_img  --output_img  --frozen_model `

####Optional Flags

1. convert_weights:

    1. `--class_names`

        1. Path to the class names file

    2. `--weights_file`

        1. Path to the desired weights file

    3. `--data_format`

        1.  `NCHW` (gpu only) or `NHWC`

    4. `--tiny`

        1. Use yolov3-tiny

    5. `--spp`

        1. Use yolov3-spp

    6. `--ckpt_file`

        1. Output checkpoint file

2. convert_weights_pb.py:

    1. `--class_names`

            1. Path to the class names file

    2. `--weights_file`

        1. Path to the desired weights file    

    3. `--data_format`

        1.  `NCHW` (gpu only) or `NHWC`

    4. `--tiny`

        1. Use yolov3-tiny

    5. `--spp`

        1. Use yolov3-spp

    6. `--output_graph`

        1. Location to write the output .pb graph to

3. demo.py

    1. `--class_names`

        1. Path to the class names file

    2. `--weights_file`

        1. Path to the desired weights file

    3. `--data_format`

        1.  `NCHW` (gpu only) or `NHWC`

    4. `--ckpt_file`

        1. Path to the checkpoint file

    5. `--frozen_model`

        1. Path to the frozen model

    6. `--conf_threshold`

        1. Desired confidence threshold

    7. `--iou_threshold`

        1. Desired iou threshold

    8. `--gpu_memory_fraction`

        1. Fraction of gpu memory to work with