Update README.md
Browse files
README.md
CHANGED
|
@@ -24,6 +24,43 @@ YOLO, for "You Only Look Once", is an object detection system in real-time, intr
|
|
| 24 |
This YOLOv4 library, inspired by previous YOLOv3 implementations here:
|
| 25 |
* [Yolov3 tensorflow](https://github.com/YunYang1994/tensorflow-yolov3)
|
| 26 |
* [Yolov3 tf2](https://github.com/zzh8829/yolov3-tf2)uses Tensorflow 2.0 and is available on this [Github](https://github.com/hunglc007/tensorflow-yolov4-tflite).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
|
| 28 |
### Evaluate on COCO 2017 Dataset
|
| 29 |
```bash
|
|
|
|
| 24 |
This YOLOv4 library, inspired by previous YOLOv3 implementations here:
|
| 25 |
* [Yolov3 tensorflow](https://github.com/YunYang1994/tensorflow-yolov3)
|
| 26 |
* [Yolov3 tf2](https://github.com/zzh8829/yolov3-tf2)uses Tensorflow 2.0 and is available on this [Github](https://github.com/hunglc007/tensorflow-yolov4-tflite).
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
### Limitations and biases
|
| 30 |
+
|
| 31 |
+
### How to use YOLOv4tflite
|
| 32 |
+
You can use this model to detect objects in an image of choice. Follow the following scripts to implement on your own!
|
| 33 |
+
|
| 34 |
+
```bash
|
| 35 |
+
# install git lfs
|
| 36 |
+
!git lfs install
|
| 37 |
+
|
| 38 |
+
# if presented with the error "git: 'lfs' is not a git command. See 'git --help'", try running these linux commands:
|
| 39 |
+
!curl -s https://packagecloud.io/install/repositories/github/git-lfs/script.deb.sh | sudo bash
|
| 40 |
+
|
| 41 |
+
# change directory to base
|
| 42 |
+
%cd ..
|
| 43 |
+
|
| 44 |
+
# install git-lfs
|
| 45 |
+
!sudo apt-get install git-lfs
|
| 46 |
+
|
| 47 |
+
# for message "Git LFS initialized"
|
| 48 |
+
!git lfs install
|
| 49 |
+
|
| 50 |
+
# change directory to yolo_v4_tflite
|
| 51 |
+
%cd ./yolo_v4_tflite
|
| 52 |
+
|
| 53 |
+
# clone this repo into your notebook
|
| 54 |
+
!git clone https://huggingface.co/SamMorgan/yolo_v4_tflite
|
| 55 |
+
|
| 56 |
+
# Run demo tensor flow for an example of how this model works
|
| 57 |
+
!python detect.py --weights ./checkpoints/yolov4-416 --size 416 --model yolov4 --image ./data/kite.jpg --output ./test.jpg
|
| 58 |
+
|
| 59 |
+
# Try with your own image
|
| 60 |
+
!python detect.py --weights ./checkpoints/yolov4-416 --size 416 --model yolov4 --image <insert path to image of choice> --output <insert path to output location of choice>
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
```
|
| 64 |
|
| 65 |
### Evaluate on COCO 2017 Dataset
|
| 66 |
```bash
|