Jesús Mudarra Luján

https://drive.google.com/file/d/1EUPtbtdF0bjRtNjGv436vDY28EN5DXDH/view?usp=sharing

The weights `(yolo-obj_last.weights)` are saved every 100 iterations after passing 1000 iterations `(yolo-obj_1000.weights)`. At least when I have trained a custom class.

`The problem of : cannot connect to X server` happens when you use `cv2.imshow()` Use --dont_show flag or comment the following lines of detect_video.py when you use Google Colab: ```...

Same way as with detect.py, you can get coordinates using the --info flag Example: `python detect_video.py --weights ./checkpoints/custom-416 --size 416 --model yolov4 --video ./data/video/license_plate.mp4 --output ./detections/recognition.avi --info`

What version of Tensorflow are you using? Try installing the requirements in a virtual environment. I had that problem because I was using a version of Tensorflow higher than `2.3.0rc0`....

I can see that you are using Google Colab. Try uncommenting the `#!pip install -r requirements-gpu.txt` cell and run it to install the libraries and dependencies.

I recommend you to install Anaconda to create virtual environments.

You will probably have to change the line: https://github.com/theAIGuysCode/yolov4-deepsort/blob/9e745bfb3ea5e7c7505cb11a8e8654f5b1319ad9/core/config.py#L14 with the name of the `obj.names` file you have created

Try installing tensorflow-gpu (instead of tensorflow) with `pip install tensorflow-gpu==2.3.0rc0` and check if the GPU is used.

Sorry, I did not see in your previous message the FPS you get. Don't worry, your `15 FPS` is great. I checked this repository on Google Colab using an `NVIDIA...