yolov4-deepsort icon indicating copy to clipboard operation
yolov4-deepsort copied to clipboard

Object tracking implemented with YOLOv4, DeepSort, and TensorFlow.

Results 122 yolov4-deepsort issues
Sort by recently updated
recently updated
newest added

weights not saved and not detection when I try to run save_model.py it runs without error but all the weights are not saved properly. it says Total params: 64,003,990 Trainable...

Hi, So I've trained a YOLOv4 custom object detector on Colab and then downloaded the yolov4-custom.weights file. When I run `python save_model.py --weights ./data/yolov4-custom.weights --output ./checkpoints/yolov4-custom --model yolov4` using a...

In the readme file, it is described that cuda toolkit version 10.1 is required for this project. But I've cuda toolkit 11.7. Will it work? If no, then how to...

Hi, I tried all 3 models - yolov3, yolov4 and yolo-tiny I downloaded the yolo .weights file, when I run `python save_model.py --model yolov4`, the `./checkpoints/yolov4-416/` has the .pb files...

I updated conda-cpu.yml with tensorflow==2.3.0 instead of 2.3.0rc0. After that I got the following "unicodedecodeerror" in "save_model.py". Has anyone solved a similar problem?

I fulfilled all the requirements except for tensorflow==2.3.0rc0 I read the rc0 part means this version is a prerelease which doesn't exist anymore. I should download tensorflow==2.3.0. I did download...

It seems tensorRT is a flag, but it's not implemented right? `flags.DEFINE_string('framework', 'tf', '(tf, tflite, trt')` There's no logic for trt.

I'm running this DeepSORT implementation on Google Colab and the runtime is about 0.4-0.5fps. I'm connected to a GPU but it seems like only the CPU is working. I've tried...

I changed .cfg file for small objects like here: https://github.com/AlexeyAB/darknet#how-to-improve-object-detection and when I run `python save_model.py --model yolov4` , I got this error: File "/content/yolov4-deepsort/core/utils.py", line 63, in load_weights conv_weights...

Hi, When I run the object_tracker.py file, I get the output video correctly, but I can only visualize some bounding boxes. For example, in the first frames, it counts 13...