deep_sort_yolov3
deep_sort_yolov3 copied to clipboard
Real-time Multi-person tracker using YOLO v3 and deep_sort with tensorflow
请问,我通过[YunYang1994/tensorflow-yolov3](https://github.com/YunYang1994/tensorflow-yolov3)生成了yolo3的模型,但格式是.ckpt或者.pb文件, 所以在Quick Start的第1步我就卡住了,如何将我自己的.ckpt或者.pb文件模型文件转换成.weights文件→.h5文件呢?  
In demo.py we can subsitude lines 71 and 72: `boxs = yolo.detect_image(image)[0] confidence = yolo.detect_image(image)[1]` for: `boxs,confidence = yolo.detect_image(image)` to double the efficiency of the execution.
你好,我想用这个工程测试一下我自己训练好的模型加入Deep-sort后的效果,但是我的类别并不像coco数据集那样多。我的模型已经转换成功了,并且我已经修改了coco.classes.txt文件为我的类别。但是还是出现了以下问题: Traceback (most recent call last): File "demo.py", line 113, in main(YOLO()) File "C:\Users\admin\Desktop\deep_sort_yolov3\yolo.py", line 33, in __init__ self.boxes, self.scores, self.classes = self.generate() File "C:\Users\admin\Desktop\deep_sort_yolov3\yolo.py", line 72, in generate score_threshold=self.score,...
flow
同步
作者你好,我用你的程序做目标跟踪,对象不是人,是一个别的物体。我按照官方重新训练了特征模型.pb文件和yolo模型,精度和Loss都很好,yolo检测很好。我试着用了mars-small128.pb 和自己训练获得的模型,效果完全一样,但是mars-small128.pb 是针对人的,我是别的目标。这就让我感觉完全没有用上特征匹配,请问这个什么问题呢,是不是有什么参数要调整?
Using TensorFlow backend. C:\Users\Administrator\AppData\Local\Programs\Python\Python37\lib\site-packages\sklearn\utils\linear_assignment_.py:21: DeprecationWarning: The linear_assignment_ module is deprecated in 0.21 and will be removed from 0.23. Use scipy.optimize.linear_sum_assignment instead. DeprecationWarning) WARNING: Logging before flag parsing goes to stderr....
Hi When I use: python convert.py yolo-obj.cfg yolo-obj_final.weights model_data/yolo.h5 I have this error: `Traceback (most recent call last): File "convert.py", line 266, in _main(parser.parse_args()) File "convert.py", line 239, in _main...
Where is the "videocaptureasync" module? I tried "demo.py", but it cannot find the module. Thank you. Using TensorFlow backend. Traceback (most recent call last): File "demo.py", line 19, in from...
你好,我在进行demo测试的时候,结果只能达到2点几帧,完全无法满足实时性的要求,我的电脑是1070的显卡,是因为测试视频的分辨率的原因吗,我用的测试的视频的分辨率也不是很高啊  