-
-
您好！当我更换主干网络为AlexNet时，对应输出为[256,6,6]和[256,18,18]，预训练模型alexnet-bn从你们之前工作SiamCAR下载的，但是总是在计算loss时报错，请问更换主干网络有什么需要注意的地方吗？谢谢
-
我在执行数据预处理裁剪的时候，得到了crop511文件，但下面都是空的文件夹，没有裁剪后的图片，但是JSON文件能正常获得，终端也没有保存，请问这是什么情况？应该怎么解决？在好几个数据集上试了都是这样的结果，很迷惑
-
请问一下作者论文3.3节中提到的freeze $v^{iou}_j$在代码的什么位置？
-
hello, i want to ask whether your training code will release? I want to study your training code, thank you for your answer
-
hi @AlexeyAB,
I tried to integrate deep sort tracker (https://github.com/Qidian213/deep_sort_yolov3) in the darknet_video.py. But deep sort works on different image format and YOLO works on differe…
-
Hi! Thank you for this amazing repository. I want to build my own backbone and integrate it into rpt, what are the necessary steps and can you please list all the files and directories where I will ne…
-
Hi,
I am running the demo.py on a Jetson Xavier NX and only getting ~4FPS.
I have verified it is running on the GPU.
I expected to get much higher frame rates - is this attainable on the devi…
-
Add multi-object tracker (dynamic array of single object trackers):
* SORT-tracker: `cv::KalmanFilter` + Hungarian algorithm https://en.wikipedia.org/wiki/Hungarian_algorithm and https://arxiv.org…
-
When I ran Dasiamese+DeepMask,I met a problem that shows:
File "tools/dasiamrpn_deepmask.py", line 1, in
from tracker.net import SiamRPNvot
ImportError: No module named 'tracker'
How can I …