ninghongbo123

I have the question as same as you meet? Have you found out this reasons?

You guys need to modify type(input) as input.type() in roi_pooling.py, line 18 ,then it works. This error caused by api changes of different pytorch version

@Vinlic 感谢你提供的stream api方案。我这边的测试发现，server端报这个错（见下边server端报错情况），但不影响程序的运行。client 端用requests是报这个错：requests.exceptions.ChunkedEncodingError: ('Connection broken: IncompleteRead(0 bytes read)', IncompleteRead(0 bytes read))。不知道你这边有遇到过吗？ server端报错：RuntimeError: CUDA error: invalid device ordinal CUDA kernel errors might be asynchronously reported at some other API call,so...

yes，I have the same problem as you. And I guess that it will work better if modifying some hyper parameters ,but firstly it is necessary to have a comprehensive understanding...

I had modified these parameter or operating logic : 1.threshold-replace 0.2 by 0.25 2.average the top five features of the track as final distance OR average the top 3rd to...

In nn_matching.py file, modifying corresponding code as below: distances.sort(axis=0) # sorted firstly return distances[2:5].mean(axis=0) #average 2-5 features @ss199302

Any modification you made depends on your application. You need to evaluate it after you have modified some parameters . I think these two parameters are irrelevant . The max...

@hongsamvo hello ! the performance of detector has a important impact on final result of tracking , so it's better to improve the capabilityof detector as soon as possible ....

mark

请问，这种多线程调用同一个模型，能不能实现异步效果？ 因为我测试了一下，感觉所有请求还是在排队处理，前一个完全处理完，才处理下一个。 还望解答。