double-zh / bytetrack Goto Github PK
View Code? Open in Web Editor NEWByteTrack超详细教程!!!---训练自己的数据集(VOC格式)&&摄像头实时检测跟踪
License: MIT License
ByteTrack超详细教程!!!---训练自己的数据集(VOC格式)&&摄像头实时检测跟踪
License: MIT License
666
LINK : fatal error LNK1181: 无法打开输入文件“D:\python file\ByteTrack-main\build\temp.win-amd64-3.10\Release\python file\ByteTrack-main\yolox\layers\csrc\cocoeval\cocoeval.obj”
error: command 'C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.25.28610\bin\HostX86\x64\link.exe' failed with exit code 1181
您好,我在执行setup.py的时候发现如上报错,发现cocoeval中没有这个文件,请问应该怎么办呢?
Hi, I have encountered the problem that how to create exp file for my datasets and where should the exp file placed?
2022-01-10 19:34:54 | INFO | yolox.core.trainer:242 - epoch: 1/300, iter: 1180/10261, mem: 9596Mb, iter_time: 0.865s, data_time: 0.706s, total_loss: 4.293, iou_loss: 1.822, l1_loss: 0.000, conf_loss: 1.585, cls_loss: 0.887, lr: 1.653e-05, size: 576, ETA: 34 days, 20:27:26
2022-01-10 19:34:54 | INFO | yolox.core.trainer:242 - epoch: 1/300, iter: 1180/10261, mem: 9596Mb, iter_time: 0.865s, data_time: 0.706s, total_loss: 4.293, iou_loss: 1.822, l1_loss: 0.000, conf_loss: 1.585, cls_loss: 0.887, lr: 1.653e-05, size: 576, ETA: 34 days, 20:27:26
When I tried to run the code, that i recived from the YOLOX-JSON Annotaion Format, i got the best_ckpt.pth file. Then, I added into the bytetrack. Although it does not show any error code and stops at 0 fps. Then, I do not know what to do. Could you please take a look ?
2021-11-15 15:09:45.537 | INFO | main:imageflow_demo:250 - Processing frame 0 (100000.00 fps)
训练一直为为0,
2022-05-10 13:10:34.235 | INFO | main:main:316 - Model Summary: Params: 8.97M, Gflops: 26.81
2022-05-10 13:10:34.416 | INFO | main:main:327 - loading checkpoint
2022-05-10 13:10:34.551 | INFO | main:main:331 - loaded checkpoint done.
2022-05-10 13:10:34.551 | INFO | main:main:334 - \tFusing model...
D:\Anaconda\envs\bytetrack\lib\site-packages\torch_tensor.py:1104: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at C:\cb\pytorch_1000000000000\work\build\aten\src\ATen/core/TensorBody.h:475.)
return self._grad
2022-05-10 13:10:36.218 | INFO | main:imageflow_demo:242 - video save_path is F:\ByteTrackbieren\videos\palace.mp4
2022-05-10 13:10:36.221 | INFO | main:imageflow_demo:252 - Processing frame 0 (100000.00 fps)
2022-05-10 13:10:37.903 | INFO | main:imageflow_demo:252 - Processing frame 1 (0.62 fps)
I would like some clarification regarding the custom dataset format.
When you say annotations, what is the format for each file? Could you please let me know?
Also, could you give me an idea for an annotation tool to label my data in this particular format?
A link to a sample custom dataset would be really helpful.
Thank you for your time!
Thank you for your great work. Could you please help me that I found two problems when running YOLOX_tiny and Byte for tracking. One is that if a target is blocked by a large area, its id will change; the other is that for the same target, just after only disappearing for 10 frames, it is detected that the id of the target will change. How to optimize this situation?
I traning with my dataset but loss_l1 are 0 in training process. Do i compile wrong ?
2022-01-10 19:17:14 | INFO | yolox.core.trainer:242 - epoch: 1/300, iter: 100/10261, mem: 9596Mb, iter_time: 0.802s, data_time: 0.601s, total_loss: 9.537, iou_loss: 2.258, l1_loss: 0.000, conf_loss: 4.065, cls_loss: 3.214, lr: 1.187e-07, size: 448, ETA: 34 days, 0:58:14
想问下按照博主您的方式进行训练,一张3090ti使用yolox-m的模型在batchsize为1时为什么显存在6000-19000来回横跳,使用bs=2时,显存就会溢出
读取视频进行预测的过程中没有看到关于类别的输出,只有跟踪的id,该如何把检测类别,分数同时cv2.puttext到视频中展示,谢谢。
Traceback (most recent call last):
File "train.py", line 10, in
from yolox.core import Trainer, launch
File "D:\github_rar\ByteTrack_zz\yolox_init_.py", line 4, in
from .utils import configure_module
File "D:\github_rar\ByteTrack_zz\yolox\utils_init_.py", line 15, in
from .setup_env import *
File "D:\github_rar\ByteTrack_zz\yolox\utils\setup_env.py", line 5, in
sys.path.remove('/opt/ros/kinetic/lib/python2.7/dist-packages')
ValueError: list.remove(x): x not in list
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.