Comments (24)
Can you please post the full error log and did you convert the video to frame images? The README includes how to do this: ffmpeg -i data/snakeboard/snakeboard.mp4 -vf fps=30 data/snakeboard/%06d.png
from trackformer.
Can you please post the full error log and did you convert the video to frame images? The README includes how to do this:
ffmpeg -i data/snakeboard/snakeboard.mp4 -vf fps=30 data/snakeboard/%06d.png
Thank you for your timely answer. I am sorry that I forget to convert it into a picture.
from trackformer.
No worries! If it works now we can close this issue?
from trackformer.
No worries! If it works now we can close this issue?
OK. Thank you again.
from trackformer.
i have convertd the video into a picture. but still get the same problem
from trackformer.
Maybe the images are in the wrong directory?
from trackformer.
I followed the instructions on the readme to split the video into images and save the images in the snakeboard folder
from trackformer.
Are your images in the DEMO
folder?
from trackformer.
from trackformer.
Image or Images? And are the snakeboard files still there? Where you able to run the snakeboard demo?
from trackformer.
As shown in the picture above, I still put the finished pictures in the sakeboard, and then directly run the README command .
Is the video divided into 131 pictures?
from trackformer.
Where you able to run the snakeboard demo?
Our code outputs individual frames not a video file.
from trackformer.
What do you mean by where it runs? It's just the left side of the readme command and waiting to click to run
from trackformer.
Sorry "Were you able ..."
from trackformer.
Let me reiterate what I did: first I split the videos in Snakeboard into images according to the prompts on the readme, which I still save in the Snakeboard folder. Then I run the track.py file according to the instructions, which are shown in the image. But there is an error like the one above.
from trackformer.
from trackformer.
In which directory are u executing this? There is some path issue that you have to figure out by going into the code and debugging.
from trackformer.
Is this error due to the path? Is it the reason why the pictures were not found?I performed the operation in the main directory of the project, which is the trackformer-mian directory。What is the reason for this error?
from trackformer.
How to detect my own dataset images and obtain corresponding visualization results?
from trackformer.
I am operating under Windows, is that why?
from trackformer.
When I don't add write_images=pretty command is used, the running result is shown in the above figure
from trackformer.
This is a path issue of some sort. A few print/debug statements in the track.py file and you will figure this out. Beyond that I can not help you.
from trackformer.
ok, i will try. thank you so much for your help
from trackformer.
May I ask how to display his ID number on the tracking box? The color of the box is used to distinguish different ID numbers
from trackformer.
Related Issues (20)
- Details of Pretrained model
- Thoughts poor performance? HOT 2
- cannot allocate memory HOT 2
- How to obtain Deformable DETR pretrained model (hidden_dim_288) HOT 2
- Issues on training custom datasets HOT 11
- Error while installing MultiScaleDeformableAttention package HOT 8
- Where can I download the pretrained model?thanks~
- Problems on running VisDrone2019 dataset
- Custom dataset: class_error: 0
- Encountered error while trying to install package lapsolver HOT 1
- Please read & provide the following HOT 2
- Loading Data for Tracking HOT 7
- Error while training custom dataset, in validation phase: HOT 3
- how to display the ID numbers HOT 1
- Problems with the MOT17 dataset when testing HOT 1
- Unknown CUDA arch (8.6) or GPU not supported HOT 1
- The MOTP metrics is showing a low score. HOT 5
- Issues related to track IDs HOT 8
- Why num_classes=20 in r50_deformable_detr_plus_iterative_bbox_refinement-checkpoint_hidden_dim_288.pth? HOT 2
- The generation of trackid
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from trackformer.