Comments (9)
@HsiaX Hi, thanks for your interest.
This is built on Detectron2, the training command is also similar to that. For example, python train_net.py --num-gpus 2 --config-file configs/Dance_R_50_3x.yaml
.
I did not use mobilenet/vovnet in the final models; I just used them in some experiments during quite early stages.
The panopticapi
can be found here: https://github.com/cocodataset/panopticapi.
from dance.
@HsiaX Hi, thanks for your interest.
This is built on Detectron2, the training command is also similar to that. For example,
python train_net.py --num-gpus 2 --config-file configs/Dance_R_50_3x.yaml
.I did not use mobilenet/vovnet in the final models; I just used them in some experiments during quite early stages.
The
panopticapi
can be found here: https://github.com/cocodataset/panopticapi.
OK, I got it. Thanks so much for your reply! :-)
By the way, now I have generated the edge file (use the Cityscapes from Deep Snake), but they seems almost black. Is this normal?
from dance.
Unfortunately, now I meet the following error info during training:
Is it means that the edge_gt is empty? I got the edge file like this, what happened? (T_T)
from dance.
Hi @HsiaX , the edge map should contain values 0/1, so nearly not visible by human eyes. If you load it into notebook and multiply by 255 and check, it should be correct.
From the log I guess it's something related to the dataloader.
I mainly used this repo's code for COCO training, and did not encounter such issues. If you want to do experiments on cityscape, I have some codes based on DeepSnake repo and changed it into our method, maybe you want to take a look?
from dance.
Hi @HsiaX , the edge map should contain values 0/1, so nearly not visible by human eyes. If you load it into notebook and multiply by 255 and check, it should be correct.
From the log I guess it's something related to the dataloader.
I mainly used this repo's code for COCO training, and did not encounter such issues. If you want to do experiments on cityscape, I have some codes based on DeepSnake repo and changed it into our method, maybe you want to take a look?
Yes you're right, the edge map is correct.
Oh if you can provide that, that's soooooo great !
And, I found that the error occurs because in training set, there are some images without objects, so the edge is empty. Maybe I need to think about how to modify the code to deal with it.
from dance.
Hi @HsiaX , the edge map should contain values 0/1, so nearly not visible by human eyes. If you load it into notebook and multiply by 255 and check, it should be correct.
From the log I guess it's something related to the dataloader.
I mainly used this repo's code for COCO training, and did not encounter such issues. If you want to do experiments on cityscape, I have some codes based on DeepSnake repo and changed it into our method, maybe you want to take a look?Yes you're right, the edge map is correct.
Oh if you can provide that, that's soooooo great !And, I found that the error occurs because in training set, there are some images without objects, so the edge is empty. Maybe I need to think about how to modify the code to deal with it.
Yes, definitely need to align the image with its correct annotation for training. Can provide your email so that I can send the zipped code to you?
from dance.
Hi @HsiaX , the edge map should contain values 0/1, so nearly not visible by human eyes. If you load it into notebook and multiply by 255 and check, it should be correct.
From the log I guess it's something related to the dataloader.
I mainly used this repo's code for COCO training, and did not encounter such issues. If you want to do experiments on cityscape, I have some codes based on DeepSnake repo and changed it into our method, maybe you want to take a look?Yes you're right, the edge map is correct.
Oh if you can provide that, that's soooooo great !
And, I found that the error occurs because in training set, there are some images without objects, so the edge is empty. Maybe I need to think about how to modify the code to deal with it.Yes, definitely need to align the image with its correct annotation for training. Can provide your email so that I can send the zipped code to you?
OK,my email is: [email protected]
Thank you!
from dance.
Hi~ Sorry to bother you again. For these day's struggle, I wonder if there are some filter strategies during generating edge targets? When I was training, it would report that the edge_target is empty,then I filter the edge maps (some images has too small objects to generate edges, so I remove them from annos). But it doesn't work.
For example:
It can be seen that the image has edges in initial edge map, but in snake_head.py, it report that the "init_ex_targets" is empty. So I want to know are there any filter strategies in edge_target generating?
from dance.
Hi @HsiaX , there should be no filtering process inside prepare_edge_map_cityscapes.py
, the code just extracts the segmentation annotation and draws the contours to get edge_map.
As you said, the training example has edge map, so the edge map annotation is correct; but you mentioned the error is init_ex_targets
is empty, I guess the problem may be your polygon annotation is not in clockwise/counter-clockwise order so that it cannot sample the target points?
BTW, if you are training on Cityscape, I would suggest you use the snake
branch (same as the code I email you), which is based on DeepSnake codebase and the code is cleaner. :)
Feel free to ask if you got further questions, or you can email me your wechat if you want and discuss there.
from dance.
Related Issues (20)
- please help!AssertionError: Attribute 'thing_classes' in the metadata of 'coco_2017_train_edge' cannot be set to a different value! HOT 10
- There have been a problem when I used the prepare_edge_map.py, it prompted that the corresponding picture is missing HOT 1
- About code on coco HOT 2
- Error when running baseline snake HOT 17
- how to train the model with own datasets ? HOT 1
- How can I visualize the prediction of a single image?
- How to get edge_map of SBD? HOT 1
- How to visualize the prediction HOT 4
- 您好,我看了下基于deepsnake的dance模型,在配置文件看来,好像不需要学习预测目标中心点的偏移量? HOT 3
- mmdet version? HOT 1
- Pre-train model with CenterNet Detector HOT 1
- Config of model HOT 2
- the results of Dance HOT 4
- DANCE network in the snake baranch uses COCO dataset to train
- prepare_edge_map_cityscapes.py有着可能的bug
- Face an error when running author's code HOT 3
- RuntimeError: stack expects a non-empty TensorList HOT 6
- Can I have a simple training on a graphics card? HOT 1
- how can i use this code on window paltform? HOT 1
- Config file (.yaml) of the basic DsnakeHead. HOT 1
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 dance.