Comments (4)
I have the same issue with my custom dataset!
I thought either the model was not proper for my custom datasets or I have not found the proper hyperparameters yet which causes sticking in a local minima! However, it is interesting that you have the same issue on your custom dataset.
@thangvubk Could you please possibly give an insight about it?
from softgroup.
Thank you for your work and sharing. I encountered an issue while training my own dataset. as shown in the figure. May I ask what could be the reason for this situation? I look forward to your response.
from softgroup.
您好:感谢您的工作和分享。我在训练自己的数据集时遇到了一个问题。我按照 S3DIS 数据集的示例构建了自己的数据集,该数据集包括两个语义类:stem 和 leaf。在训练第一个纪元和第 100 个纪元时,叶实例的精度评估保持不变。在这100个纪元中,叶实例的精度没有变化,而茎实例的精度略有变化,如图所示。请问造成这种情况的原因是什么?我期待着你的答复。
Hello, I'm glad to hear that our research directions are similar. I would be happy to exchange ideas and collaborate with you. Please feel free to provide me with your contact information, and I will be in touch. I look forward to our future discussions.
from softgroup.
Hello: Thank you for your work and sharing. I encountered an issue while training my own dataset. I constructed my own dataset following the example of the S3DIS dataset., which includes two semantic classes: stem and leaf. When training for the first epoch and the 100th epoch, the accuracy evaluation of leaf instance remains the same. There is no change in the accuracy of leaf instance throughout these 100 epochs, while there is slight variation in the accuracy of stem instance, as shown in the figure. May I ask what could be the reason for this situation? I look forward to your response.
@buggogogo : Hello, I was wondering if you were able to find the source of error for the accuracy issue?
I have the same issue and appreciate sharing your experience; Thanks
from softgroup.
Related Issues (20)
- Inference without label
- How do I run this network with my own data?
- Volume of instances
- Model reproducibility
- BatchNorm not training
- Understanding the how the visualization process works on instance segmentation
- import error can not import ops from module softgroupe.ops HOT 1
- cannot find the pretrained model:softgroup_s3dis_spconv2.pth HOT 1
- i dont know how to kill a hanging progress HOT 2
- about late devoxelization HOT 1
- AssertionError: Empty dataset HOT 1
- Did anyone succeed in training custom data? HOT 4
- TypeError: expected string or bytes-like object
- No instant_pred results for scans_test split (not val and without label) dataset ? HOT 1
- (mistakenly opened this issue - ignore)
- Is the available model now SoftGroup++ or SoftGroup?
- 自定义数据集出错 HOT 1
- validation failed : absence of pred_instances and gt_instances HOT 1
- training on S3DIS from scratch
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 softgroup.