Comments (3)
- Firstly, the mask_size has no relation with the number of classes. The mask size is the size of our mask regression output (A inner product layer with num_output = MASK_SIZE x MASK_SIZE) in stage 2/4.
2)&3) You also need to notice that the test_iter = 8 in my solver.prototxt. So every iteration consists 8 forward/backward operations. But it's still seems too slow for your experiments, what's your hardward configuration? And for the number of training iters, I believe you should try which is the best training iters by hand.
-
The accuracy will be highly affected by the number of background samples per batch, since background is much easier to be correctly classified. In your case, it seems there are too many background samples which results no instances are detected while the accuracy is very high.
-
Could you give more information about this issue? I didn't fully understand your description.
from mnc.
Hi @suhalim9, have you solved your problem, seems like we have similar problem. I also want to train MNC using my own dataset and the dataset only has one type of object. If you have solved your problem, could you share some experience please?
from mnc.
Hi @wuzheng-sjtu ,
To be honest, I ended up letting it trained slowly. My training images are pretty high resolutions so definitely took way longer than expected. I used the default iteration number but stopped at ~20000 iterations (after several days) because loss became -inf. I took the latest one that loss stayed normal (I don't remember the exact iteration number).
But I still have a problem with the accuracy. My object type is very simple without not many visible features (not like face, animal, etc.) So I wondered if my issue was because of the nature of the object.
In summary, I didn't see much success with the MNC model for the object I wanted to detect. But having more iterations helped a bit. I also used the 5 stage, which seemed slightly better than the 3 stage. I don't think my experience would help you..
If you have a success story, please share. :)
from mnc.
Related Issues (20)
- image size my own data HOT 4
- MNC performance with NVidia Pascal architecture
- caffe-MNC compile error with cuda 8 and both cudnn 5.1.10 and 6.0.21 HOT 2
- Keras version of MNC HOT 3
- Is it possible to train an unmodified version on MNC with a different dataset? HOT 2
- Creating SBD dataset from polygon information
- cpu_mask_voting v.s. gpu_mask_voting HOT 1
- Onedrive Download Error
- The issue of speed
- trained
- What is the purpose of MIX_INDEX
- Caffe compilation issues (CUDNNv5)
- caffe-mnc folder is empty HOT 1
- Error in demo HOT 1
- compile lib in windows
- How can the inference process use 5 stage when the cascade structures are for training 3 stages?
- download the trained MNC model failed
- pretrained resnet101 mnc model download
- Is there interest in Dockerizing the MNC code? HOT 2
- Will the code for BoxSup be released?
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 mnc.