Comments (7)
Thanks for your interest in our work!
We're aware of the bugs, and we're working on a patch to release soon.
In terms of the content on the paper, this should have been explained better but in the forward pass too we approximate argmax with gumbel softmax.
from gscnn.
Thanks for sharing this code and the excellent work!
I am still having questions:
How to approximate argmax with gumbel softmax? The output of the argmax should be one channel with pixels taking values of the labels. However, the gumbel softmax in the released code has 19 channels. There seems a soft argmax ops missing. My question is that is eq.(5) computed over boundary map (output of eq. (4)) with shape (H, W,,1) or with shape (H, W, 19)? In the paper, it says (H, W, 1), but in the code, it is (H, W, 19).
Thanks!
from gscnn.
Have u done the training process successfully now? In fact I meet problem when I try evaluating it...the codes stuck when import encoding and did not return any error message...
from gscnn.
Have u done the training process successfully now? In fact I meet problem when I try evaluating it...the codes stuck when import encoding and did not return any error message...
I can train it but have not reproduced the results yet. It took four GPUs to train and I do not have so many GPUs yet.
from gscnn.
Have u done the training process successfully now? In fact I meet problem when I try evaluating it...the codes stuck when import encoding and did not return any error message...
I can train it but have not reproduced the results yet. It took four GPUs to train and I do not have so many GPUs yet.
Would you mind giving me the version of libs you used? I met problem when running import encoding... thx sooooo much!
from gscnn.
No I didn't reproduce the results using this code.
from gscnn.
from gscnn.
Related Issues (20)
- How to use the argument 'trunk' and the backbone 'resnet18'?
- DualTaskLoss not working HOT 4
- ede
- Change the picture test method
- from network.wider_resnet import wider_resnet38_a2 HOT 3
- Error in DualTaskLoss while running the evaluation HOT 1
- TypeError: resolve_type_from_object()
- gate about reset
- Typo in gradient_central_diff in custom_functional.py
- How to test with single image?
- the computer crashed und rebooted after training for a while HOT 1
- result is not very good HOT 2
- ValueError: batch_size should be a positive integer value, but got batch_size=0
- Segment single image using saved model HOT 4
- ImportError: No module named 'enclib_cpu'
- ModuleNotFoundError: No module named 'encoding' HOT 2
- このコードの構造は本当に改善する必要があります
- 07-07 16:49:07.175 NaN or Inf found in input tensor.
- Question about Dual Task Loss notation in the paper
- THCudaCheck FAIL file=/pytorch/aten/src/THC/THCGeneral.cpp line=383 error=8 : invalid device function
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 gscnn.