Comments (4)
Me too, I also trained the example/multitask/train.py
, aka mobilenetv2+MTLWRefineNet without any change.
Finally, I get the mIOU=0.27, RMSE=0.72 with 1000epoch.
It didn't achieve the paper-claimed performance.
Anyone knows why?
from densetorch.
HI,
I am trying to follow your instruction to match the result of the paper usubg NYU dataset. But the mIOU and RMSE are still can not be the same. They get stable after 300 iterations and stop at 25% and 0.7. Is there anything I missed or lost in the instructions? Thanks!
Best
Kuo
Have you achieved the multi-taskes by these codes?
from densetorch.
HI,
I am trying to follow your instruction to match the result of the paper usubg NYU dataset. But the mIOU and RMSE are still can not be the same. They get stable after 300 iterations and stop at 25% and 0.7. Is there anything I missed or lost in the instructions? Thanks!
Best
KuoHave you achieved the multi-taskes by these codes?
To run multi-tasks is no doubt.
However, I can't fully reproduce the training procedure mentioned in the paper to get the claimed performance.
Interesting thing is that the provided model can reach the claimed performance of the pape.
from densetorch.
See the following script for multi-task training with MobileNet-v2 and Multi-Task Light-Weight RefineNet: https://github.com/DrSleep/DenseTorch/blob/dev/examples/scripts/segm-depth-normals-mbv2-rflw.sh
Without changes, it should reach ~37% mean iou, 0.60 RMSE and 24 mean angular error. To achieve higher numbers, as described in the paper, you have to use the Raw NYUD dataset with knowledge distillation on missing segmentation labels -- this is not provided by this repository.
from densetorch.
Related Issues (15)
- Python version HOT 1
- Predicted depth maps aren't as expected. HOT 5
- visualize and unsupervised loss HOT 1
- ModuleNotFoundError: No module named 'densetorch.engine.miou'
- How do I get segmentation map and depth of field map with model (. Tar)
- Missing Keys in state_dict ; Unexpected keys in state_dict HOT 2
- What return and combine layers for single head models?
- numpy in setup.py HOT 1
- Download the NYUDv2 dataset with segmentation and depth masks HOT 3
- Data link is broken HOT 1
- Training with my own dataset HOT 1
- RuntimeError: cuda runtime error (59) : device-side assert triggered at /pytorch/aten/src/THC/THCReduceAll.cuh:327 HOT 2
- Run pip install -e. An error occurred, please help me HOT 2
- Evaluation scripts of multi-task tight-weight refineNet. HOT 4
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 densetorch.