Comments (6)
y_s
是没有dilated convolution
的backbone
的输出, 即经典FCN
的backbone
的输出h
是通过一个CNN
(即JPU
) 建模的。具体来说,JPU
是在进行如下操作: (1)求解出一个隐式的h
, (2)使用隐式的h
来处理y_m
, 获得最后上采样后的特征图
from fastfcn.
Hi, SOTA with 3x speedup. Nice job!
Due to my limited knowledge of segmentation, I find the following descriptions hard to understand, any help?
- The caption of Figure 5:
... and the rest part of y_m
. What do you mean therest part
? - The right subfigure of Figure 5 wraps node 1,2,3 with
3x3 conv, d=1
, yet left subfigure uses node 0,2,4. Note thatdilation rate 1 focuses on y^0_m
, which corresponds to the left subfigure or the other? How to understanddilation rate 1 focuses on y^0_m
andd=2 aims at y^0_m and y_s
? - The problem defined in Eq.(1): is
a known function? If it is true, Eq.(4) with learnable
and
may be different from the pre-defined joint upsampling problem.
- As described in section 3.3.3,
Eq.(4) is an optimization problem
. What is the specific learning target in this problem?
Thanks in advance.
from fastfcn.
- As shown in
Equation 4
,y_m
can be split intoy_m^0
andy_m^1
. The rest part ofy_m
meansy_m^1
. - Both
d=1
andd=2
correspond to the right figure. The left figure shows thaty_s
only depends ony_m^0
. The inputs ofd=1
(the dotted box) arey_m^0
andy_m^1
, while the inputs ofd=2
(the solid box) arey_m^0
. f()
is a know function. As forEquation 4
,y_s = h(y_m^0)
is also a know function after the training converges.- The objective is to find a function
\hat{h}()
to approximatey_s = h(y_m^0)
.
from fastfcn.
Thanks for your responses. I still wonder the proposed solving with CNNs
indeed solves the optimization problem strictly? The stage (b) seems to optimize and
simultaneously.
from fastfcn.
JPU
does not solve the optimization problem strictly. Motivated by joint upsampling, we employ a CNN
to approximate the optimization problem.
from fastfcn.
Cool, thanks.
from fastfcn.
Related Issues (20)
- Pre-training weights HOT 1
- What do I need change in code to run CPU testing without using CUDA
- What do I need change in code to run "test" script only on CPU without using CUDA?
- I can't successfully run train script on my dataset. HOT 1
- "IndexError: list index out of range" durinng "test" and "test single image" scipt HOT 3
- Need your suggestions HOT 5
- FastFCN has been supported by MMSegmentation. HOT 9
- In order to run this on a different dataset say CamVid what changes need to be made HOT 2
- RuntimeError: Failed downloading url https://hangzh.s3.amazonaws.com/encoding/models/resnet50-ebb6acbb.zip HOT 3
- RuntimeError: => no checkpoint found at 'encnet_jpu_res50_pcontext.pth.tar' HOT 1
- Why use seperable convolutions with dilation factor? HOT 1
- Run Time error when trying to train AdeK20 dataset HOT 1
- What batch size and learning rate would you recommend training for a 24gb GPU?
- Runtime error wile downloading pretrained model
- About the PContext precision results HOT 1
- 训练时出现 raise RuntimeError("{} is a zip archive (did you mean to use torch.jit.load()?)". HOT 5
- 不能下载 HOT 2
- about syncbn HOT 3
- latest版本训练的时候卡住 HOT 1
- How could I set "resume" while running test_single_image? HOT 8
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 fastfcn.