Comments (2)
Dear sir, in train.prototxt about line 1670, there are three bottom input:
name: "flow_loss1"
type: "L1Loss"
#bottom: "predict_flow1"
bottom: "blob66"
bottom: "blob65"
bottom: "blob65Confidence"
top: "flow_loss1"
loss_weight: 1
l1_loss_param {
l2_per_location: false
normalize_by_num_entries: true
}
}
When bottom: "blob65" was commented, the error about MaxBottomBlobs() >= bottom.size() (2 vs. 3) L1Loss Layer takes at most 2 bottom blob(s) as input. #6
is solved.
name: "flow_loss1"
type: "L1Loss"
#bottom: "predict_flow1"
bottom: "blob66"
#bottom: "blob65"
bottom: "blob65Confidence"
top: "flow_loss1"
loss_weight: 1
l1_loss_param {
l2_per_location: false
normalize_by_num_entries: true
}
}
Can you give me some suggestion about how to change flow_loss1 layer? Thanks.
from unsupervised-adaptation-for-deep-stereo.
Are you sure to be using our implementation of L1Loss layer? One of the difference between our code and the original flownet one is indeed the number of bottom blob allowed.
from unsupervised-adaptation-for-deep-stereo.
Related Issues (11)
- The source of training and test HOT 2
- Inference results from tensorflow version
- Inference results from tensorflow version HOT 3
- How to increase the variety of training set HOT 3
- Pretrained model HOT 2
- src/caffe/layers/l1loss_layer.cpp:28:5: error: ‘diff_bottom_vec_’ was not declared in this scope HOT 2
- input and filter must have the same depth: 3 vs 1 HOT 2
- The model is not convergent. HOT 1
- A question about paper, thanks your help. HOT 2
- the link to tensorflow version "dispflownet-tf" is unsupervised? HOT 3
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 unsupervised-adaptation-for-deep-stereo.