Comments (11)
@twmht, score / 10 = score * 0.1, we just use reciprocal of T.
from person_search.
@twmht, my bad, I mean score / 0.1 = score * 10. The temperature T is 0.1, we use its reciprocal for simpler implementation.
from person_search.
IMS_PER_BATCH is how many whole scene images inside each mini-batch. It is fixed as 1 in our project.
BATCH_SIZE is how many pedestrian proposals, or region of interests (RoIs) equivalently, in each mini-batch.
from person_search.
I see.
Does the BATCH_SIZE related to the number of labeled identities inside the Lookup Table?
from person_search.
No. The total number of labeled identities is 5532. BATCH_SIZE is how many bounding boxes proposed by the pedestrian proposal network.
from person_search.
Did you mean the number of labeled identities inside the Lookup Table always fixed at 5532 throughout the training process?
I feel confused, what is the difference between RPN_BATCHSIZE and BATCH_SIZE?
from person_search.
@tankienleong Yes, the size of the Lookup Table is fixed at 5532 during training.
Our framework is based on Faster-RCNN, which can be thought of as a cascaded detector. The first stage regresses an anchor to a proposal, the second stage further refines and classifies the proposal. RPN_BATCHSIZE
is used for the first stage while BATCH_SIZE
is for the second stage.
from person_search.
Hi @Cysu May I know which part of the code define the value of temperature T for both of the equation 1 and equation 2 in your paper "Joint Detection and Identification Feature Learning for Person Search"? I had read the code in softmax_loss_layer.cpp & softmax_loss_layer.cu but fail to figured out what is the value of T.
from person_search.
@tankienleong It's actually implemented by using the Power layer in prototxt, see here.
from person_search.
in the paper, the temperature scalar T is set to 0.1, why you set T to 10 in the prototxt?
from person_search.
I have looked at labeled_matching_layer
, this only implements cosine similarity.
and the succeeding power layer multiples the similarity score by 10, not divided by 10.
see caffe (http://caffe.berkeleyvision.org/tutorial/layers/power.html)
from person_search.
Related Issues (20)
- target_blobs.size() == source_layer.blobs_size() (1 vs. 0) Incompatible number of blobs for layer feat
- Rewrite batch question
- demo.py error HOT 2
- Error in demo --gpu 0
- about train model download
- About the log file of oim loss
- about dataset
- Caffe Installation Issue on GPU GTX 1050 Ubuntu 18.04 HOT 2
- CUHK-SYSU Person Search Dataset HOT 1
- Can I use standard caffe for inference only? HOT 1
- If you have problems when compiling, please see here
- About the Datase
- About the Dataset HOT 2
- Please help !!! problems running the demo HOT 1
- Implementation bug about unlabeled_matching_layer?
- A good pytorch implementation is available now.
- cuda 8.0 and cudnn v5.1
- 折线图 HOT 1
- how to get cuhk02 03 and sysu
- CMake error
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 person_search.