Comments (3)
Hi, can you provide more details?
from hdml.
In main_triplet.py, is there any reason to pass the anchors and positives to the generator?
I think it is sufficient to pass the negatives only to the generator so I believe it is necessary to extract negatives from the variable 'embedding_yq'.
In addition, even though there are some reasons to pass anchors/positives to the generator, the variable 'embedding_z_quta' should be edited to include positives and anchors from the variable 'embedding_z' and negatives from the variable 'embedding_z_quta' when the variable 'J_syn' is formed.
If there is an error in my understanding, please correct me.
By the way, thank you for your amazing work!
from hdml.
For evaluation, line 196-197 in main_triplet.py "nmi_te, f1_te, recalls_te = evaluation.Evaluation(stream_test, image_mean, sess, x_raw, label_raw, is_Training, embedding_z, 98, neighbours)" should be corrected as "nmi_te, f1_te, recalls_te = evaluation.Evaluation(stream_test, image_mean, sess, x_raw, label_raw, is_Training, embedding_z, 100, neighbours)".
Is that right?
Thank you again.
from hdml.
Related Issues (16)
- code problem HOT 2
- Inferences HOT 2
- running on gpu
- [Maths] Symbol in the paper? HOT 7
- code problem HOT 1
- Code gives better results than that mentioned in the paper HOT 8
- How to run the code for the triplet loss? HOT 2
- What about the way of loading data in tfrecord? HOT 1
- Hi What does this step mean? HOT 1
- Error loading data? HOT 1
- Error for products dataset
- some questions about train and evaluate my own dataset HOT 4
- Configuration on SOP dataset HOT 2
- the question about evaluate.py HOT 1
- Embedding Normalization for Triplet Loss
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 hdml.