Comments (2)
the network configuration and loss function worked for my problem statement that doesn't necessarily mean it should work for any type of problem statement. Try with bigger network but loss function won't change as it is a multi label classification matrix and try with different optimization technique and you can add your own evaluation metric while tranining.
for your reference:
https://keras.io/metrics/
from keras-multi-label-image-classification.
I use the vgg16 network to retrain my data, I found that the complete result for test data is zero,
from keras-multi-label-image-classification.
Related Issues (18)
- You should use binary_accuracy instead of accuracy
- Getting 404 for https://suraj-deshmukh.github.io/Multi-Label-Image-Classification/ HOT 1
- what does best_threshold mean๏ผ HOT 1
- test issue HOT 1
- How to solve the problem that topK's K is different for every input text? HOT 1
- Dataset link HOT 1
- InvalidArgumentError: Default MaxPoolingOp only supports NHWC on device type CPU HOT 1
- how to reproduce the evaluation results
- link to dataset is broken
- what is your tensorflow version?
- Can't use model.predict_proba in function API
- loss function may be not right HOT 2
- Classify an Image independently HOT 7
- How to use the costomised data to train the model? HOT 6
- error occurred when I run the miml.ipnb HOT 1
- weight file HOT 1
- hello,you did excellent work,i studied your project of Multi-Label-Image-Classification,and i got some problem of the part process data,can you share me the code of processing data?Ths! HOT 12
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from keras-multi-label-image-classification.