Comments (3)
Hi,
You can train Inception v3 to recognise classes not in ImageNet. You can train any pre trained network to recognise other classes.
1.Bottom conv blocks will act as general feature extractors. ( Frozen )
2.Upper Conv Blocks -- > Retrained with your dataset ( Unfrozen : Fine tuned to your dataset )
3.Fully connected layer --> Trained with your dataset.
You can just plug the same code as it is.
from deeplearningsandbox.
Thanks, I know I can train Inception v3 to recognise classes not in ImageNet.
My question was to make a model that recognizes classes in ImageNet and EVEN my own classes.
Basically I want to extend Inception v3 to recognize not only 1000 classes from ImageNet, even my 2 other classes. So in total it should recognizes 1002 classes.
from deeplearningsandbox.
from deeplearningsandbox.
Related Issues (5)
- predict throw error: ValueError: incompatible sizes: argument 'width' must be length 2 or scalar HOT 1
- ValueError: You are passing a target array of shape (32, 1) while using as loss `categorical_crossentropy`. `categorical_crossentropy` expects targets to be binary matrices (1s and 0s) of shape (samples, classes). If your targets are integer classes, you can convert them to the expected format via: HOT 1
- model = ResNet50(weights='imagenet') / imagenet 1000 human readable terms?
- squeezenet avalable
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 deeplearningsandbox.