Comments (4)
srivatsan88
commented on May 13, 2024
Easiest way @KaichiehKJ is to convert image data to csv file and the instead of spec as constants.DEFAULT_DNN use constants.DEFAULT_CNN. But record defaults might kill you. Another option is to inherit the abstract class ( model_search.data.Provider) and build your own data provider along with CNN spec. At the end there is no straight forward way. Sorry :(
from model_search.
magedhelmy1
commented on May 13, 2024
@srivatsan88 can you please submit a short script/tutorial on your comment? It will be appreciated :)
@hanna-maz Is there future plans to implement this in a straight forward way?
from model_search.
hanna-maz
commented on May 13, 2024
The current way to run on images is to create your own "data.Provider" class as explained in the readme.md
Wrapping tf.keras.preprocessing.image_dataset_from_directory should be the simplest solution.
We might be able to prioritize creating full code for a running example soon. Thanks for your patience.
from model_search.
hanna-maz
commented on May 13, 2024
New version (today) added simple apis for loading an image dataset.
Readme.md was updated with further instructions.
from model_search.
Related Issues (20)
- How to Train a model with 2 dimensional dataset , ie. sentence with wordVec
- RuntimeError: Error when executing query: file is not a database query
- Could it search for models that use time series such as RNN HOT 5
- Evaluating Model Search Results HOT 7
- Model Architecture Output? HOT 2
- Is there anyway we can use model_search for object detection also ?
- Is it feasible to use MirroredStrategy for training?
- I'm confused by distributed search, any suggestions are welcomed!
- RuntimeError: Cannot connect sqlite3 database: unable to open database file HOT 2
- Neural Network Architecture Details HOT 3
- Documentation for Utilizing Output of Model Search?
- Possible beta for Regression Modeling? HOT 1
- Training on Multiclass Image Dataset HOT 1
- How to predict from model_search saved_model.pb HOT 3
- How to know which model is the best and what is its accuracy? HOT 4
- AttributeError: module 'ml_metadata.metadata_store' has no attribute 'MetadataStore' HOT 1
- UnicodedecodeErroe HOT 1
- sqlite default filename is not Windows compatible
- AttributeError: 'Tensor' object has no attribute 'numpy'
- Project dependencies may have API risk issues
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 model_search.