Comments (2)
TheRum
commented on August 27, 2024
Not sure about the Memory requirement of AutoML but this Memory error depends on your dataset size as well.
Since you are using a few thousand RGB images, it will take up a huge space and eventually may fail on VRAM/RAM in execution.
And "Batch size" is not yet configurable from the user side, so you will not be even able to trim down data flowing per batch.
I suggest to try with just a few hundred images and monitor the Memory used up!
from autokeras.
haifeng-jin
commented on August 27, 2024
Thank you for the question.
Currently, we do not support loading batch by batch.
We may implement it later.
If really in need, you can submit an issue with the feature request template for it.
Thanks.
from autokeras.
Related Issues (20)
- Feature: Model Agnostic Explanability - Permutation Importance and Counterfactual
- Bug: UnicodeDecodeError: 'utf-8' codec can't decode byte 0xd5 in position 205. in Chinese path, not in English path
- Bug: TypeError: can only concatenate str (not "NoneType") to st HOT 1
- Bug: Unable to predict data using the model trained (Node: 'model/multi_category_encoding/string_lookup_22/None_Lookup/LookupTableFindV2' Table not initialized. [[{{node model/multi_category_encoding/string_lookup_22/None_Lookup/LookupTableFindV2}}]] [Op:__inference_predict_function_10129638] )
- Bug: HOT 4
- AttributeError: module 'numpy' has no attribute 'object' when using autokeras with structured data HOT 5
- Autokers textinput text classifier does not work.
- ModuleNotFoundError: No module named 'tensorflow.keras.layers.experimental'Bug: HOT 5
- Bug: import autokeras as ak --> ModuleNotFoundError: No module named 'tensorflow.keras.layers.experimental' HOT 9
- Bug: FatalTypeError: Expected the model-building function, or HyperModel.build() to return a valid Keras Model instance
- Bug: StructuredDataClassifier and StructuredDataRegressor gone? HOT 9
- Bug: Autokeras/TF fails with CUDA_ERROR_ILLEGAL_ADDRESS/CUDA_ERROR_INVALID_HANDLE when max_trials is not 1
- Bug: "Best val_accuracy So Far" is mistaken for "Best val_loss So Far"
- Feature: 希望AutoKeras可以基于目前最新的Keras3，支持Keras3的新特性！
- Why was the TimeSeries parts of the package removed in the latest version?
- Feature:
- Bug: HOT 1
- Bug: ModuleNotFoundError: No module named 'tensorflow.keras.layers.experimental' HOT 2
- Bug: trouble loading and using tensorflow savedmodel with custom input layer in keras, has been working fine for 2+ years and now currently looking for the solutions with my team HOT 1
- module 'autokeras' has no attribute 'StructuredDataClassifier'
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 autokeras.