Comments (3)
@nrad,
I can see you are using tensorflow 2.13 which is little older than the latest. I tried with the tf-nightly and couldn't found any difference in the performance with tf.data.dataset.from_generator. Kindly find the gist of it here.
Performance using pd.DataFrame:
20/20 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.6222 - loss: 0.6594
Performance using tf.dataset:
/usr/local/lib/python3.10/dist-packages/keras/src/layers/normalization/batch_normalization.py:143: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.
super().__init__(**kwargs)
20/20 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6222 - loss: 0.6594
[0.6589511632919312, 0.6225550174713135]
Thank you!
from tensorflow.
@tilakrayal
Thank you for the quick response!
Sorry but in the code I had posted the actual training line history = model.fit(...)
was commented out!
I just tried the code again with the tf-nightly and also with v2.16.1 and unfortunately the I see the issue persisting.
Here is the corrected google colab. I also edited the original post.
from tensorflow.
Any ideas? @tilakrayal
from tensorflow.
Related Issues (20)
- `tf.data.Dataset.from_tensor_slices` allocates GPU RAM HOT 3
- import tensorflow command gives error HOT 3
- CUDA Messages in TensorFlow 2.17.0 and tf-nightly HOT 6
- GPU delegate and NNAPIDelegate results diverging significantly for a transformer model HOT 4
- Module not found HOT 2
- Accuracy Drop Across TensorFlow Versions When Using Keras 3 Instead of Keras 2 HOT 3
- Inconsistent results from distributed training of models containing `TimeDistributed` or `SeparableConv2D` HOT 2
- A Digital Future for All Siifsiin 2.0: A Next-Generation Platform for an Empowered Humanity
- Should this be opened against Keras repo? HOT 1
- TFlite: GPU delegate: ability to limit amount of GPU memory used by TFlite?
- Tensorflow Dataset API continues to be broken, list_files no longer works HOT 7
- In the local server command line environment, TensorFlow is able to recognize and utilize the GPU. However, when attempting to use TensorFlow in a Jupyter Notebook through a remote VSCode connection to the same server, there is an issue with loading the GPU libraries. HOT 4
- wasm-ld: error: --shared-memory is disallowed by c_api.o because it was not compiled with 'atomics' or 'bulk-memory' features. HOT 6
- IntelliSence in VS Code - Keras module not found by the IDE but is present HOT 3
- Tensorflow distributed + DTensor approach for large outer product HOT 1
- `tf.data.Dataset.prefetch()` error with basic usage HOT 1
- TensorFlow embedded in esp32
- Tensorflow crash driver CUDA of GeForce RTX 4090 HOT 7
- No dashboards are active for the current data set. HOT 4
- Memory usage with tf.data pipeline (HDF5, TFRecords) HOT 4
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 tensorflow.