This project Executes Mnist digit classification (0-9) using tensorflow. Tensorflow is an effective machine learning tool that is utilized here. Although keras is simpler to understand, tensorflow is observed to be a more powerful tool.
TensorFlow 2.0 Alpha is available
- tensorflow==2.0.0-alpha0 —Preview TF 2.0 Alpha build for CPU-only (unstable)
- tensorflow-gpu==2.0.0-alpha0 —Preview TF 2.0 Alpha build with GPU support (unstable, Ubuntu and Windows)
- tensorflow —Latest stable release for CPU-only (Ubuntu and Windows)
- tensorflow-gpu —Latest stable release with GPU support (Ubuntu and Windows)
- tf-nightly —Preview nightly build for CPU-only (unstable)
- tf-nightly-gpu —Preview nightly build with GPU support (unstable, Ubuntu and Windows)
- Ubuntu 16.04 or later (64-bit)
- macOS 10.12.6 (Sierra) or later (64-bit) (no GPU support)
- Windows 7 or later (64-bit) (Python 3 only)
- Raspbian 9.0 or later
https://www.tensorflow.org/install/pip
For installing Tensorflow, follow the directions mentioned in the link above.
To run the code, First initialize the virtual environment used to install tensorflow, and run the code either from the command prompt directly( Recommended for GPU users ) or any IDE.
If no error is observed, we can see an output like this.
- Rajaram Sivaramakrishnan - raja1196
This project is licensed under the MIT License - see the LICENSE.md file for details