Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/martincastroalvarez/tensorflow-image-detection-classification
Image Detection using TensorFlow in Python.
https://github.com/martincastroalvarez/tensorflow-image-detection-classification
computer-vision data-science deep-learning image-detection matplotlib neural-network prediction-model python3 tensorflow
Last synced: 27 days ago
JSON representation
Image Detection using TensorFlow in Python.
- Host: GitHub
- URL: https://github.com/martincastroalvarez/tensorflow-image-detection-classification
- Owner: MartinCastroAlvarez
- Created: 2019-07-24T19:37:42.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2023-02-15T22:00:51.000Z (almost 2 years ago)
- Last Synced: 2023-03-04T12:42:01.834Z (almost 2 years ago)
- Topics: computer-vision, data-science, deep-learning, image-detection, matplotlib, neural-network, prediction-model, python3, tensorflow
- Language: Python
- Homepage: https://martincastroalvarez.com
- Size: 241 MB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 8
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Belgium
Implementation of TensorFlow in Python.
This app is intended to analyze Belgium traffic (image) data.## References
- [TensorFlow Installation](https://www.tensorflow.org/install/pip)
- [TensorFlow Tutorial](https://www.datacamp.com/community/tutorials/tensorflow-tutorial)
- [TensorFlow vs NumPy](https://www.quora.com/What-is-the-difference-between-Numpy-and-TensorFlow)
- [Tutorials for TensorFlow](https://www.guru99.com/tensorflow-tutorial.html)
- [Scikit Image](https://scikit-image.org/)
- [Python3 LRU Cache](https://docs.python.org/dev/library/functools.html#functools.lru_cache)
- [Matplotlib](https://matplotlib.org/3.1.1/gallery/subplots_axes_and_figures/figure_title.html)
- [OpenCV2](https://pypi.org/project/opencv-python/)
- [Save and restore in TensorFlow](https://www.tensorflow.org/guide/saved_model)## Why TensorFlow?
```
Numpy has N-d array support but does not have methods to create tensor functions, can’t automatically compute derivatives and it can’t take advantage of GPU.TensorFlow provides primitives for defining functions on tensors and automatically computing their derivatives. TensorFlow computations define a graph that has no numerical value until evaluated.
```## Data Visualization
![sample-alt](./plot/random-sample.png)
![histogram-alt](./plot/data-histogram.png)
![predictions-alt](./plot/sample-predictions.png)## Usage
Install the virtual environment.
```bash
virtualenv -p python3 .env
source .env/bin/activate
```
First, download the datasets from [here](http://btsd.ethz.ch/shareddata/).
Then, execute the AI script:
```bash
clear; python3 think.py
```