https://github.com/datarohit/walk-or-run-image-classification
This is Deep Learning project made using InveptionV3 model and Images taken from Kaggle to predict if the person in Image is Walking or Running.
https://github.com/datarohit/walk-or-run-image-classification
cnn-classification inceptionv3 keras keras-tensorflow matplotlib numpy tensorflow
Last synced: 6 months ago
JSON representation
This is Deep Learning project made using InveptionV3 model and Images taken from Kaggle to predict if the person in Image is Walking or Running.
- Host: GitHub
- URL: https://github.com/datarohit/walk-or-run-image-classification
- Owner: DataRohit
- Created: 2022-06-16T14:05:00.000Z (over 3 years ago)
- Default Branch: master
- Last Pushed: 2022-06-16T14:21:18.000Z (over 3 years ago)
- Last Synced: 2025-02-15T07:47:21.831Z (8 months ago)
- Topics: cnn-classification, inceptionv3, keras, keras-tensorflow, matplotlib, numpy, tensorflow
- Homepage: https://www.kaggle.com/code/datarohitingole/walk-or-run-inceptionv3-model-91-accuracy
- Size: 1.08 MB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: Readme.md
Awesome Lists containing this project
README
# Walk-or-Run Image Classification
## Data
#### Data for this project is taken from Kaggle. It contains 500+ images for training and 100+ images for testing. This image data needs to be processed and then used to build a CNN to classifiy images. Find the data on kaggle [here](https://www.kaggle.com/datasets/huan9huan/walk-or-run).
## Files
#### The code is written in python using google colab. Find all the for the project [here](https://drive.google.com/drive/folders/1NEBoKMyIoYkpaaD4pTOvODC2_wa9Q8mA?usp=sharing).
## Analysis
#### The analysis i.e. processing of image data and model building is done using tensorflow and keras. Here I have used InceptionV3 model which is an inbuilt model in keras. InceptionV3 model gave highest 97% accuracy.
## End-to-End
#### The webapp to test the CNN in action to classify running and walking images is built using streamlit. You can read about streamlit [here](https://docs.streamlit.io/). Below is the image of the webapp desing.
