Sign In

100 Sports Image Classification

Project Title: 100 Sports Image Classification

AIM : To build and train a State of the art Neural Network model using Pytorch API that can recognize different Sports by just processing the images.


Computer vision is playing a vital role in the field of image identification and analysis. It deals with the understanding of machines about images. Machines these days are capable enough to detect objects, particular activities, etc. Humans use their eyes and brain to identify things, to sense their surroundings. Computer
vision is a field that provides a similar capability to a machine. There are a lot of applications of computer vision and I have implemented one such application, which is Sports Image Classification. The dataset consists of 100 different sports images.

The model will be a Convolutional Neural Network model that is designed and trained totally using Pytorch Library.

Why CNN?

In machine learning, Convolutional Neural Networks (CNN or Conv2D) are complex neural networks. CNNs are used for image classification and recognition because of its high accuracy.

Why Pytorch?

PyTorch is an optimized tensor processing library primarily used for Deep Learning applications using GPUs and CPUs. It is an open-source machine learning library for Python, mainly developed by the Facebook AI Research team. It is one of the widely used Machine learning libraries, like TensorFlow and Keras.

!pip install jovian --upgrade --quiet
import jovian
# Execute this to save new versions of the notebook
[jovian] Detected Colab notebook... [jovian] Please enter your API key ( from ): API KEY: ·········· [jovian] Uploading colab notebook to Jovian... Committed successfully!