HenryMorganDibie/BigCats-Image-Classification-with-ML-DL-techniques-

The Big Cats Image Classification dataset is a collection of images of ten different species of big cats, namely the African leopard, Amur leopard, cheetah, jaguar, leopard, lion, puma, snow leopard, tiger, and clouded leopard. The dataset consists of a total of 2440 images, with 2339 images for training and 50 images each for validation and testin # BigCats-Image-Classification ### Explanation of dataset, prediction and its analysis here, medium.com * Here's a summary of the exploratory data analysis (EDA) performed on the dataset: Importing the necessary libraries and loading the dataset. Checked for info, dtypes, got to understand the length and shape of the dataset, as well as if their were null vallues. The dataset contains a total of 2440 images of 10 different species of big cats, with 80% of the images allocated to the training set and 20% allocated to the validation set. The images are distributed across 10 classes, one for each species of big cat. The dataset appears to be balanced, with each class containing approximately the same number of images. The average size of the images in the dataset is 380 x 531 pixels, with a standard deviation of 147 x 201 pixels. The minimum size of the images is 150 x 150 pixels, while the maximum size is 1192 x 794 pixels. The dataset contains images of big cats from both the Panthera and Neofelis genera. Within the Panthera genus, the dataset includes images of the following species: African leopard, Amur leopard, Asiatic cheetah, Bengal tiger, Indochinese tiger, Jaguar, Lion, and Snow leopard. Within the Neofelis genus, the dataset includes images of the Clouded leopard and Sunda clouded leopard. Overall, the dataset appears to be a good starting point for building a deep learning model to classify images of big cats. However, it may be necessary to preprocess the images to ensure they are all the same size and to augment the data to increase the size of the dataset and prevent overfitting. * Preprocessing steps that were performed on the dataset: Splitting the dataset into training, validation, and testing sets with a ratio of 0.8:0.1:0.1. Resizing all images to 224x224 pixels to ensure consistency in size. Converting all images to grayscale to reduce the num …