Python is used to do all the process, training, and testing for plant Seedings Classification dataset. All the processes are done using Python3 Google Colab. To tackle this problem, I used deep learning approach. Deep learning is a subset of machine learning algorithms that use multiple layers to extract higher level features from raw data. One of deep learning algorithm is Convolution Neural Network (CNN) which is a class of deep neural networks. CNN showed high learning performance of detecting objects using huge ImageNet datasets. CNN is a feed forward neural network which takes fixed size inputs and generates fixed size outputs, CNNs are easier to train because they have much fewer connections and parameters. CNN Model Architecture: Neural network is a multilayer perceptron of artificial nodes. Each node has weighted input data, pass it to an activation function and output node for the result. CNN model architecture has three layers: • Input layer which will take the image data in form of a matrix. • Hidden layers which will allow neural network to learn complex features within the data. • Output layer that will give the outcome. DataSet: https://www.kaggle.com/c/plant-seedlings-classification/data?select=train