TF-Binary-Classification
- 0 Collaborators
TF-Binary-Classification is a python package on PyPI. It can be used to train and test a model in a single line of terminal command. ...learn more
Project status: Published/In Market
Groups
Student Developers for AI
Intel Technologies
Other
Overview / Usage
TF-Binary-Classification python package helps developers focus more on the problem area. The packages has two part i.e training and testing. The user using the command line gives all the details like path, epochs, and categories names that needs training followed by testing. For any data set the model gives 80-89% accuracy. Thus, with just a single line of command line argument binary classification can be implemented.
Methodology / Approach
The user enters the parameters in the command line which is then extracted using argument parser. These arguments are then used to train or test the model that is already designed. The model has 4 layer neural network with the hidden layers having activation functions "ReLU" and output layer "Sigmoid". The images are first converted into 64x64 single channel and fed into the network for training. After the training the model is saves as 64x3-CNN.model. This model is used to test with the test images where the path is given by the user in the terminal. To avoid any confusion the user must work in the same folder for testing and training.
Technologies Used
Python Libraries used:
numpy
matplotlib.pyplot
os
cv2
tqdm
tensorflow
from tensorflow.keras.datasets import cifar10
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Activation, Flatten
from tensorflow.keras.layers import Conv2D, MaxPooling2D
import pickle