Sequential Neural Network using PyTorch
The Fashion-MNIST dataset contains 60,000 training images (and 10,000 test images) of fashion and clothing items, taken from 10 classes. Each image is a standardized 28x28 size in grayscale (784 total pixels).
To run the program, copy the virtual environment in this repository's yml file: using the Anaconda command line, enter the command below.
conda env create --name torch_copy_env -f torch_env.yml
After 30 epochs, the neural network's training accuracy was 94% and validation accuracy was 88%.