https://github.com/yasnakateb/tensorflownotes

classification computer-vision deep-learning fashion-mnist mnist-dataset neural-networks python3 tensorflow

Last synced: 3 months ago
JSON representation

TensorFlow for deep learning

Host: GitHub
URL: https://github.com/yasnakateb/tensorflownotes
Owner: yasnakateb
License: apache-2.0
Created: 2022-07-25T16:53:39.000Z (almost 4 years ago)
Default Branch: main
Last Pushed: 2022-07-30T19:26:44.000Z (almost 4 years ago)
Last Synced: 2025-12-27T22:48:55.174Z (6 months ago)
Topics: classification, computer-vision, deep-learning, fashion-mnist, mnist-dataset, neural-networks, python3, tensorflow
Language: Jupyter Notebook
Homepage:
Size: 13.5 MB
Stars: 0
Watchers: 1
Forks: 0
Open Issues: 0
Metadata Files:
- Readme: README.md
- License: LICENSE

README

# TensorFlowNotes

## Objectives

✅ Monitor the accuracy of the housing price predictions

✅ Analyze housing price predictions that come from a single layer neural network

✅ Use TensorFlow to build a single layer neural network for fitting linear models

✅ Use callback functions for tracking model loss and accuracy during training

✅ Make predictions on how the layer size affects network predictions and training speed

✅ Implement pixel value normalization to speed up network training

✅ Build a multilayer neural network for classifying the Fashion MNIST image dataset

✅ Use callback functions to interrupt training after meeting a threshold accuracy

✅ Test the effect of adding convolution and MaxPooling to the neural network for classifying Fashion MNIST images

✅ Explain and visualize how convolution and MaxPooling aid in image classification tasks

✅ Reflect on the possible shortcomings of your binary classification model implementation

✅ Execute image preprocessing with the Keras ImageDataGenerator functionality

✅ Carry out real life image classification by leveraging a multilayer neural network for binary classification

## How to build

Run the codes on Google Colaboratory 😄