Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/gregoritsch3/dl_cnn_resnet50_digitrecognition
A Deep Learning Computer Vision project on the MNIST Digit Dataset. The project demonstrates the use of four TensorFlow Neural Network architectures, ranging from a basic Shallow Sigmoid Model to a Deep Convolutional Model constructed using the FunctionalAPI, and even a modified Resnet50 Model. Includes Error Analysis and test runs on real images.
https://github.com/gregoritsch3/dl_cnn_resnet50_digitrecognition
cnn convolutional-neural-networks cv2 keras matplotlib numpy resnet-50 tensorflow
Last synced: 30 days ago
JSON representation
A Deep Learning Computer Vision project on the MNIST Digit Dataset. The project demonstrates the use of four TensorFlow Neural Network architectures, ranging from a basic Shallow Sigmoid Model to a Deep Convolutional Model constructed using the FunctionalAPI, and even a modified Resnet50 Model. Includes Error Analysis and test runs on real images.
- Host: GitHub
- URL: https://github.com/gregoritsch3/dl_cnn_resnet50_digitrecognition
- Owner: Gregoritsch3
- Created: 2025-01-06T11:20:13.000Z (about 1 month ago)
- Default Branch: main
- Last Pushed: 2025-01-06T11:25:51.000Z (about 1 month ago)
- Last Synced: 2025-01-06T12:29:34.911Z (about 1 month ago)
- Topics: cnn, convolutional-neural-networks, cv2, keras, matplotlib, numpy, resnet-50, tensorflow
- Language: Jupyter Notebook
- Homepage: https://yann.lecun.com/exdb/mnist/
- Size: 89.7 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# DL_Digit_Recognition
A Deep Learning Computer Vision project that classifies images from the MNIST Digit Dataset. The project demonstrates the use of four TensorFlow Neural Network architectures, ranging from a basic Shallow Sigmoid Model to a deep Convolutional Model constructed using the FunctionalAPI, and even a modified Resnet50 Model. The project includes Error Analysis and Test Runs on custom-made images. The results are satisfactory.