Final project for EE3314 at Yonsei University. Report includes training/testing accuracies for a simple CNN trained with the MNIST handwritten digits dataset. Sections two and three of the report refer to an AlexNet architecture CNN built with Tensorflow. After training the network with the CIFAR10 dataset, transfer learning was applied for the Network to distinguish a unique dataset including 1000s of small face pictures. Our team also utilized three-fold cross-validation with the help of scikitlearn for better testing accuracy.
forked from jbk41/ai_final
-
Notifications
You must be signed in to change notification settings - Fork 0
Final project for EE3314 at Yonsei University. Report includes training/testing accuracies for a simple CNN trained with the MNIST handwritten digits dataset. Sections two and three of the report refer to an AlexNet architecture CNN built with Tensorflow. After training the network with the CIFAR10 dataset, transfer learning was applied for the …
wnam98/AIFinalProject
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Final project for EE3314 at Yonsei University. Report includes training/testing accuracies for a simple CNN trained with the MNIST handwritten digits dataset. Sections two and three of the report refer to an AlexNet architecture CNN built with Tensorflow. After training the network with the CIFAR10 dataset, transfer learning was applied for the …
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published
Languages
- Jupyter Notebook 100.0%