https://github.com/ksdkamesh99/ai-capstone-project

It is a AI Capstone project done as a part of IBM AI Engineering
https://github.com/ksdkamesh99/ai-capstone-project

capstone-project resnet-50 vgg16

Last synced: 3 months ago
JSON representation

It is a AI Capstone project done as a part of IBM AI Engineering

• Host: GitHub
• URL: https://github.com/ksdkamesh99/ai-capstone-project
• Owner: ksdkamesh99
• License: mit
• Created: 2020-05-16T02:34:08.000Z (almost 5 years ago)
• Default Branch: master
• Last Pushed: 2020-10-23T11:16:44.000Z (over 4 years ago)
• Last Synced: 2024-11-02T12:34:01.333Z (4 months ago)
• Topics: capstone-project, resnet-50, vgg16
• Language: Jupyter Notebook
• Homepage:
• Size: 83.2 MB
• Stars: 17
• Watchers: 2
• Forks: 11
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# AI-Capstone-Project

[![Codacy Badge](https://app.codacy.com/project/badge/Grade/c0f88d5257844aa986c260bf5970782a)](https://www.codacy.com/manual/ksdkamesh99/AI-Capstone-Project?utm_source=github.com&utm_medium=referral&utm_content=ksdkamesh99/AI-Capstone-Project&utm_campaign=Badge_Grade)

## Dataset used:-

[https://s3-api.us-geo.objectstorage.softlayer.net/cf-courses-data/CognitiveClass/DL0321EN/data/concrete_data_week4.zip](https://s3-api.us-geo.objectstorage.softlayer.net/cf-courses-data/CognitiveClass/DL0321EN/data/concrete_data_week4.zip)

## Course:-

[https://www.coursera.org/learn/ai-deep-learning-capstone](https://www.coursera.org/learn/ai-deep-learning-capstone)

## About the repository:-

1 . This Repository contains the 4 week AI Capstone project assignment using keras as a part of IBM-AI Engineering in which we need to classify a image containing a stone cracked or not by processing 40000 images in which nearly 30000 for training and 10000 for validation.  

2 . 4th week is final assignment in which we need to campare performance in between pretrained models like Resnet50 and VGG16 using keras.

## Performance of Models:-

I ran both models to 2 epochs. Performance is as shown in below table.

| Model          | Training Accuracy | Validation Accuracy | Test Accuracy  | Valdation Loss | Training Loss   | 

|----------------|-------------------|---------------------|----------------|----------------|-----------------|

| Resnet 50      | 91.08%            | 93.88%              | 54.19          | 0.0016         | 0.0070          |

| VGG16          | 99.76%            | 99.81%              | 98.0%          | 7.4741e-05     | 0.0074          |

## Conclusion:-

In the 2 models by the above data we can conclude VGG16 is appropriate for the above dataset. After all my final assignment is passed and graded 100%.  

You can check it out [here](https://www.coursera.org/account/accomplishments/records/PTE5WUKY5GMV)

## Licence:-

[MIT Licence](https://github.com/ksdkamesh99/AI-Capstone-Project/blob/master/LICENSE)