Work with Tensorflow and image data & implement different models with this (eg- VGG16, VGG19, RSNET)
Exercise Statement
[Explain and describe what the exercise is]
The dataset contains parasitized and uninfected cells from the thin blood smear slide images of segmented cells. Here a VGG16 model is used to classify the cells as Infected & Uninfected
Prerequisites
[Prerequisites, in terms of concepts or other exercises in this repo]
Tensorflow/Keras, Transfer Learning
Data source/summary:
This dataset is simple and interesting enough to learn to implement different CNN architectures
The Malaria dataset contains a total of 27,558 cell images with equal instances of parasitized and uninfected cells from the thin blood smear slide images of segmented cells.
https://www.kaggle.com/iarunava/cell-images-for-detecting-malaria
(Optional) Suggest/Propose Solutions
I have the solution using the VGG19 model in Tensorflow, & will be happy to create a pull request and will then implement other models on this dataset.
Learning Goals
Work with Tensorflow and image data & implement different models with this (eg- VGG16, VGG19, RSNET)
Exercise Statement
[Explain and describe what the exercise is] The dataset contains parasitized and uninfected cells from the thin blood smear slide images of segmented cells. Here a VGG16 model is used to classify the cells as Infected & Uninfected
Prerequisites
[Prerequisites, in terms of concepts or other exercises in this repo] Tensorflow/Keras, Transfer Learning
Data source/summary:
This dataset is simple and interesting enough to learn to implement different CNN architectures The Malaria dataset contains a total of 27,558 cell images with equal instances of parasitized and uninfected cells from the thin blood smear slide images of segmented cells. https://www.kaggle.com/iarunava/cell-images-for-detecting-malaria
(Optional) Suggest/Propose Solutions
I have the solution using the VGG19 model in Tensorflow, & will be happy to create a pull request and will then implement other models on this dataset.