<h3 align="center">
<img src="assets/histopathologic_cancer_detector_icon_web.png" width="300">
</h3>
# Histopathologic Cancer Detector
Python Jupyter Notebook leveraging **Transfer Learning** and **Convolutional Neural Networks** implemented with **Keras**.
Part of the [Kaggle competition](https://www.kaggle.com/c/histopathologic-cancer-detection).
Submitted [Kernel](https://www.kaggle.com/greg115/histopathologic-cancer-detector-lb-0-958) with 0.958 LB score.
Check out corresponding Medium article:
[Histopathologic Cancer Detector - Machine Learning in Medicine](https://towardsdatascience.com/histopathologic-cancer-detector-finding-cancer-cells-with-machine-learning-b77ce1ee9b0a)
## Data
**Dataset:** [Link](https://www.kaggle.com/c/histopathologic-cancer-detection/data)
**Description:** Binary classification whether a given histopathologic image contains a tumor or not.
**Training:** 153k (0.9) images
**Validation:** 17k (0.1) images
**Testing:** 57.5k images
## Model
<h3>
<img src="assets/model_plot.png" width="500">
</h3>
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_1 (InputLayer) (None, 96, 96, 3) 0
__________________________________________________________________________________________________
xception (Model) (None, 3, 3, 2048) 20861480 input_1[0][0]
__________________________________________________________________________________________________
NASNet (Model) (None, 3, 3, 1056) 4269716 input_1[0][0]
__________________________________________________________________________________________________
global_average_pooling2d_1 (Glo (None, 2048) 0 xception[1][0]
__________________________________________________________________________________________________
global_average_pooling2d_2 (Glo (None, 1056) 0 NASNet[1][0]
__________________________________________________________________________________________________
concatenate_5 (Concatenate) (None, 3104) 0 global_average_pooling2d_1[0][0]
global_average_pooling2d_2[0][0]
__________________________________________________________________________________________________
dropout_1 (Dropout) (None, 3104) 0 concatenate_5[0][0]
__________________________________________________________________________________________________
dense_1 (Dense) (None, 1) 3105 dropout_1[0][0]
==================================================================================================
Total params: 25,134,301
Trainable params: 25,043,035
Non-trainable params: 91,266
__________________________________________________________________________________________________
## Training
<h3>
<img src="assets/training.png" width="500">
</h3>
<h3>
<img src="assets/validation.png" width="500">
</h3>
<h3>
<img src="assets/roc.png" width="500">
</h3>
## Results
Kaggle score: **0.958**
## Author
**Greg (Grzegorz) Surma**
[**PORTFOLIO**](https://gsurma.github.io)
[**GITHUB**](https://github.com/gsurma)
[**BLOG**](https://medium.com/@gsurma)
<a href="https://www.paypal.com/paypalme2/grzegorzsurma115">
<img alt="Support via PayPal" src="https://cdn.rawgit.com/twolfson/paypal-github-button/1.0.0/dist/button.svg"/>
</a>
没有合适的资源?快使用搜索试试~ 我知道了~
histopathologic_cancer_detector:CNN组织病理学肿瘤识别码
共10个文件
png:5个
gitignore:1个
md:1个
需积分: 10 4 下载量 24 浏览量
2021-02-04
07:29:43
上传
评论
收藏 1.97MB ZIP 举报
温馨提示
histopathologic_cancer_detector:CNN组织病理学肿瘤识别码
资源推荐
资源详情
资源评论
收起资源包目录
histopathologic_cancer_detector-master.zip (10个子文件)
histopathologic_cancer_detector-master
.gitignore 1KB
README.md 4KB
histopathologic_cancer_detector.ipynb 13KB
.github
FUNDING.yml 16B
LICENSE 1KB
assets
roc.png 16KB
training.png 17KB
histopathologic_cancer_detector_icon_web.png 1.83MB
model_plot.png 100KB
validation.png 16KB
共 10 条
- 1
资源评论
快快跑起来
- 粉丝: 21
- 资源: 4626
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功