https://github.com/egiiputra/googlenet-leukemia-classification
Leukemia Lymphoblastic Acute classification using googlenet architecture
https://github.com/egiiputra/googlenet-leukemia-classification
cnn deeplearning image-classification streamlit tensorflow
Last synced: about 2 months ago
JSON representation
Leukemia Lymphoblastic Acute classification using googlenet architecture
- Host: GitHub
- URL: https://github.com/egiiputra/googlenet-leukemia-classification
- Owner: egiiputra
- License: mit
- Created: 2024-11-30T01:09:33.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-01-27T10:38:22.000Z (over 1 year ago)
- Last Synced: 2025-01-27T11:45:40.581Z (over 1 year ago)
- Topics: cnn, deeplearning, image-classification, streamlit, tensorflow
- Language: Jupyter Notebook
- Homepage:
- Size: 16.7 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Leukemia classification using googlenet architecture
## Requirements
- python runtime >=3.10 <=3.12
- tensorflow
- streamlit
- opencv
- Etc, see ```streamlit/requirements.txt``` for details.
## How to run streamlit
First, you have to clone this repository
```
git clone https://github.com/Egi-putrA/googlenet-leukemia-classification.git
```
Then, open streamlit subdirectory
```
cd googlenet-leukemia-classification/streamlit
```
### Optional: use python virtual environments before install dependecies
Create virtual env
```
python -m venv venv
```
Activate virtual env
```
venv\Scripts\activate.bat # for windows
venv\bin\activate # for linux
```
### Install dependencies
install dependencies from requirements.txt
```
pip install -r requirements.txt
```
### Download trained model
You can download my trained model in [here](https://github.com/Egi-putrA/googlenet-leukemia-classification/releases/).
Make sure to change model path in main.py
```python
...
@st.cache_resource
def load_model():
return tf.saved_model.load('path/to/model').signatures['serving_default']
...
```
### Run streamlit app
```
streamlit run main.py
```