Add Labeling Guideline && Update app.py + README.md for Deployment

Author: 18520339

.gitignore

@@ -1,7 +1,2 @@
 *.zip
 *.hdf5
-!Model\ Implement/ResNet152V2/fine_tune_model_best.hdf5
-test.py
-secret.ini
-Dataset
-credentials.json

Labeling Guideline.pdf

@@ -1,14 +1,16 @@
 # A Dataset for Vietnamese Food Images Recognition
 
-- Dataset: https://www.kaggle.com/quandang/vietnamese-foods
-- Demo: https://www.youtube.com/watch?v=GV_1TGohFU8
+-   Dataset: https://www.kaggle.com/quandang/vietnamese-foods
+-   Demo: https://www.youtube.com/watch?v=GV_1TGohFU8
 
 ## Publication
+
 > Paper: https://ieeexplore.ieee.org/abstract/document/9530774
 
 This paper introduces a large dataset of **25136 images of 30 popular Vietnamese foods**. Several machine learning and deep learning image classification techniques have been applied to test the dataset and the results were compared and report. A **decent accuracy of 77.54%** and a high **top 5-accuracy of 96.07%** were achieved. The dataset and the performance comparison of state-of-the-art algorithm tested on the dataset will be useful for ones to develop new food image classification algorithms.
 
 ## Implementation process
+
 1.  Collecting Data: https://git.io/Jthak
 2.  Preprocessing Data:
 
@@ -20,7 +22,7 @@ This paper introduces a large dataset of **25136 images of 30 popular Vietnamese
 
 3.  Model Implement: https://git.io/Jc1Bi
 4.  Model Evaluation: https://git.io/Jc7fL
-5.  Deployment: https://share.streamlit.io/18520339/30VNFoods/main/app.py
+5.  Deployment: **temporarily inactive** due to the large model exceeded my Git LFS quota. You can watch the [demo](https://www.youtube.com/watch?v=GV_1TGohFU8) or try to make [your own deployment](https://github.com/18520339/30VNFoods/blob/main/app.py) with [our trained models](https://drive.google.com/drive/folders/1HQQaB3Tqc6m1XGxkqD5blQOO6vfdGONO?usp=sharing) using [Streamlit](https://docs.streamlit.io/en/stable/deploy_streamlit_app.html#deploy-your-app)
 
 ## License
 

README.md

@@ -99,7 +99,7 @@ def plot_probs(outputs):
     )
 
 img_test = preprocess_image('./test.jpg')
-model = load_model('Model Implement/ResNet152V2/fine_tune_model_best.hdf5')
+model = load_model('[PLACE_YOUR_MODEL_PATH_HERE]')
 pred_probs = model.predict(img_test)[0]
 print(pred_probs)