important file added

.dvcignore

@@ -0,0 +1,3 @@
+# Add patterns of files dvc should ignore, which could improve
+# the performance. Learn more at
+# https://dvc.org/doc/user-guide/dvcignore

.gitignore

@@ -160,3 +160,4 @@ cython_debug/
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
+artifacts/*

Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.11-slim
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+COPY . /code
+
+CMD ["streamlit", "run", "app.py"]

README.md

@@ -1 +1,64 @@
-# Chicken-disease-classification
+
+---
+title: Image To Text App
+emoji: 📹
+colorFrom: blue
+colorTo: red
+sdk: streamlit
+app_file: app.py
+pinned: false
+---
+## Workflows
+
+1. Update config.yaml
+2. Update secrets.yaml [Optional]
+3. Update params.yaml
+4. Update the entity
+5. Update the configuration manager in src config
+6. Update the components
+7. Update the pipeline 
+8. Update the main.py
+9. Update the dvc.yaml
+
+
+# How to run?
+### STEPS:
+
+Clone the repository
+
+```bash
+https://github.com/HAKIM-ML/Chicken-Disease-Classification-Using-Mlops
+```
+### STEP 01- Create a conda environment after opening the repository
+
+```bash
+conda create -n cnncls python=3.8 -y
+```
+
+```bash
+conda activate cnncls
+```
+
+
+### STEP 02- install the requirements
+```bash
+pip install -r requirements.txt
+```
+
+
+```bash
+# Finally run the following command
+python app.py
+```
+
+Now,
+```bash
+open up you local host and port
+```
+
+
+### DVC cmd
+
+1. dvc init
+2. dvc repro
+3. dvc dag

app.py

@@ -0,0 +1,75 @@
+
+import streamlit as st
+import io
+from PIL import Image
+import os
+from src.cnnClassfier.pipeline.predict import Prediction
+
+st.set_page_config(page_title="Chicken Health Predictor", page_icon="🐔", layout="wide")
+
+st.title("🐔 Chicken Health Predictor")
+st.markdown("### Upload an image to predict if the chicken is healthy or has coccidiosis")
+
+uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
+
+col1, col2 = st.columns(2)
+
+if uploaded_file is not None:
+    image = Image.open(uploaded_file)
+    col1.image(image, caption="Uploaded Image", use_column_width=True)
+    
+    # Save the uploaded file temporarily
+    temp_file = "temp_image.jpg"
+    image.save(temp_file)
+    
+    with st.spinner("Analyzing the image..."):
+        predictor = Prediction(temp_file)
+        prediction = predictor.predict()
+    
+    # Remove the temporary file
+    os.remove(temp_file)
+    
+    col2.markdown("## Prediction Result")
+    if prediction == "Healthy":
+        col2.success(f"The chicken appears to be **{prediction}**! 🎉")
+        col2.markdown("Keep up the good care for your feathered friend!")
+    else:
+        col2.error(f"The chicken may have **{prediction}**. 😢")
+        col2.markdown("Please consult with a veterinarian for proper treatment.")
+    
+    col2.markdown("### What is Coccidiosis?")
+    col2.info("""
+    Coccidiosis is a parasitic disease of the intestinal tract of animals caused by coccidian protozoa. 
+    The disease spreads from one animal to another by contact with infected feces or ingestion of infected tissue. 
+    Diarrhea, which may become bloody in severe cases, is the primary symptom.
+    """)
+
+st.sidebar.title("About")
+st.sidebar.info(
+    "This app uses a deep learning model to predict whether a chicken is healthy "
+    "or has coccidiosis based on an uploaded image. Always consult with a "
+    "veterinarian for accurate diagnosis and treatment."
+)
+
+st.sidebar.title("Instructions")
+st.sidebar.markdown(
+    """
+    1. Upload a clear image of a chicken.
+    2. Wait for the model to analyze the image.
+    3. View the prediction result and additional information.
+    """
+)
+
+st.markdown(
+    """
+    <style>
+    .reportview-container {
+        background: linear-gradient(to right, #FDFCFB, #E2D1C3);
+    }
+    .sidebar .sidebar-content {
+        background: linear-gradient(to bottom, #FDFCFB, #E2D1C3);
+    }
+    </style>
+    """,
+    unsafe_allow_html=True,
+)

dvc.yaml

@@ -0,0 +1,55 @@
+stages:
+  data_ingestion:
+    cmd: python src/cnnClassfier/pipeline/stage_01_data_ingestion.py
+    deps:
+      - src/cnnClassfier/pipeline/stage_01_data_ingestion.py
+      - config/config.yaml
+    outs:
+      - artifacts/data_ingestion/Chicken-fecal-images
+
+
+  prepare_base_model:
+    cmd: python src/cnnClassfier/pipeline/stage02_base_model.py
+    deps:
+      - src/cnnClassfier/pipeline/stage02_base_model.py
+      - config/config.yaml
+    params:
+      - IMAZE_SIZE
+      - INCLUDE_TOP
+      - CLASSES
+      - WEIGHTS
+      - LEARNING_RATE
+    outs:
+      - artifacts/prepare_base_model
+
+
+  training:
+    cmd: python src/cnnClassfier/pipeline/stage_03_train.py
+    deps:
+      - src/cnnClassfier/pipeline/stage_03_train.py
+      - src/cnnClassfier/components/callbacks.py
+      - config/config.yaml
+      - artifacts/data_ingestion/Chicken-fecal-images
+      - artifacts/prepare_base_model
+    params:
+      - IMAZE_SIZE
+      - EPOCHS
+      - BATCH_SIZE
+      - AUGMENTATION
+    outs:
+      - artifacts/training/model.h5
+
+
+  evaluation:
+    cmd: python src/cnnClassfier/pipeline/stage_04_evaluation.py
+    deps:
+      - src/cnnClassfier/pipeline/stage_04_evaluation.py
+      - config/config.yaml
+      - artifacts/data_ingestion/Chicken-fecal-images
+      - artifacts/training/model.h5
+    params:
+      - IMAZE_SIZE
+      - BATCH_SIZE
+    metrics:
+    - scores.json:
+        cache: false

main.py

@@ -0,0 +1,54 @@
+from cnnClassfier import logger
+from cnnClassfier.pipeline.stage_01_data_ingestion import DataIngestionTrainingPipeline
+from cnnClassfier.pipeline.stage02_base_model import PrepareBaseModelTrainigPipeline
+from cnnClassfier.pipeline.stage_03_train import ModelTrainingPipeline
+from cnnClassfier.pipeline.stage_04_evaluation import EvaluationTrainigPipeline
+
+
+STAGE_NAME  = "Data Ingestion Stage"
+
+try:
+    logger.info(f">>>>>> Stage {STAGE_NAME} Started >>>>>>")
+    data_ingestion = DataIngestionTrainingPipeline()
+    data_ingestion.main()
+    logger.info(f"<<<<<< Stage {STAGE_NAME} Completed >>>>>>")
+except Exception as e:
+    logger.exception(e)
+    raise e
+
+
+STAGE_NAME  = "Prepare Base Model"
+
+try:
+    logger.info(f">>>>>> Stage {STAGE_NAME} Started >>>>>>")
+    base_model = PrepareBaseModelTrainigPipeline()
+    base_model.main()
+    logger.info(f"<<<<<< Stage {STAGE_NAME} Completed >>>>>>")
+except Exception as e:
+    logger.exception(e)
+    raise e
+
+
+STAGE_NAME  = "Model Trainig"
+
+try:
+    logger.info(f">>>>>> Stage {STAGE_NAME} Started >>>>>>")
+    model_trainer = ModelTrainingPipeline()
+    model_trainer.main()
+    logger.info(f"<<<<<< Stage {STAGE_NAME} Completed >>>>>>")
+except Exception as e:
+    logger.exception(e)
+    raise e
+
+
+STAGE_NAME  = "Model Evaluation"
+
+try:
+    logger.info(f">>>>>> Stage {STAGE_NAME} Started >>>>>>")
+    model_evaluation = EvaluationTrainigPipeline()
+    model_evaluation.main()
+    logger.info(f"<<<<<< Stage {STAGE_NAME} Completed >>>>>>")
+except Exception as e:
+    logger.exception(e)
+    raise e
+

params.yaml

@@ -0,0 +1,8 @@
+AUGMENTATION : True
+IMAZE_SIZE : [224,224,3]
+BATCH_SIZE: 16
+INCLUDE_TOP: FALSE
+EPOCHS : 1
+CLASSES : 2
+WEIGHTS: imagenet
+LEARNING_RATE : 0.01

requirements.txt

@@ -0,0 +1,17 @@
+pandas 
+dvc
+notebook
+numpy
+matplotlib
+seaborn
+python-box==6.0.2
+pyYAML
+tqdm
+ensure==1.0.2
+joblib
+types-PyYAML
+scipy
+Flask
+Flask-Cors
+tensorflow==2.15.0
+streamlit

scores.json

@@ -0,0 +1,4 @@
+{
+    "loss": 8.425772666931152,
+    "accuracy": 0.5
+}

setup.py

@@ -0,0 +1,30 @@
+import setuptools
+
+with open("README.md", "r", encoding="utf-8") as f:
+    long_description = f.read()
+
+
+__version__ = "0.0.0"
+
+REPO_NAME = "Chicken-disease-classification"
+AUTHOR_USER_NAME = "HAKIM-ML"
+SRC_REPO = "cnnClassifier"
+AUTHOR_EMAIL = "akborislamamir5555@gmail.com"
+
+
+setuptools.setup(
+    name=SRC_REPO,
+    version=__version__,
+    author=AUTHOR_USER_NAME,
+    author_email=AUTHOR_EMAIL,
+    description="A small python package for CNN app",
+    long_description=long_description,
+    long_description_content="text/markdown",
+    url=f"https://github.com/{AUTHOR_USER_NAME}/{REPO_NAME}",
+    project_urls={
+        "Bug Tracker": f"https://github.com/{AUTHOR_USER_NAME}/{REPO_NAME}/issues",
+    },
+    package_dir={"": "src"},
+    packages=setuptools.find_packages(where="src")
+    
+)

template.py

@@ -0,0 +1,43 @@
+import os
+from pathlib import Path
+import logging
+
+logging.basicConfig(level=logging.INFO, format='[%(asctime)s]: (message)s:')
+
+project_name = 'cnnClassfier'
+
+list_of_files = [
+    '.github/workflows/.gitkeep',
+    f"src/{project_name}/__init__.py",
+    f"src/{project_name}/components/__init__.py",
+    f"src/{project_name}/utils/__init__.py",
+    f"src/{project_name}/config/__init__.py",
+    f"src/{project_name}/config/configuration.py",
+    f"src/{project_name}/pipeline/__init__.py",
+    f"src/{project_name}/entity/__init__.py",
+    f"src/{project_name}/constants/__init__.py",
+    "config/config.yaml",
+    'dvc.yaml',
+    'params.yaml',
+    'requirements.txt',
+    'setup.py',
+    'research./tails.ipynb',
+    
+]
+
+for filepath in list_of_files:
+    filepath = Path(filepath)
+    fildir, file_name = os.path.split(filepath)
+    
+    
+    if fildir != '':
+        os.makedirs(fildir, exist_ok=True)
+        logging.info(f"creating directory: {fildir} for the file: {file_name}")
+        
+    if (not os.path.exists(filepath)) or (os.path.getsize(filepath) == 0):
+        with open(filepath, 'w') as f:
+            pass
+            logging.info(f"Creating empty file: {filepath}")
+            
+    else:
+        logging.info(f"{file_name} is already exists")