Upload 23 files

Procfile

@@ -0,0 +1 @@
+web: uvicorn application.server.main:app --host 0.0.0.0 --port $PORT --workers 2

app.py

@@ -0,0 +1,58 @@
+import streamlit as st
+import json
+import requests
+from PIL import Image
+import os
+
+
+def load_image(image):
+	img = Image.open(image)
+	return img
+
+def save_uploadedfile(uploadedfile):
+     with open(os.path.join("images/img",uploadedfile.name),"wb") as f:
+         f.write(uploadedfile.getbuffer())
+         uploaded_location = os.path.join("images/img",uploadedfile.name)
+     return uploaded_location#st.success("Saved File:{} to {}".format(uploadedfile.name, uploaded_location))
+     
+
+st.title("Covid Prediction App from CT Images")
+
+
+#taking user inputs
+
+st.write("")
+
+#converting input to json
+
+
+image = st.file_uploader("Upload CT Scan", type=["png","jpg","jpeg"])
+ 
+if image is not None:
+	  # To See details
+	  file_details = {"filename":image.name, "filetype":image.type,
+	      "filesize":image.size}
+	  st.write(file_details)
+	  #image1 = Image.open(image)
+	  #img_array = np.array(image1)
+
+	#View Uploaded Image
+	  st.image(load_image(image),width=250)
+	  #save image to disk
+	  saved = save_uploadedfile(image)
+
+	  if st.button ('Analyze'):
+	  	  test_file = open(os.path.join("images/img", image.name), "rb")
+	  	  response = requests.post('http://127.0.0.1:8000/predict/image', files={'file': test_file })
+	  	  prediction = response.json()##json_object["prediction"]
+	  	  st.write(prediction)
+	  	  st. subheader (f"Response from Covid Analyzer API = {prediction}")
+
+#RUN BOTH...
+#streamlit run app.py
+#uvicorn application.server.main:app 
+
+#OPTION 2....
+
+
+

application/components/__init__.py

@@ -0,0 +1 @@
+from .prediction.serve_model import predict, read_imagefile

application/components/prediction/serve_model.py

@@ -0,0 +1,50 @@
+from io import BytesIO
+
+import numpy as np
+import tensorflow as tf
+from PIL import Image
+#from tensorflow.keras.applications.imagenet_utils import decode_predictions
+from tensorflow.keras.models import load_model
+import os
+
+
+model = None
+
+def load_model2():
+    model = load_model('application/models/resnet_ct.h5')
+    #model = load_model(os.path.join(modelpath, 'resnet_ct.h5'))
+    print("Model loaded")
+    return model
+
+
+def predict(image: Image.Image):
+    global model
+    if model is None:
+        model = load_model2()
+
+    image = np.asarray(image.resize((224, 224)))[..., :3]
+    image = np.expand_dims(image, 0)
+    image = image / 127.5 - 1.0
+
+    result = model.predict(image)
+    probability = result[0]
+            #print("Resnet Predictions:")
+    if probability[0] > 0.5:
+        resnet_chest_pred = str('%.2f' % (probability[0]*100) + '% COVID') 
+    else:
+        resnet_chest_pred = str('%.2f' % ((1-probability[0])*100) + '% NonCOVID')
+
+    response = []
+    for i, res in enumerate(result):
+        resp = {}
+        resp["prediction"] = resnet_chest_pred
+        #resp["confidence"] = f"{res[2]*100:0.2f} %"
+
+        response.append(resp)
+
+    return response
+
+
+def read_imagefile(file) -> Image.Image:
+    image = Image.open(BytesIO(file))
+    return image

application/components/prediction/symptom_check.py

@@ -0,0 +1,14 @@
+from application.schema import Symptom
+
+def get_risk_level(symptom: Symptom):
+    if not (symptom.fever or symptom.dry_cough or symptom.tiredness or symptom.breathing_problem):
+        return 'Low risk level. THIS IS A DEMO APP'
+    
+    if not (symptom.breathing_problem or symptom.dry_cough):
+        if symptom.fever:
+            return 'moderate risk level. THIS IS A DEMO APP'
+    
+    if symptom.breathing_problem:
+        return 'High risk level. THIS IS A DEMO APP'
+    
+    return 'THIS IS A DEMO APP'

application/models/resnet_ct.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b20cd339ff029070d5a715ea2778143061a885bf1395cdc26464a8db8090825
+size 59338824

application/schema.py

@@ -0,0 +1,7 @@
+from pydantic import BaseModel
+
+class Symptom(BaseModel):
+    fever: bool = False
+    dry_cough: bool = False
+    tiredness: bool = False
+    breathing_problem: bool = False

application/server/main.py

@@ -0,0 +1,35 @@
+import uvicorn
+from fastapi import FastAPI, File, UploadFile
+from starlette.responses import RedirectResponse
+
+from application.components import predict, read_imagefile
+from application.schema import Symptom
+from application.components.prediction import symptom_check
+
+app_desc = """<h2>Try this app by uploading any image with `predict/image`</h2>
+<h2>Try Covid symptom checker api - it is just a learning app demo</h2>
+<br>by Aniket Maurya"""
+
+app = FastAPI(title='Tensorflow FastAPI Starter Pack', description=app_desc)
+
+
+@app.get("/", include_in_schema=False)
+async def index():
+    return RedirectResponse(url="/docs")
+
+
+@app.post("/predict/image")
+async def predict_api(file: UploadFile = File(...)):
+    extension = file.filename.split(".")[-1] in ("jpg", "jpeg", "png")
+    if not extension:
+        return "Image must be jpg or png format!"
+    image = read_imagefile(await file.read())
+    prediction = predict(image)
+
+    return prediction
+
+
+
+
+if __name__ == "__main__":
+    uvicorn.run(app, debug=True)

requirements.txt

@@ -0,0 +1,9 @@
+tensorflow-cpu
+fastapi
+Pillow
+starlette
+gunicorn
+uvicorn
+numpy
+python-multipart
+streamlit==1.15.2

runtime.txt

@@ -0,0 +1 @@
+python-3.7.8