Model integration

requirements.txt

 absl-py==0.14.0

routes/prediction.py

+from fastapi import APIRouter, File, UploadFile
+import tensorflow as tf
+from tensorflow import keras 
 from typing import List
-from fastapi import APIRouter
 from os import error
 import pandas as pd
 import numpy as np
 import json
-import os
+from keras.preprocessing import image 
+
 
 prediction = APIRouter()
 
+batch_size = 32
+img_height = 180
+img_width = 180
+class_names = ['Acne and Rosacea Photos', 'Actinic Keratosis Basal Cell Carcinoma and other Malignant Lesions', 'Atopic Dermatitis Photos', 'Bullous Disease Photos', 'Cellulitis Impetigo and other Bacterial Infections', 'Eczema Photos', 'Exanthems and Drug Eruptions', 'Hair Loss Photos Alopecia and other Hair Diseases', 'Herpes HPV and other STDs Photos', 'Light Diseases and Disorders of Pigmentation', 'Lupus and other Connective Tissue diseases', 'Melanoma Skin Cancer Nevi and Moles', 'Nail Fungus and other Nail Disease', 'Poison Ivy Photos and other Contact Dermatitis', 'Psoriasis pictures Lichen Planus and related diseases', 'Scabies Lyme Disease and other Infestations and Bites', 'Seborrheic Keratoses and other Benign Tumors', 'Systemic Disease', 'Tinea Ringworm Candidiasis and other Fungal Infections', 'Urticaria Hives', 'Vascular Tumors', 'Vasculitis Photos', 'Warts Molluscum and other Viral Infections']
+
+
 def load_data_json(path=''):
   with open(path, 'r') as fp:
     data = json.load(fp)
   fp.close()
   return data
 
+def is_image(filename: str)->bool:
+  valid = (".png", ".jpg", "jpeg")
+  return filename.endswith(valid)
+
+def read_imagefile( image:UploadFile ):
+  if is_image(image.filename):
+    directory = './temp_images/temp_image.jpg'
+    with open(directory, 'wb+') as image_upload:
+      image_upload.write(image.file.read())
+    return directory
+  return None
+
+
 @prediction.post('/api/predictions/symptoms')
 async def predict_symptoms(symptoms: List[int]):
     try:
@@ -33,5 +55,37 @@ async def predict_symptoms(symptoms: List[int]):
     except error: 
         return {"success": False, "msg": error}
 
+@prediction.post('/api/predictions/picture')
+async def predict_symptoms(req_file: UploadFile = File(...)):
+    try:
+      img = read_imagefile(req_file)
+
+      if img is None:
+        return {"success": False, "msg": 'Not a valid data format'}
+
+      model_path = './xception'
+      image_path = "./temp_images/temp_image.jpg"
+
+      #load model
+      model = keras.models.load_model(model_path)
+
+      #load data
+      load_img = image.load_img(image_path, target_size=(img_height, img_width))
+      img_array = image.img_to_array(load_img)
+      img_array = tf.expand_dims(img_array, 0)
+
+      #predict
+      predictions = model.predict(img_array, batch_size)
+      score = tf.nn.softmax(predictions[0])
+
+      #return
+      prediction = class_names[np.argmax(score)]
+
+      return {"success": True, "result": prediction}
+      
+    except error: 
+      return {"success": False, "msg": error}
+
+