Remove current fastapi files

src/config.py

@@ -1,4 +0,0 @@
-import os
-
-MODEL_HDF5_PATH = os.getenv("MODEL_HDF5_PATH")
-

src/handler.py

@@ -1,39 +0,0 @@
-from fastapi import UploadFile
-from skimage.io import imread
-from io import BytesIO
-import numpy as np
-import urllib
-from tensorflow.keras.preprocessing.image import array_to_img, img_to_array
-
-from PIL import Image
-
-def preprocess(img: np.ndarray) -> np.ndarray:
-    img = array_to_img(img, scale=False)
-    img = img.resize((224, 224))
-    img = img_to_array(img)
-    return img / 255.0
-
-
-def handle_url(url: str) -> np.ndarray:
-    try:
-        img_data = imread(url)
-    except Exception:
-        req = urllib.request.Request(url, headers={"User-Agent": "Magic Browser"})
-        con = urllib.request.urlopen(req)
-        img_data = imread(con)
-    processed_img = preprocess(img_data)
-    img_array = np.array([processed_img])
-    return img_array
-
-
-def read_imagefile(file):
-    file_bytes = BytesIO(file)
-    image = Image.open(file_bytes)
-    return image
-
-
-def handle_file(file: UploadFile) -> np.ndarray:
-    img_data = read_imagefile(file)
-    processed_img = preprocess(img_data)
-    img_array = np.array([processed_img])
-    return img_array

src/labels.txt

@@ -1,101 +0,0 @@
-Apple pie
-Baby back ribs
-Baklava
-Beef carpaccio
-Beef tartare
-Beet salad
-Beignets
-Bibimbap
-Bread pudding
-Breakfast burrito
-Bruschetta
-Caesar salad
-Cannoli
-Caprese salad
-Carrot cake
-Ceviche
-Cheesecake
-Cheese plate
-Chicken curry
-Chicken quesadilla
-Chicken wings
-Chocolate cake
-Chocolate mousse
-Churros
-Clam chowder
-Club sandwich
-Crab cakes
-Creme brulee
-Croque madame
-Cup cakes
-Deviled eggs
-Donuts
-Dumplings
-Edamame
-Eggs benedict
-Escargots
-Falafel
-Filet mignon
-Fish and chips
-Foie gras
-French fries
-French onion soup
-French toast
-Fried calamari
-Fried rice
-Frozen yogurt
-Garlic bread
-Gnocchi
-Greek salad
-Grilled cheese sandwich
-Grilled salmon
-Guacamole
-Gyoza
-Hamburger
-Hot and sour soup
-Hot dog
-Huevos rancheros
-Hummus
-Ice cream
-Lasagna
-Lobster bisque
-Lobster roll sandwich
-Macaroni and cheese
-Macarons
-Miso soup
-Mussels
-Nachos
-Omelette
-Onion rings
-Oysters
-Pad thai
-Paella
-Pancakes
-Panna cotta
-Peking duck
-Pho
-Pizza
-Pork chop
-Poutine
-Prime rib
-Pulled pork sandwich
-Ramen
-Ravioli
-Red velvet cake
-Risotto
-Samosa
-Sashimi
-Scallops
-Seaweed salad
-Shrimp and grits
-Spaghetti bolognese
-Spaghetti carbonara
-Spring rolls
-Steak
-Strawberry shortcake
-Sushi
-Tacos
-Takoyaki
-Tiramisu
-Tuna tartare
-Waffles

src/main.py

@@ -1,44 +0,0 @@
-from fastapi import FastAPI, UploadFile, File, HTTPException, status, Header
-from fastapi.responses import RedirectResponse
-
-from handler import handle_file, handle_url
-from predict import predict_model
-
-
-app = FastAPI()
-
-@app.get("/")
-async def docs_redirect():
-    return RedirectResponse(url='/docs')
-
-
-@app.get("/predict_url")
-async def predict_url(url: str):
-    model_input = handle_url(url)
-    model_output = predict_model(model_input)
-    return model_output
-
-
-@app.get("/healthcheck")
-async def healthcheck():
-    return {"status": "alive"}
-
-
-def validate_image_content(content_type: str = Header(...)):
-    """Require request MIME-type to be image/*"""
-
-    content_main_type = content_type.split("/")[0]
-    if content_main_type != "image":
-        raise HTTPException(
-            status.HTTP_415_UNSUPPORTED_MEDIA_TYPE,
-            f"Unsupported media type: {content_type}."
-            " It must be image/",
-        )
-
-
-@app.post("/predict_file")
-async def predict_file(upload_file: UploadFile = File(...)):
-    validate_image_content(upload_file.content_type)
-    model_input = handle_file(await upload_file.read())
-    model_output = predict_model(model_input)
-    return model_output

src/model.py

@@ -1,62 +0,0 @@
-import numpy as np
-from tensorflow.keras.utils import get_file
-from config import MODEL_HDF5_PATH
-
-
-with open("labels.txt", "r") as f:
-    LABELS = list(filter(None, f.read().split("\n")))
-
-
-
-def initialize_model():
-    # import the necessary packages
-    from tensorflow.keras.models import Sequential
-    from tensorflow.keras.layers import BatchNormalization
-    from tensorflow.keras.layers import Conv2D, MaxPooling2D
-    from tensorflow.keras.layers import Flatten, Dropout, Dense
-
-    # CONV => RELU => POOL
-    cnn = Sequential()
-    inputShape = (224, 224, 3)
-    chanDim = -1
-    classes = 101
-    # Sequence of Convolution (scan filters), BatchNormalization (normalize numbers),
-    #  MaxPooling (shrink tensor down), Dropout (prevent overfit)
-    cnn.add(
-        Conv2D(32, (3, 3), padding="same", input_shape=inputShape, activation="relu")
-    )
-    cnn.add(BatchNormalization(axis=chanDim))
-    cnn.add(MaxPooling2D(pool_size=(3, 3)))
-    cnn.add(Dropout(rate=0.25))
-    cnn.add(Conv2D(64, (3, 3), padding="same", activation="relu"))
-    cnn.add(BatchNormalization(axis=chanDim))
-    cnn.add(Conv2D(64, (3, 3), padding="same", activation="relu"))
-    cnn.add(BatchNormalization(axis=chanDim))
-    cnn.add(MaxPooling2D(pool_size=(2, 2)))
-    cnn.add(Dropout(rate=0.25))
-    cnn.add(Conv2D(128, (3, 3), padding="same", activation="relu"))
-    cnn.add(BatchNormalization(axis=chanDim))
-    cnn.add(Conv2D(128, (3, 3), padding="same", activation="relu"))
-    cnn.add(BatchNormalization(axis=chanDim))
-    cnn.add(MaxPooling2D(pool_size=(2, 2)))
-    cnn.add(Dropout(rate=0.25))
-    cnn.add(Flatten())
-    cnn.add(Dense(1024, activation="relu"))
-    cnn.add(BatchNormalization())
-    cnn.add(Dropout(rate=0.5))
-    # softmax classifier
-    cnn.add(Dense(classes, activation="softmax"))
-
-    return cnn
-
-
-CNN = initialize_model()
-
-
-CNN.load_weights(
-    get_file(
-        "weights.hdf5",
-        MODEL_HDF5_PATH,
-        cache_dir="."
-    )
-)

src/predict.py

@@ -1,10 +0,0 @@
-from model import CNN, LABELS
-
-
-
-def predict_model(img_array):
-    class_prob = CNN.predict(img_array)
-    top_values_index = (-class_prob).argsort()[0][:10]
-    top_guesses = [LABELS[i].title() for i in top_values_index]
-
-    return top_guesses