Copy setup from yahoo-ff-dev and grubguesser-api

.gitignore

@@ -0,0 +1,165 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  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/
+
+
+*.json
+*.png
+*.csv

Dockerfile

@@ -1,14 +1,27 @@
-# read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
-# you will also find guides on how best to write your Dockerfile
+FROM python:3.8.13 as base
 
-FROM python:3.9
+# RUN apt-get update && \
+#     apt-get -y install curl gunicorn python3
 
-WORKDIR /code
+FROM base as python-base
+RUN curl -sSL https://bootstrap.pypa.io/get-pip.py | python3 -
+ENV APP_BASE_PATH="/opt/src"
+RUN mkdir -p ${APP_BASE_PATH}
+ENV PYTHONPATH="${APP_BASE_PATH}:${PYTHONPATH}"
 
-COPY ./requirements.txt /code/requirements.txt
 
-RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+FROM python-base as pip-tools-install
+RUN python3 -m pip install pip-tools
+WORKDIR ${APP_BASE_PATH}
 
-COPY . .
+FROM python-base as pip-install
+COPY src/requirements.txt ./requirements.txt
+RUN python3 -m pip install -r requirements.txt
 
-CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860"]
+FROM pip-install as copy-src
+COPY ./src /opt/src
+WORKDIR /opt/src
+
+
+FROM copy-src as production
+CMD ["python3", "-m", "uvicorn", "main:app", "--workers", "1", "--host", "0.0.0.0", "--port", "7860"]

run_dev_container.sh

@@ -0,0 +1,10 @@
+
+docker buildx build \
+    -f Dockerfile \
+    --tag dev-$(basename `git rev-parse --show-toplevel`) \
+    . \
+&& docker run -it \
+    --rm \
+    --mount type=bind,source="$(pwd)/src",target=/opt/src \
+    dev-$(basename `git rev-parse --show-toplevel`) \
+    bash

run_pip_tools.sh

@@ -0,0 +1,15 @@
+
+CONTAINER_NAME=dev-pip-tools-$(basename `git rev-parse --show-toplevel`)
+
+docker build \
+    -f Dockerfile \
+    --target pip-tools-install \
+    --tag $CONTAINER_NAME \
+    . \
+&& docker run -it \
+    --rm \
+    --mount type=bind,source="$(pwd)/src",target=/opt/src \
+    $CONTAINER_NAME \
+    pip-compile requirements.in --resolver=backtracking
+
+

src/config.py

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

src/handler.py

@@ -0,0 +1,39 @@
+from fastapi import UploadFile
+from skimage.io import imread
+from io import BytesIO
+import numpy as np
+import urllib
+from 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

@@ -0,0 +1,101 @@
+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

@@ -0,0 +1,43 @@
+from fastapi import FastAPI, UploadFile, File, HTTPException, status, Header
+
+from handler import handle_file, handle_url
+from predict import predict_model
+
+app = FastAPI()
+
+
+@app.get("/")
+async def root():
+    return {"message": "Hello World"}
+
+
+@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

@@ -0,0 +1,60 @@
+import numpy as np
+from keras.utils.data_utils import get_file
+from config import MODEL_HDF5_PATH
+
+
+LABELS = np.loadtxt("labels.txt", dtype=object, delimiter="\n")
+
+
+def initialize_model():
+    # import the necessary packages
+    from keras.models import Sequential
+    from keras.layers import BatchNormalization
+    from keras.layers.convolutional import Conv2D, MaxPooling2D
+    from keras.layers.core 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

@@ -0,0 +1,10 @@
+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

src/pyproject.toml

@@ -0,0 +1,2 @@
+[tool.black]
+line-length = 120

src/requirements.in

@@ -0,0 +1,7 @@
+keras
+tensorflow-cpu
+fastapi
+uvicorn
+scikit-image
+numpy
+python-multipart

src/requirements.txt

@@ -0,0 +1,176 @@
+#
+# This file is autogenerated by pip-compile with Python 3.8
+# by the following command:
+#
+#    pip-compile requirements.in
+#
+absl-py==1.4.0
+    # via
+    #   tensorboard
+    #   tensorflow-cpu
+anyio==3.6.2
+    # via starlette
+astunparse==1.6.3
+    # via tensorflow-cpu
+cachetools==5.3.0
+    # via google-auth
+certifi==2023.5.7
+    # via requests
+charset-normalizer==3.1.0
+    # via requests
+click==8.1.3
+    # via uvicorn
+fastapi==0.95.2
+    # via -r requirements.in
+flatbuffers==23.5.9
+    # via tensorflow-cpu
+gast==0.4.0
+    # via tensorflow-cpu
+google-auth==2.18.1
+    # via
+    #   google-auth-oauthlib
+    #   tensorboard
+google-auth-oauthlib==1.0.0
+    # via tensorboard
+google-pasta==0.2.0
+    # via tensorflow-cpu
+grpcio==1.54.2
+    # via
+    #   tensorboard
+    #   tensorflow-cpu
+h11==0.14.0
+    # via uvicorn
+h5py==3.8.0
+    # via tensorflow-cpu
+idna==3.4
+    # via
+    #   anyio
+    #   requests
+imageio==2.28.1
+    # via scikit-image
+importlib-metadata==6.6.0
+    # via markdown
+jax==0.4.10
+    # via tensorflow-cpu
+keras==2.12.0
+    # via
+    #   -r requirements.in
+    #   tensorflow-cpu
+lazy-loader==0.2
+    # via scikit-image
+libclang==16.0.0
+    # via tensorflow-cpu
+markdown==3.4.3
+    # via tensorboard
+markupsafe==2.1.2
+    # via werkzeug
+ml-dtypes==0.1.0
+    # via jax
+networkx==3.1
+    # via scikit-image
+numpy==1.23.5
+    # via
+    #   -r requirements.in
+    #   h5py
+    #   imageio
+    #   jax
+    #   ml-dtypes
+    #   opt-einsum
+    #   pywavelets
+    #   scikit-image
+    #   scipy
+    #   tensorboard
+    #   tensorflow-cpu
+    #   tifffile
+oauthlib==3.2.2
+    # via requests-oauthlib
+opt-einsum==3.3.0
+    # via
+    #   jax
+    #   tensorflow-cpu
+packaging==23.1
+    # via
+    #   scikit-image
+    #   tensorflow-cpu
+pillow==9.5.0
+    # via
+    #   imageio
+    #   scikit-image
+protobuf==4.23.1
+    # via
+    #   tensorboard
+    #   tensorflow-cpu
+pyasn1==0.5.0
+    # via
+    #   pyasn1-modules
+    #   rsa
+pyasn1-modules==0.3.0
+    # via google-auth
+pydantic==1.10.7
+    # via fastapi
+python-multipart==0.0.6
+    # via -r requirements.in
+pywavelets==1.4.1
+    # via scikit-image
+requests==2.30.0
+    # via
+    #   requests-oauthlib
+    #   tensorboard
+requests-oauthlib==1.3.1
+    # via google-auth-oauthlib
+rsa==4.9
+    # via google-auth
+scikit-image==0.20.0
+    # via -r requirements.in
+scipy==1.9.1
+    # via
+    #   jax
+    #   scikit-image
+six==1.16.0
+    # via
+    #   astunparse
+    #   google-auth
+    #   google-pasta
+    #   tensorflow-cpu
+sniffio==1.3.0
+    # via anyio
+starlette==0.27.0
+    # via fastapi
+tensorboard==2.12.3
+    # via tensorflow-cpu
+tensorboard-data-server==0.7.0
+    # via tensorboard
+tensorflow-cpu==2.12.0
+    # via -r requirements.in
+tensorflow-estimator==2.12.0
+    # via tensorflow-cpu
+tensorflow-io-gcs-filesystem==0.32.0
+    # via tensorflow-cpu
+termcolor==2.3.0
+    # via tensorflow-cpu
+tifffile==2023.4.12
+    # via scikit-image
+typing-extensions==4.5.0
+    # via
+    #   pydantic
+    #   starlette
+    #   tensorflow-cpu
+urllib3==1.26.15
+    # via
+    #   google-auth
+    #   requests
+uvicorn==0.22.0
+    # via -r requirements.in
+werkzeug==2.3.4
+    # via tensorboard
+wheel==0.40.0
+    # via
+    #   astunparse
+    #   tensorboard
+wrapt==1.14.1
+    # via tensorflow-cpu
+zipp==3.15.0
+    # via importlib-metadata
+
+# The following packages are considered to be unsafe in a requirements file:
+# setuptools